From 207692bc161f004193af4bc750703e089cb59b71 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 23:55:33 +0800 Subject: [PATCH 1/5] feat(goal): add human goal command --- docs/architecture.md | 2 +- docs/config-catalog.md | 26 +- docs/cookbook/extension-cookbook.i18n.yaml | 4 +- docs/cookbook/extension-cookbook.md | 2 +- docs/cookbook/extension-cookbook.zh.md | 2 +- docs/core-data-structures/core.md | 2 +- docs/glossary.md | 3 +- docs/module-graph.md | 15 +- docs/rfc/INDEX.md | 1 + .../feature/2026-06-30-interception-seams.md | 2 +- .../2026-07-19-human-goal-command.i18n.yaml | 6 + .../feature/2026-07-19-human-goal-command.md | 72 +++++ .../2026-07-19-human-goal-command.zh.md | 72 +++++ ...26-07-19-model-facing-goal-tools.i18n.yaml | 4 +- .../2026-07-19-model-facing-goal-tools.md | 2 +- .../2026-07-19-model-facing-goal-tools.zh.md | 2 +- examples/acp-agent/tests/acp.snapshot.ts | 2 + .../advanced-toolchain/stdout.expected.jsonl | 2 +- .../system-prompt.expected.md | 24 ++ .../tool-schemas.expected.json | 69 +++++ .../bash-spill/stdout.expected.jsonl | 2 +- .../both-mode-turn/stdout.expected.jsonl | 2 +- .../both-mode-turn/system-prompt.expected.md | 24 ++ .../both-mode-turn/tool-schemas.expected.json | 69 +++++ .../cancel-tool-calls/stdout.expected.jsonl | 2 +- .../snapshots/cancel/stdout.expected.jsonl | 2 +- .../code-mode-turn/stdout.expected.jsonl | 2 +- .../code-mode-turn/system-prompt.expected.md | 24 ++ .../stdout.expected.jsonl | 2 +- .../system-prompt.expected.md | 24 ++ .../config-options/stdout.expected.jsonl | 2 +- .../stdout.expected.jsonl | 2 +- .../error-finish/stdout.expected.jsonl | 2 +- .../escalation-approved/stdout.expected.jsonl | 2 +- .../escalation-rejected/stdout.expected.jsonl | 2 +- .../snapshots/fs-edit/stdout.expected.jsonl | 2 +- .../fs-policy-reject/stdout.expected.jsonl | 2 +- .../fs-read-window/stdout.expected.jsonl | 2 +- .../snapshots/fs-read/stdout.expected.jsonl | 2 +- .../fs-terminal-card/stdout.expected.jsonl | 2 +- .../fs-write-overwrite/stdout.expected.jsonl | 2 +- .../snapshots/fs-write/stdout.expected.jsonl | 2 +- .../snapshots/goal-command-status/input.json | 7 + .../goal-command-status/session.jsonl | 1 + .../goal-command-status/stdout.expected.jsonl | 5 + .../snapshots/handshake/stdout.expected.jsonl | 2 +- .../stdout.expected.jsonl | 2 +- .../stdout.expected.jsonl | 2 +- .../hook-cc-pretool-ask/stdout.expected.jsonl | 2 +- .../stdout.expected.jsonl | 2 +- .../stdout.expected.jsonl | 2 +- .../stdout.expected.jsonl | 2 +- .../stdout.expected.jsonl | 2 +- .../stdout.expected.jsonl | 2 +- .../stdout.expected.jsonl | 2 +- .../stdout.expected.jsonl | 2 +- .../stdout.expected.jsonl | 2 +- .../stdout.expected.jsonl | 2 +- .../stdout.expected.jsonl | 2 +- .../model-switching/stdout.expected.jsonl | 2 +- .../model-switching/system-prompt.expected.md | 4 + .../tool-schemas.expected.json | 138 ++++++++++ .../multi-turn/stdout.expected.jsonl | 2 +- .../parallel-tool-calls/stdout.expected.jsonl | 2 +- .../stdout.expected.jsonl | 2 +- .../system-prompt.expected.md | 4 + .../tool-schemas.expected.json | 138 ++++++++++ .../repeat-tool-guard/stdout.expected.jsonl | 2 +- .../skill-load/stdout.expected.jsonl | 2 +- .../skill-load/system-prompt.expected.md | 2 + .../skill-load/tool-schemas.expected.json | 69 +++++ .../subagent-fork/stdout.expected.jsonl | 2 +- .../subagent-mixed/stdout.expected.jsonl | 2 +- .../subagent-multi/stdout.expected.jsonl | 2 +- .../subagent-spawn/stdout.expected.jsonl | 2 +- .../snapshots/text-turn/stdout.expected.jsonl | 2 +- .../text-turn/system-prompt.expected.md | 2 + .../text-turn/tool-schemas.expected.json | 69 +++++ .../snapshots/todo-plan/stdout.expected.jsonl | 2 +- .../tool-call-turn/stdout.expected.jsonl | 2 +- .../workflow-run/stdout.expected.jsonl | 2 +- .../workspace-context/stdout.expected.jsonl | 2 +- .../system-prompt.expected.md | 2 + .../tool-schemas.expected.json | 69 +++++ .../workspace-edit/stdout.expected.jsonl | 2 +- .../workspace-edit/system-prompt.expected.md | 2 + .../workspace-edit/tool-schemas.expected.json | 69 +++++ .../tests/contract-regressions.spec.ts | 2 +- packages/examples/README.md | 6 +- packages/examples/acp-demo/README.md | 4 +- packages/examples/acp-demo/package.json | 2 + packages/examples/acp-demo/src/index.ts | 8 +- .../examples/acp-demo/tests/acp-agent.spec.ts | 31 ++- packages/examples/acp-demo/tsconfig.json | 3 + packages/examples/agent-spine-demo/README.md | 11 +- .../examples/agent-spine-demo/package.json | 8 +- .../examples/agent-spine-demo/src/index.ts | 33 ++- .../agent-spine-demo/tests/agent-core.spec.ts | 39 +++ .../examples/agent-spine-demo/tsconfig.json | 9 + packages/examples/stdio-demo/README.md | 5 +- packages/examples/stdio-demo/package.json | 2 + packages/examples/stdio-demo/src/index.ts | 7 + .../stdio-demo/tests/stdio-agent.spec.ts | 22 +- packages/examples/stdio-demo/tsconfig.json | 3 + packages/goal/README.md | 1 + packages/goal/command-goal/README.md | 56 ++++ packages/goal/command-goal/package.json | 38 +++ packages/goal/command-goal/src/index.ts | 165 ++++++++++++ .../command-goal/tests/command-goal.spec.ts | 254 ++++++++++++++++++ packages/goal/command-goal/tsconfig.json | 24 ++ packages/goal/tool-goal/README.md | 2 +- pnpm-lock.yaml | 48 ++++ python/sdk-runtime/package.json | 3 + tsconfig.json | 1 + 114 files changed, 1831 insertions(+), 88 deletions(-) create mode 100644 docs/rfc/implemented/feature/2026-07-19-human-goal-command.i18n.yaml create mode 100644 docs/rfc/implemented/feature/2026-07-19-human-goal-command.md create mode 100644 docs/rfc/implemented/feature/2026-07-19-human-goal-command.zh.md create mode 100644 examples/acp-agent/tests/snapshots/goal-command-status/input.json create mode 100644 examples/acp-agent/tests/snapshots/goal-command-status/session.jsonl create mode 100644 examples/acp-agent/tests/snapshots/goal-command-status/stdout.expected.jsonl create mode 100644 packages/goal/command-goal/README.md create mode 100644 packages/goal/command-goal/package.json create mode 100644 packages/goal/command-goal/src/index.ts create mode 100644 packages/goal/command-goal/tests/command-goal.spec.ts create mode 100644 packages/goal/command-goal/tsconfig.json diff --git a/docs/architecture.md b/docs/architecture.md index b83c7494bb..f32a7dbb27 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -157,7 +157,7 @@ Exceptions combine layers: LLM interface/consumer; filesystem policy; web regist ### Bundles And Apps -`dsh-agent-spine-demo` bundles the default spine ([README](../packages/examples/agent-spine-demo/README.md)). Apps add front doors; TUI/ACP mount commands ([ui/](../packages/ui/README.md)). `dsh-jsonrpc-agent` boots external `cordis.yml`, including the Python SDK default ([Python SDK](../python/README.md)). Deployments stay thin with swappable backends/tools ([examples/](../examples/AGENTS.md), [runnable wirings](cookbook/extension-cookbook.md#runnable-wirings), [graph atlas](graph-atlas.md)). +`dsh-agent-spine-demo` bundles the default spine and an opt-in persisted-goal stack ([README](../packages/examples/agent-spine-demo/README.md)). Terminal and ACP apps enable goals plus the shared `/goal` command by default; other apps choose explicitly. `dsh-jsonrpc-agent` boots external `cordis.yml`, including the Python SDK default ([Python SDK](../python/README.md)). Deployments stay thin with swappable backends/tools ([examples/](../examples/AGENTS.md), [runnable wirings](cookbook/extension-cookbook.md#runnable-wirings), [graph atlas](graph-atlas.md)). ### Where New Behavior Goes diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 15433ee095..0cbe1854e1 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -66,12 +66,14 @@ export interface Config { toolBash?: NonNullable /** Generic background-task controls forwarded through agent-core; set false to omit their tool surface. */ toolTasks?: NonNullable + /** Persisted same-session goals; owner defaults enable them, or false disables the stack and command. */ + goals?: agentCore.GoalConfig | false } ``` Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) -Source: [`packages/examples/acp-demo/src/index.ts:34`](../packages/examples/acp-demo/src/index.ts) +Source: [`packages/examples/acp-demo/src/index.ts:35`](../packages/examples/acp-demo/src/index.ts) ## `@deepseek-ai/dsh-agent-loop` @@ -115,7 +117,8 @@ Source: [`packages/core/agent-loop/src/index.ts:369`](../packages/core/agent-loo * `dshHome` to bash environment and local skill discovery, `skills` to the * skill registry/local provider/tool consumer, `workspaceContext` to the * workspace-context loader, and `toolBash`/`toolTasks` to the model-facing tool - * plugins this bundle owns. Owner schemas supply defaults for optional input; + * plugins this bundle owns. `goals` opts into and configures the persisted goal + * domain plus its model tool and same-session driver. Owner schemas supply defaults for optional input; * workspace context instead requires an explicit byte budget or `false` because * it changes model-visible input. Producer opt-in stays producer-local: * `toolBash` configures bash only; independently composed producers keep their @@ -142,6 +145,8 @@ export interface Config { toolBash?: toolBash.Config /** Generic background-task controls; set false to keep the task service without model-facing task tools. */ toolTasks?: toolTasks.Config | false + /** Opt-in persisted same-session goal stack; set false or omit to leave it unmounted. */ + goals?: GoalConfig | false } /** Skill bundle config forwarded to the registry, local provider, and model-facing consumer. */ @@ -155,11 +160,19 @@ export interface SkillConfig { /** Model-facing skill catalog and tool settings. */ tool?: toolSkill.Config } + +/** Persisted goal domain, model-tool policy, and same-session driver config. */ +export interface GoalConfig { + /** Goal-domain creation defaults. */ + domain?: GoalDomainConfig + /** Model-facing goal-tool authority policy. */ + tool?: toolGoal.Config +} ``` -Depends on: [`AgentLoopConfig`](#deepseek-aidsh-agent-loop) · [`SkillLocal`](../packages/skill/skill-local/src/index.ts) · [`SkillRegistryConfig`](#deepseek-aidsh-skill) · [`SystemPromptConfig`](#deepseek-aidsh-system-prompt) · [`toolBash`](../packages/bash/tool-bash/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`toolSkill`](../packages/skill/tool-skill/src/index.ts) · [`toolTasks`](../packages/tasks/tool-tasks/src/index.ts) · [`workspaceContext`](../packages/context/workspace-context/src/index.ts) +Depends on: [`AgentLoopConfig`](#deepseek-aidsh-agent-loop) · [`GoalDomainConfig`](#deepseek-aidsh-goal) · [`SkillLocal`](../packages/skill/skill-local/src/index.ts) · [`SkillRegistryConfig`](#deepseek-aidsh-skill) · [`SystemPromptConfig`](#deepseek-aidsh-system-prompt) · [`toolBash`](../packages/bash/tool-bash/src/index.ts) · [`toolGoal`](../packages/goal/tool-goal/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`toolSkill`](../packages/skill/tool-skill/src/index.ts) · [`toolTasks`](../packages/tasks/tool-tasks/src/index.ts) · [`workspaceContext`](../packages/context/workspace-context/src/index.ts) -Source: [`packages/examples/agent-spine-demo/src/index.ts:59`](../packages/examples/agent-spine-demo/src/index.ts) +Source: [`packages/examples/agent-spine-demo/src/index.ts:71`](../packages/examples/agent-spine-demo/src/index.ts) ## `@deepseek-ai/dsh-bash-local` @@ -878,6 +891,8 @@ export interface Config { toolBash?: NonNullable /** Generic background-task controls forwarded through agent-core; set false to omit their tool surface. */ toolTasks?: NonNullable + /** Persisted same-session goals; owner defaults enable them, or false disables the stack and command. */ + goals?: agentCore.GoalConfig | false /** * If set, the pre-created agent RESUMES this persisted session id instead of * starting fresh. Sourced from an env var in the leaf `cordis.yml` @@ -902,7 +917,7 @@ export type TerminalMode = 'auto' | 'readline' | 'tui' Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`uiTui`](../packages/ui/tui/src/index.ts) -Source: [`packages/examples/stdio-demo/src/index.ts:76`](../packages/examples/stdio-demo/src/index.ts) +Source: [`packages/examples/stdio-demo/src/index.ts:77`](../packages/examples/stdio-demo/src/index.ts) ## `@deepseek-ai/dsh-subagent-acp` @@ -1491,6 +1506,7 @@ Source: [`packages/context/workspace-context/src/config.ts:16`](../packages/cont These load from a `cordis.yml` entry with no `config:` block; they declare no config surface. - `@deepseek-ai/dsh-agent` ([`packages/core/agent/src/index.ts`](../packages/core/agent/src/index.ts)) +- `@deepseek-ai/dsh-command-goal` — requires `commands` · `goals` ([`packages/goal/command-goal/src/index.ts`](../packages/goal/command-goal/src/index.ts)) - `@deepseek-ai/dsh-commands` ([`packages/ui/commands/src/index.ts`](../packages/ui/commands/src/index.ts)) - `@deepseek-ai/dsh-fs-policy` ([`packages/fs/fs-policy/src/index.ts`](../packages/fs/fs-policy/src/index.ts)) - `@deepseek-ai/dsh-goal-session` — requires `agents` · `goals` · `sessions` ([`packages/goal/goal-session/src/index.ts`](../packages/goal/goal-session/src/index.ts)) diff --git a/docs/cookbook/extension-cookbook.i18n.yaml b/docs/cookbook/extension-cookbook.i18n.yaml index 313cb8489b..61340e9364 100644 --- a/docs/cookbook/extension-cookbook.i18n.yaml +++ b/docs/cookbook/extension-cookbook.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -extension-cookbook.md: c6bf6ddd4bf0da8bd7377ab57e779750b72bd25e -extension-cookbook.zh.md: dcc188b7d3ac44f5d86253c20147e95da0bea648 +extension-cookbook.md: 145d7fdcf779d353ddaef3070fa1fd307305c9cf +extension-cookbook.zh.md: 5e0fd8fc5fcb1d1fc2729d03cb1babd94d1bb9ab diff --git a/docs/cookbook/extension-cookbook.md b/docs/cookbook/extension-cookbook.md index c6bf6ddd4b..145d7fdcf7 100644 --- a/docs/cookbook/extension-cookbook.md +++ b/docs/cookbook/extension-cookbook.md @@ -98,7 +98,7 @@ Every product feature maps to a listener on a documented extension seam — the | Product feature | Plugin mechanism | |---|---| | Hook system (user + project level) | listeners on `agent/session-start`, `agent/prompt-submit`, `agent/request`, `agent/step-result`, `tools/pre-execute`, `tools/post-execute`, `agent/turn-continuation` — each interception waterfall returns a typed Decision; the `dsh-hooks-claude` / `dsh-hooks-codex` bridges map hook config files onto these seams | -| `/goal` | force-continue via `agent/turn-continuation` + `steer()` reminders | +| `/goal` | `ctx.goals` owns durable state, `dsh-goal-session` schedules same-session rounds through the public `Agent`, and separate command/tool producers expose human/model control | | `/loop` | on the `turn/end` session event, `send()` the next iteration; or force-continue | | Dynamic workflow | `ctx.workflows` + the worker-thread engine + the `workflow` tool; structured in-process children enforce output with scoped prompt/tool registrations, a monotonic tool guard, final `tools/result` commit (including enclosing `run_code`), and terminal `agent/turn-stop` | | Queued + steering messages | core `Agent.send()` / `Agent.steer()` | diff --git a/docs/cookbook/extension-cookbook.zh.md b/docs/cookbook/extension-cookbook.zh.md index dcc188b7d3..5e0fd8fc5f 100644 --- a/docs/cookbook/extension-cookbook.zh.md +++ b/docs/cookbook/extension-cookbook.zh.md @@ -98,7 +98,7 @@ export function apply(ctx: Context) { | 产品功能 | 插件机制 | |---|---| | 钩子系统（用户级 + 项目级） | `agent/session-start`、`agent/prompt-submit`、`agent/request`、`agent/step-result`、`tools/pre-execute`、`tools/post-execute`、`agent/turn-continuation` 上的监听器——每个拦截 waterfall 返回一个类型化 Decision；`dsh-hooks-claude` / `dsh-hooks-codex` 桥接器将钩子配置文件映射到这些 seam 上 | -| `/goal` | 通过 `agent/turn-continuation` 强制继续 + `steer()` 提醒 | +| `/goal` | `ctx.goals` 管理持久状态，`dsh-goal-session` 通过公共 `Agent` 调度同会话回合，独立的命令/工具生产方分别提供人类/模型控制 | | `/loop` | 在 `turn/end` 会话事件上 `send()` 下一次迭代；或强制继续 | | 动态工作流 | `ctx.workflows` + worker-thread 引擎 + `workflow` 工具；结构化的进程内子任务通过作用域化的 prompt/工具注册、单调工具守卫、最终 `tools/result` 提交（包括外层 `run_code`）和终端 `agent/turn-stop` 来强制输出 | | 排队消息 + steering（中途引导） | 核心 `Agent.send()` / `Agent.steer()` | diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index b89e9fa891..5de52ce8c3 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -439,7 +439,7 @@ type PromptDecision = | { kind: 'block'; reason: string } ``` -`agent/turn-continuation` returns a `ContinuationDecision` (the loop's default is `continue` when the step had tool calls or steering was injected, else `stop`; a `continue` `reason` is recorded as next-step steering in the same turn and therefore carries no context envelope or metadata — the typed `/goal` pattern): +`agent/turn-continuation` returns a `ContinuationDecision` (the loop's default is `continue` when the step had tool calls or steering was injected, else `stop`; a `continue` `reason` is recorded as next-step steering in the same turn and therefore carries no context envelope or metadata): ```ts type-equiv /** Turn continuation override; a continue reason is recorded as next-step steering in the same turn. */ diff --git a/docs/glossary.md b/docs/glossary.md index 7759f45542..9a27ead799 100644 --- a/docs/glossary.md +++ b/docs/glossary.md @@ -20,13 +20,14 @@ FIXME(glossary-completeness): Expand this glossary before the first release so i - **goal** — one durable completion objective attached to an existing session, with a revisioned lifecycle phase and a goal-round cap. A goal is state, not a scheduler or a separate conversation; the session log remains its source of truth. - **goal round** — one continuation cycle admitted for the current goal. The same-session driver materializes a goal round as one goal-sourced [turn](#turn), which can contain multiple steps; unrelated human turns in the same session do not consume the goal-round cap. -- **goal activation** — process-local permission for a continuation consumer to admit another goal round. Activation is either `armed` or `disarmed`; it is deliberately absent from durable replay, so resume and fork require a later explicit resume mutation before automatic work. +- **goal activation** — process-local permission for a continuation consumer to admit another goal round. Activation is either `armed` or `disarmed`; it is deliberately absent from durable replay, so resume and fork require a later human-authorized resume mutation through `/goal` or the model tool before automatic work. ## human command - **human command** — a slash-prefixed instruction interpreted and executed by a human-facing adapter through `ctx.commands`, without becoming a model message. It is distinct from a model-facing tool and from shell command execution through `ctx.bash`. - **command plane** — discovery, parsing, dispatch, cancellation, and result rendering owned by UI adapters and command plugins. Command output is UI state unless the handler separately mutates a durable domain. - **command surface** — the adapter identity used to filter definitions, such as `tui` or `acp`; one scoped definition may shadow a same-named global command for its exact agent. +- **goal command** — the `/goal` human command contributed by `dsh-command-goal`; it observes or mutates the current goal directly while the goal domain owns every durable, model-visible record. ## loop hierarchy diff --git a/docs/module-graph.md b/docs/module-graph.md index 7222397cd9..a9b4876334 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -29,6 +29,7 @@ flowchart TD pkg_tools["tools"] end subgraph group_goal["packages/goal"] + pkg_command_goal["command-goal"] pkg_goal["goal"] pkg_goal_session["goal-session"] pkg_tool_goal["tool-goal"] @@ -254,6 +255,8 @@ flowchart TD pkg_tools --> pkg_session pkg_tools --> pkg_system_prompt pkg_tools --> pkg_user_approval + pkg_command_goal --> pkg_commands + pkg_command_goal --> pkg_goal pkg_goal_session --> pkg_agent pkg_goal_session --> pkg_goal pkg_goal_session --> pkg_llm @@ -415,6 +418,8 @@ flowchart TD pkg_tui --> pkg_user_interaction pkg_agent_spine_demo --> pkg_agent pkg_agent_spine_demo --> pkg_agent_loop + pkg_agent_spine_demo --> pkg_goal + pkg_agent_spine_demo --> pkg_goal_session pkg_agent_spine_demo --> pkg_home pkg_agent_spine_demo --> pkg_invariants pkg_agent_spine_demo --> pkg_llm @@ -424,6 +429,7 @@ flowchart TD pkg_agent_spine_demo --> pkg_system_prompt pkg_agent_spine_demo --> pkg_tasks pkg_agent_spine_demo --> pkg_tool_bash + pkg_agent_spine_demo --> pkg_tool_goal pkg_agent_spine_demo --> pkg_tool_skill pkg_agent_spine_demo --> pkg_tool_tasks pkg_agent_spine_demo --> pkg_tools @@ -444,6 +450,7 @@ flowchart TD pkg_acp_demo --> pkg_acp pkg_acp_demo --> pkg_agent_spine_demo pkg_acp_demo --> pkg_app_boot + pkg_acp_demo --> pkg_command_goal pkg_acp_demo --> pkg_commands pkg_acp_demo --> pkg_session_persistence_jsonl pkg_acp_demo --> pkg_tools @@ -461,6 +468,7 @@ flowchart TD pkg_stdio_demo --> pkg_agent_loop pkg_stdio_demo --> pkg_agent_spine_demo pkg_stdio_demo --> pkg_app_boot + pkg_stdio_demo --> pkg_command_goal pkg_stdio_demo --> pkg_commands pkg_stdio_demo --> pkg_llm pkg_stdio_demo --> pkg_session @@ -531,6 +539,7 @@ flowchart TD | [`tasks`](../packages/tasks/tasks) | `tasks` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`session`](../packages/core/session), [`timeout`](../packages/util/timeout) | | [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/ui/user-approval) | +| [`command-goal`](../packages/goal/command-goal) | `goal` | [`commands`](../packages/ui/commands), [`goal`](../packages/goal/goal) | | [`goal-session`](../packages/goal/goal-session) | `goal` | [`agent`](../packages/core/agent), [`goal`](../packages/goal/goal), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`sandbox`](../packages/sandbox/sandbox) | | [`permission`](../packages/ui/permission) | `ui` | [`bash`](../packages/bash/bash), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`user-approval`](../packages/ui/user-approval) | @@ -562,10 +571,10 @@ flowchart TD | [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`stdio`](../packages/ui/stdio) | `ui` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`user-interaction`](../packages/ui/user-interaction) | | [`tui`](../packages/ui/tui) | `ui` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`commands`](../packages/ui/commands), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | -| [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`home`](../packages/util/home), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools), [`workspace-context`](../packages/context/workspace-context) | +| [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`home`](../packages/util/home), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tool-bash`](../packages/bash/tool-bash), [`tool-goal`](../packages/goal/tool-goal), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools), [`workspace-context`](../packages/context/workspace-context) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | -| [`acp-demo`](../packages/examples/acp-demo) | `examples` | [`acp`](../packages/ui/acp), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`commands`](../packages/ui/commands), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction), [`workspace-context`](../packages/context/workspace-context) | +| [`acp-demo`](../packages/examples/acp-demo) | `examples` | [`acp`](../packages/ui/acp), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`command-goal`](../packages/goal/command-goal), [`commands`](../packages/ui/commands), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction), [`workspace-context`](../packages/context/workspace-context) | | [`cli-demo`](../packages/examples/cli-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`workspace-context`](../packages/context/workspace-context) | -| [`stdio-demo`](../packages/examples/stdio-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`commands`](../packages/ui/commands), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`stdio`](../packages/ui/stdio), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`tui`](../packages/ui/tui), [`user-interaction`](../packages/ui/user-interaction), [`workspace-context`](../packages/context/workspace-context) | +| [`stdio-demo`](../packages/examples/stdio-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`command-goal`](../packages/goal/command-goal), [`commands`](../packages/ui/commands), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`stdio`](../packages/ui/stdio), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`tui`](../packages/ui/tui), [`user-interaction`](../packages/ui/user-interaction), [`workspace-context`](../packages/context/workspace-context) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index f7019bf60e..90e508da27 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -90,6 +90,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Optional time-context plugin](implemented/feature/2026-07-14-time-context-plugin.md) | 2026-07-14 | | [Durable per-step time context](implemented/feature/2026-07-16-durable-per-step-time-context.md) | 2026-07-16 | | [Dedicated full-screen TUI front door](implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md) | 2026-07-17 | +| [Human `/goal` command](implemented/feature/2026-07-19-human-goal-command.md) | 2026-07-19 | | [Model-facing same-session goal tools](implemented/feature/2026-07-19-model-facing-goal-tools.md) | 2026-07-19 | | [Persisted same-session goal domain](implemented/feature/2026-07-19-persisted-same-session-goal-domain.md) | 2026-07-19 | | [Plugin-owned human command registration](implemented/feature/2026-07-19-plugin-command-registration.md) | 2026-07-19 | diff --git a/docs/rfc/implemented/feature/2026-06-30-interception-seams.md b/docs/rfc/implemented/feature/2026-06-30-interception-seams.md index 1356afa06b..a69caa05ba 100644 --- a/docs/rfc/implemented/feature/2026-06-30-interception-seams.md +++ b/docs/rfc/implemented/feature/2026-06-30-interception-seams.md @@ -16,7 +16,7 @@ The canonical surface separates transformable policy, around-dispatch control, a - `agent/session-start(agent, source)` — emit, once before turn 1, carrying a `SessionStartSource` (`startup` for a fresh/forked create, `resume` for a reloaded persisted session; `clear`/`compact` reserved). A pure notification — it CANNOT block startup (a deliberate gap: a bridge logs/injects, it does not gate startup). A listener seeds context via `agent.inject()`. - `agent/prompt-submit(agent, content, source, next) → PromptDecision` — waterfall, fired per drained queued message inside the open turn, before the `user/message` append. `allow` (optionally rewriting the prompt `content` or attaching separately sourced `additionalContexts[]`) or `block` (dropping the prompt; the loop appends a durable `prompt/blocked` in its place — see the dispatch note below). -**`agent/turn-continuation`** receives and returns a `ContinuationDecision`. A `{action:'continue', reason?}` may carry model-facing content and source recorded as next-step steering in the same turn — the typed twin of the `/goal` step-end-steer pattern. It is not a `context/message`, so its type does not offer a context envelope or durable context metadata. +**`agent/turn-continuation`** receives and returns a `ContinuationDecision`. A `{action:'continue', reason?}` may carry model-facing content and source recorded as next-step steering in the same turn. It is not a `context/message`, so its type does not offer a context envelope or durable context metadata. ### The tool pipeline gives each phase one kind of authority diff --git a/docs/rfc/implemented/feature/2026-07-19-human-goal-command.i18n.yaml b/docs/rfc/implemented/feature/2026-07-19-human-goal-command.i18n.yaml new file mode 100644 index 0000000000..fb49026f5b --- /dev/null +++ b/docs/rfc/implemented/feature/2026-07-19-human-goal-command.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-19-human-goal-command.md: 5392165732b50d1422960755efea7d8f1d31aea0 +2026-07-19-human-goal-command.zh.md: ca1882fdd347dc91e504681c8f42560c83a3b589 diff --git a/docs/rfc/implemented/feature/2026-07-19-human-goal-command.md b/docs/rfc/implemented/feature/2026-07-19-human-goal-command.md new file mode 100644 index 0000000000..5392165732 --- /dev/null +++ b/docs/rfc/implemented/feature/2026-07-19-human-goal-command.md @@ -0,0 +1,72 @@ +# RFC: Human `/goal` command + +Status: implemented + +English | [中文](2026-07-19-human-goal-command.zh.md) + +## Problem + +The same-session goal domain and model tools provide the state machine and semantic natural-language path, but they are not a sufficient human UX. A user needs to inspect the exact current phase and round budget without asking the model, explicitly pause or clear work without spending a model turn, and rearm a restored active goal after the required post-resume human decision. Implementing those actions independently in TUI and ACP would duplicate parsing, let the surfaces drift, and risk routing an unknown or unavailable command into the model. + +The command must also respect the goal design's two kinds of state. Durable phase, objective, revisions, and rounds come from the session log; process-local activation decides whether an active goal may continue automatically. Showing only “active” after a resume would be misleading when the restored goal is intentionally disarmed and waiting for human authorization. + +## Decision + +`@deepseek-ai/dsh-command-goal` in `packages/goal/command-goal/` is a command producer over `ctx.commands` and `ctx.goals`. It registers one global `goal` definition for the TUI and ACP surfaces. The handler receives the exact target agent from command dispatch, reads or mutates that agent's goal through the domain service, and returns direct plain-text UI output. It does not import either adapter or the concrete agent loop. + +The command follows the compact current Codex shape documented by the [official developer-command reference](https://learn.chatgpt.com/docs/developer-commands?surface=cli): bare status, a free-form objective, and `clear`, `edit`, `pause`, or `resume` controls. This repository keeps its own event-sourced state, round-count policy, and post-resume activation rule rather than copying Codex's SQLite, token budget, or automatic-resume behavior. + +### Grammar and lifecycle verbs + +`/goal` reports the objective, human-readable durable phase, `roundsStarted/maxGoalRounds`, process-local `armed` or `disarmed` activation, and commands meaningful from that state. With no current goal it reports that fact plus complete usage. Reading status adds no session event. + +`/goal ` creates an active armed goal. A completed goal may be replaced, which creates a fresh goal identity through the existing domain rule. Any unfinished goal makes the command fail directly with instructions to use inline edit or explicit clear. The generic command service deliberately has no modal confirmation API, so silently clearing and creating two durable records would manufacture destructive consent and expose a non-atomic failure window. + +`/goal edit ` edits the current non-complete goal without changing phase or activation. On a completed goal it creates a fresh active goal because the domain does not permit completed state to resume and a new completion objective is a new goal identity. Bare `edit` is an error rather than an editor launch because ACP's shared unstructured command contract has no portable modal editor. + +`/goal pause`, `/goal resume`, and `/goal clear` call the matching compare-and-set domain verbs against the current view. Resume covers both stopped durable phases and an active-but-disarmed goal after session resume, fork, or driver replacement. Domain rules still reject exhausted round caps, redundant active/armed resume, invalid phase transitions, and stale identity. Clear removes the current pointer while the session log retains the revisioned tombstone and earlier snapshots. + +Control words are ASCII-case-insensitive after outer whitespace trimming. They are controls only when they occupy the full suffix; any other non-empty text is an objective. This matches the predictable free-form command rule: `/goal pause after verification` is a goal objective, not a partially parsed pause command. + +### Output and failure boundary + +Status output omits branded ids and compare-and-set revisions because those are model/plugin coordination details rather than human controls. It includes activation because that fact changes whether work will continue. Command hints are derived from the exact state: an armed active goal offers pause, a disarmed active or resumable stopped goal offers resume, budget-limited and completed states do not advertise an invalid resume. + +Expected `GoalError` failures become `CommandResult.error`, so invalid human operations receive a stable direct response and never enter model history. Other exceptions remain adapter-visible command failures; treating programmer faults as ordinary domain errors would hide defects. The command handler performs only synchronous domain mutations, so request cancellation is decided by the command registry before the mutation begins and there is no escaped asynchronous side effect to unwind. + +Generic slash input, status text, and errors are not persisted. Successful goal mutations use the existing `Agent.inject()` path, producing the raw model-visible goal snapshot or clear tombstone that persistence already owns. The command therefore changes no session format and introduces no second audit record that could disagree with the domain event. + +### App composition + +`agent-spine-demo` accepts an optional `goals` composition object containing the goal-domain and model-tool owner configs. Omission or `false` leaves the stack unmounted. This explicit opt-in is important for headless one-shot callers: their result API settles one correlated physical turn and must not silently become a long-running logical goal operation. + +The terminal and ACP app bundles make the opposite product choice. They default `goals` to the owner defaults, mount the goal domain, model tools, same-session driver, command registry, and this producer, and accept `goals: false` as one coherent opt-out. The TUI and ACP bridge then discover the same definition through the generic registry. The line-oriented stdio mode does not consume the command plane; a typed `/goal` there remains an ordinary human prompt that the model may interpret through its separately authorized goal tools. + +## Testing + +The producer suite uses the real command registry, goal service, agent registry, and session log. It covers Loader-safe exports, discovery on both surfaces, disposal, empty status, objective parsing, unfinished replacement refusal, inline edit, completed replacement, all missing-state controls, pause/resume/clear, every durable phase, armed/disarmed presentation, round-budget presentation, expected domain errors, unexpected failures, and persisted mutation records. App composition tests cover explicit spine opt-in, terminal/ACP defaults, coherent opt-out, forwarded domain/tool config, command discovery, and the expanded model-tool assembly. The keyless ACP snapshots pin the resulting `/goal` discovery metadata and goal tool schemas in the shipped app composition. + +## Alternatives considered + +- **Let the model handle `/goal` as ordinary text** — rejected because status and direct lifecycle actions would cost a model turn, could be reinterpreted, and would not provide deterministic ACP discovery. +- **Implement separate TUI and ACP handlers** — rejected because grammar, error behavior, and goal-state formatting would drift and optional deployments could not add or remove the capability as one effect. +- **Add modal editing and replacement confirmation to `ctx.commands`** — rejected because the existing cross-surface contract is unstructured input plus direct output; a general interaction protocol needs more than this one producer. +- **Silently replace an unfinished goal** — rejected because it combines clear and create without atomicity or explicit destructive intent. +- **Expose goal id and revision in human status** — rejected because human actions always target the exact current view inside one synchronous handler; those fields add implementation noise without preventing another race. +- **Enable goals unconditionally in the UI-less spine** — rejected because one-shot SDK/CLI settlement is a physical-turn API, not a goal-operation API. + +## Consequences + +- TUI and ACP expose one Codex-shaped `/goal` command supplied by a removable plugin. +- Human status distinguishes durable phase from live activation and reports the exact goal-round cap. +- Direct pause, resume, clear, creation, and edit consume no model turn while their accepted mutations remain reconstructable from the session log. +- Restored sessions wait for a human decision; `/goal resume` is the literal command path, while an ordinary prompt in any language may authorize the model tool path. +- Headless compositions retain one-turn behavior unless they explicitly opt into goals and define their own long-running settlement contract. + +## Known limitations and deferred work + +- The portable command contract has no modal editor or confirmation interaction; inline edit and explicit clear are intentional until a general cross-surface interaction primitive exists. +- `/goal` does not accept a per-command round cap. Deployment config owns the default, and the authorized model tool can edit a cap after direct human instruction. +- TUI and ACP render portable plain text rather than a continuously updated goal status widget. Reconnectable command output and adapter-specific status indicators are deferred. +- The line-oriented stdio and JSON-RPC front doors do not consume the command registry. +- The command observes and mutates state but does not certify completion or blockers. Evaluator-backed certification remains deferred to a separate policy layer with an explicit authority and isolation contract. diff --git a/docs/rfc/implemented/feature/2026-07-19-human-goal-command.zh.md b/docs/rfc/implemented/feature/2026-07-19-human-goal-command.zh.md new file mode 100644 index 0000000000..ca1882fdd3 --- /dev/null +++ b/docs/rfc/implemented/feature/2026-07-19-human-goal-command.zh.md @@ -0,0 +1,72 @@ +# RFC：面向人类的 `/goal` 命令 + +Status: implemented + +[English](2026-07-19-human-goal-command.md) | 中文 + +## 问题 + +同会话目标领域和模型工具提供了状态机与自然语言语义路径，但尚不足以构成面向人类的 UX。用户需要在不询问模型的情况下检查准确的当前阶段与回合预算，在不消耗模型轮次的情况下明确暂停或清除工作，并在会话恢复后经过必要的人类决策重新激活已恢复的活跃目标。若在 TUI 与 ACP 中分别实现这些操作，就会重复解析逻辑、导致两个表面发生偏差，还可能把未知或不可用的命令交给模型处理。 + +该命令还必须遵守目标设计中的两类状态。持久阶段、目标描述、修订号与回合来自会话日志；进程本地激活态决定活跃目标能否自动继续。恢复后若只显示“活跃”，就会掩盖目标已被有意设为未激活、正在等待人类授权这一事实。 + +## 决策 + +位于 `packages/goal/command-goal/` 的 `@deepseek-ai/dsh-command-goal` 是构建在 `ctx.commands` 与 `ctx.goals` 之上的命令生产方。它为 TUI 和 ACP 表面注册一个全局 `goal` 定义。处理器从命令分发接收准确的目标 agent（智能体），通过领域服务读取或改变该 agent 的目标，并返回直接的纯文本 UI 输出。它不导入任何适配器或具体 agent loop（智能体循环）。 + +该命令遵循[官方开发者命令参考](https://learn.chatgpt.com/docs/developer-commands?surface=cli)所记录的当前 Codex 紧凑形态：无参数状态查询、自由形式目标描述，以及 `clear`、`edit`、`pause` 或 `resume` 控制。本仓库保留自身的事件溯源状态、回合计数策略与恢复后激活规则，而不复制 Codex 的 SQLite、token 预算或自动恢复行为。 + +### 语法与生命周期动词 + +`/goal` 报告目标描述、面向人类的持久阶段、`roundsStarted/maxGoalRounds`、进程本地 `armed` 或 `disarmed` 激活态，以及当前状态下有意义的命令。没有当前目标时，它会报告该事实与完整用法。读取状态不会添加会话事件。 + +`/goal ` 创建活跃且已激活的目标。已完成目标可以被替换，此时通过现有领域规则创建新的目标身份。任何未完成目标都会让命令直接失败，并提示用户使用行内编辑或明确清除。通用命令服务有意不提供模态确认 API；若静默执行清除再创建两条持久记录，就等于凭空制造破坏性同意，并暴露一个非原子的失败窗口。 + +`/goal edit ` 编辑当前未完成目标，但不改变其阶段或激活态。若目标已经完成，则创建一个新的活跃目标，因为领域不允许恢复已完成状态，而新的完成条件应拥有新的目标身份。单独使用 `edit` 会返回错误而不是启动编辑器，因为 ACP 共享的非结构化命令契约没有可移植的模态编辑器。 + +`/goal pause`、`/goal resume` 与 `/goal clear` 使用当前视图调用相应的比较并交换领域动词。恢复既适用于停止的持久阶段，也适用于会话恢复、fork 或驱动器替换后处于活跃但未激活状态的目标。领域规则仍会拒绝已耗尽的回合上限、对已活跃且已激活目标的重复恢复、非法阶段转换与陈旧身份。清除会移除当前指针，而会话日志保留带修订号的墓碑和此前快照。 + +控制词会在去除两端空白后按 ASCII 大小写不敏感方式匹配。只有占据完整后缀时才被视为控制；其余任何非空文本都是目标描述。这保持了可预测的自由形式命令规则：`/goal pause after verification` 是目标描述，而不是被部分解析的暂停命令。 + +### 输出与失败边界 + +状态输出省略品牌化 id 与比较并交换修订号，因为它们属于模型/插件协调细节，而不是人类控制项。输出包含激活态，因为该事实会改变工作是否继续。命令提示从准确状态派生：已激活的活跃目标提供暂停，未激活的活跃目标或可恢复的停止目标提供恢复，受预算限制和已完成状态不会宣传非法的恢复操作。 + +预期的 `GoalError` 失败会变为 `CommandResult.error`，因此非法人类操作会收到稳定的直接响应，且绝不会进入模型历史。其他异常仍是适配器可见的命令失败；若把程序缺陷当成普通领域错误，就会隐藏问题。命令处理器只执行同步领域变更，因此请求取消会在变更开始前由命令注册表决定，不存在需要回滚的外逸异步副作用。 + +通用斜杠输入、状态文本与错误不会持久化。成功的目标变更使用现有 `Agent.inject()` 路径，产出持久化本就拥有的原始模型可见目标快照或清除墓碑。因此该命令不会改变会话格式，也不会引入可能与领域事件不一致的第二份审计记录。 + +### 应用组合 + +`agent-spine-demo` 接受可选的 `goals` 组合对象，其中包含目标领域与模型工具的所有者配置。省略或设为 `false` 时不会挂载该栈。对无头单次调用方而言，明确选择加入非常重要：它们的结果 API 会在一个相关物理轮次后结束，不能静默变成长时间运行的逻辑目标操作。 + +终端和 ACP 应用包作出相反的产品选择。它们默认让 `goals` 使用所有者默认值，挂载目标领域、模型工具、同会话驱动器、命令注册表与本生产方，并接受 `goals: false` 作为一致的整体退出选项。随后，TUI 与 ACP 桥通过通用注册表发现同一个定义。行式 stdio 模式不消费命令平面；在那里输入的 `/goal` 仍是普通人类提示词，模型可以通过独立授权的目标工具解释它。 + +## 测试 + +生产方测试套件使用真实命令注册表、目标服务、agent 注册表与会话日志。它覆盖 Loader 安全导出、两个表面的发现、资源释放、空状态、目标描述解析、拒绝未完成目标替换、行内编辑、已完成目标替换、所有缺失状态控制、暂停/恢复/清除、每个持久阶段、已激活/未激活展示、回合预算展示、预期领域错误、意外失败与持久变更记录。应用组合测试覆盖显式主干选择加入、终端/ACP 默认值、一致退出、转发的领域/工具配置、命令发现与扩展后的模型工具组装。无密钥 ACP 快照固定了交付应用组合中的 `/goal` 发现元数据和目标工具 schema。 + +## 考虑过的替代方案 + +- **让模型把 `/goal` 当作普通文本处理**——不予采纳，因为状态与直接生命周期操作会消耗模型轮次、可能被重新解释，也无法提供确定性的 ACP 发现。 +- **分别实现 TUI 和 ACP 处理器**——不予采纳，因为语法、错误行为与目标状态格式会发生偏差，可选部署也无法把该功能作为一个 effect 统一增删。 +- **为 `ctx.commands` 添加模态编辑与替换确认**——不予采纳，因为现有跨表面契约是非结构化输入加直接输出；通用交互协议所需的设计远超这一个生产方。 +- **静默替换未完成目标**——不予采纳，因为这会在没有原子性或明确破坏性意图的情况下组合清除与创建。 +- **在人类状态中暴露目标 id 与修订号**——不予采纳，因为人类操作始终在一个同步处理器内针对准确当前视图；这些字段只会增加实现噪声，无法消除其他竞争。 +- **在无 UI 主干中无条件启用目标**——不予采纳，因为单次 SDK/CLI 的结束契约是物理轮次 API，而不是目标操作 API。 + +## 后果 + +- TUI 与 ACP 暴露由可移除插件提供的同一个 Codex 形态 `/goal` 命令。 +- 人类状态会区分持久阶段与实时激活态，并报告准确的目标回合上限。 +- 直接暂停、恢复、清除、创建与编辑不消耗模型轮次，而其已接受变更仍可从会话日志重建。 +- 恢复后的会话等待人类决策；`/goal resume` 是字面命令路径，任何语言的普通提示词则可以授权模型工具路径。 +- 无头组合保持单轮行为，除非明确选择加入目标并定义自己的长时间运行结束契约。 + +## 已知限制与延期工作 + +- 可移植命令契约没有模态编辑器或确认交互；在出现通用跨表面交互原语之前，行内编辑与明确清除是有意选择。 +- `/goal` 不接受逐命令回合上限。部署配置拥有默认值；得到直接人类指示后，已授权模型工具可以编辑上限。 +- TUI 与 ACP 渲染可移植纯文本，而不是持续更新的目标状态组件。可重连命令输出和适配器专用状态指示器予以延期。 +- 行式 stdio 与 JSON-RPC 前端不消费命令注册表。 +- 该命令观察并改变状态，但不认证完成或阻塞。基于评估器的认证延期到具有明确权限与隔离契约的独立策略层。 diff --git a/docs/rfc/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml b/docs/rfc/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml index e4e0fbf855..b2b1983e31 100644 --- a/docs/rfc/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml +++ b/docs/rfc/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-19-model-facing-goal-tools.md: cb823aa944d69228005884ac73cc99b67fa00dfb -2026-07-19-model-facing-goal-tools.zh.md: f93ffa3a2eed602d8c7d98faccf09c9e46924f28 +2026-07-19-model-facing-goal-tools.md: 7b4e9aa69215ae223ec043ea9e7612757598f024 +2026-07-19-model-facing-goal-tools.zh.md: c2da32aefd41ffc0c5cf25e1db89fbe38e74b878 diff --git a/docs/rfc/implemented/feature/2026-07-19-model-facing-goal-tools.md b/docs/rfc/implemented/feature/2026-07-19-model-facing-goal-tools.md index cb823aa944..7b4e9aa692 100644 --- a/docs/rfc/implemented/feature/2026-07-19-model-facing-goal-tools.md +++ b/docs/rfc/implemented/feature/2026-07-19-model-facing-goal-tools.md @@ -61,5 +61,5 @@ Unit coverage pins registration and disposal, exclusive scheduling, generated pr - Semantic classification of a substantial goal, a request to continue, objective completion, and the same blocking condition remains model judgment. An independent evaluator or completion certificate is deferred. - These tools mutate goal state but do not schedule goal rounds, classify abnormal driver stops, or cancel an active turn; the same-session driver owns those behaviors. -- Human slash-command discovery and rendering are deferred to the command-surface layer. +- Human slash-command discovery and rendering are owned by the separate [`dsh-command-goal`](../../../../packages/goal/command-goal/README.md) plugin. - A scope can hide tool registrations while leaving the independently registered prompt section visible unless the deployment scopes both together. diff --git a/docs/rfc/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md b/docs/rfc/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md index f93ffa3a2e..c2da32aefd 100644 --- a/docs/rfc/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md +++ b/docs/rfc/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md @@ -61,5 +61,5 @@ Status: implemented - 是否属于重大目标、是否要求继续、目标是否完成以及阻塞条件是否相同，仍由模型进行语义分类。独立评估器或完成证书予以延期。 - 这些工具会改变目标状态，但不调度目标回合、不分类异常驱动停止，也不取消活跃轮次；这些行为由同会话驱动器负责。 -- 面向人类的斜杠命令发现与渲染延期到命令表面层。 +- 面向人类的斜杠命令发现与渲染由独立的 [`dsh-command-goal`](../../../../packages/goal/command-goal/README.md) 插件负责。 - 若部署没有同时设定两个注册项的作用域，某个作用域可能隐藏工具注册，却保留独立注册的提示词段。 diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index 37b420378c..c894d6f44f 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -49,6 +49,8 @@ function snapshotModeFromEnv(value: string | undefined): SnapshotSuiteOptions['m const SCENARIOS: Scenario[] = [ { name: 'handshake', hasModelTurn: false, recorded: false }, { name: 'reject-extra-dirs', hasModelTurn: false, recorded: false }, + // Direct command dispatch reports goal state without spending a model turn. + { name: 'goal-command-status', hasModelTurn: false, recorded: false }, // text-turn is the pinned-header scenario: the minimal single text turn. // Its prompt and tool-schema sidecars pin the composed header. { name: 'text-turn', hasModelTurn: true, recorded: true, pinsHeader: true }, diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.expected.jsonl index 50d688089e..beec785c9d 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-mount","title":"Mount plugin into live cordis runtime","kind":"execute","status":"in_progress","rawInput":{"code":"return { name: 'snapshot-marker', apply() {} }"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"advanced-mount","status":"completed","content":[{"type":"content","content":{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}}]}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md index b8acef973c..5ba28dca73 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md @@ -9,6 +9,8 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. + Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). @@ -61,6 +63,15 @@ declare const tools: { /** The dynamic mount id returned by cordis_mount (e.g. "dyn-1"). */ id: string; }): Promise; + /** Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say "create a goal". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority. */ + create_goal(args: { + /** The concrete completion objective inferred from the direct human request. */ + objective: string; + /** Optional positive safe-integer cap; omission uses the goal-domain deployment default. */ + max_goal_rounds?: number; + }): Promise; + /** Read the current same-session goal, including its exact id/revision, durable phase, admitted round count, cap, and live process-local activation. Call this before updating a goal. */ + get_goal(args: Record): Promise; /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */ skill(args: { /** The exact skill name from the available skills list. */ @@ -112,6 +123,19 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; + /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human turn. complete and blocked additionally accept the exact admitted goal round. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds. */ + update_goal(args: { + /** Exact id returned by get_goal. */ + goal_id: string; + /** Exact positive revision returned by get_goal. */ + revision: number; + /** edit | pause | resume | complete | blocked */ + action: "edit" | "pause" | "resume" | "complete" | "blocked"; + /** Replacement objective; valid only with action edit. */ + objective?: string; + /** Replacement cap; valid only with action edit. */ + max_goal_rounds?: number; + }): Promise; /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ workflow(args: { /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */ diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json index 978819fa1f..c27f1788e7 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json @@ -102,6 +102,34 @@ ] } }, + { + "name": "create_goal", + "description": "Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say \"create a goal\". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority.", + "parameters": { + "type": "object", + "properties": { + "objective": { + "type": "string", + "description": "The concrete completion objective inferred from the direct human request." + }, + "max_goal_rounds": { + "type": "number", + "description": "Optional positive safe-integer cap; omission uses the goal-domain deployment default." + } + }, + "required": [ + "objective" + ] + } + }, + { + "name": "get_goal", + "description": "Read the current same-session goal, including its exact id/revision, durable phase, admitted round count, cap, and live process-local activation. Call this before updating a goal.", + "parameters": { + "type": "object", + "properties": {} + } + }, { "name": "run_code", "description": "Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.", @@ -274,6 +302,47 @@ ] } }, + { + "name": "update_goal", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human turn. complete and blocked additionally accept the exact admitted goal round. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "parameters": { + "type": "object", + "properties": { + "goal_id": { + "type": "string", + "description": "Exact id returned by get_goal." + }, + "revision": { + "type": "number", + "description": "Exact positive revision returned by get_goal." + }, + "action": { + "type": "string", + "description": "edit | pause | resume | complete | blocked", + "enum": [ + "edit", + "pause", + "resume", + "complete", + "blocked" + ] + }, + "objective": { + "type": "string", + "description": "Replacement objective; valid only with action edit." + }, + "max_goal_rounds": { + "type": "number", + "description": "Replacement cap; valid only with action edit." + } + }, + "required": [ + "goal_id", + "revision", + "action" + ] + } + }, { "name": "workflow", "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.", diff --git a/examples/acp-agent/tests/snapshots/bash-spill/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/bash-spill/stdout.expected.jsonl index 875ff05303..30ed2e1e42 100644 --- a/examples/acp-agent/tests/snapshots/bash-spill/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/bash-spill/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_spill","title":"node -e \"process.stdout.write('SPILL_START-' + 'x'.repeat(2000) + '-SPILL_END')\"","kind":"execute","status":"in_progress","rawInput":"node -e \"process.stdout.write('SPILL_START-' + 'x'.repeat(2000) + '-SPILL_END')\"","content":[{"type":"content","content":{"type":"text","text":"Print large deterministic output"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_spill","status":"completed","content":[{"type":"content","content":{"type":"text","text":"```console\nSPILL_START-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx-SPILL_END\n\n(Omitted 1417 bytes. Full formatted result stored at: {{spillLocator:bash.txt}}. Use read with offset/limit, or grep this path to search within it.)\n```"}}]}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.expected.jsonl index 6c6e1d6158..3e626e9b08 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md index f1a3b9ff92..9b14172e43 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md @@ -9,6 +9,8 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. + Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). @@ -44,6 +46,15 @@ declare const tools: { /** Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access. */ justification?: string; }): Promise; + /** Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say "create a goal". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority. */ + create_goal(args: { + /** The concrete completion objective inferred from the direct human request. */ + objective: string; + /** Optional positive safe-integer cap; omission uses the goal-domain deployment default. */ + max_goal_rounds?: number; + }): Promise; + /** Read the current same-session goal, including its exact id/revision, durable phase, admitted round count, cap, and live process-local activation. Call this before updating a goal. */ + get_goal(args: Record): Promise; /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */ skill(args: { /** The exact skill name from the available skills list. */ @@ -95,6 +106,19 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; + /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human turn. complete and blocked additionally accept the exact admitted goal round. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds. */ + update_goal(args: { + /** Exact id returned by get_goal. */ + goal_id: string; + /** Exact positive revision returned by get_goal. */ + revision: number; + /** edit | pause | resume | complete | blocked */ + action: "edit" | "pause" | "resume" | "complete" | "blocked"; + /** Replacement objective; valid only with action edit. */ + objective?: string; + /** Replacement cap; valid only with action edit. */ + max_goal_rounds?: number; + }): Promise; /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ workflow(args: { /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */ diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json index edf1a7c001..5112f55a25 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json @@ -45,6 +45,34 @@ ] } }, + { + "name": "create_goal", + "description": "Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say \"create a goal\". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority.", + "parameters": { + "type": "object", + "properties": { + "objective": { + "type": "string", + "description": "The concrete completion objective inferred from the direct human request." + }, + "max_goal_rounds": { + "type": "number", + "description": "Optional positive safe-integer cap; omission uses the goal-domain deployment default." + } + }, + "required": [ + "objective" + ] + } + }, + { + "name": "get_goal", + "description": "Read the current same-session goal, including its exact id/revision, durable phase, admitted round count, cap, and live process-local activation. Call this before updating a goal.", + "parameters": { + "type": "object", + "properties": {} + } + }, { "name": "run_code", "description": "Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.", @@ -217,6 +245,47 @@ ] } }, + { + "name": "update_goal", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human turn. complete and blocked additionally accept the exact admitted goal round. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "parameters": { + "type": "object", + "properties": { + "goal_id": { + "type": "string", + "description": "Exact id returned by get_goal." + }, + "revision": { + "type": "number", + "description": "Exact positive revision returned by get_goal." + }, + "action": { + "type": "string", + "description": "edit | pause | resume | complete | blocked", + "enum": [ + "edit", + "pause", + "resume", + "complete", + "blocked" + ] + }, + "objective": { + "type": "string", + "description": "Replacement objective; valid only with action edit." + }, + "max_goal_rounds": { + "type": "number", + "description": "Replacement cap; valid only with action edit." + } + }, + "required": [ + "goal_id", + "revision", + "action" + ] + } + }, { "name": "workflow", "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.", diff --git a/examples/acp-agent/tests/snapshots/cancel-tool-calls/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/cancel-tool-calls/stdout.expected.jsonl index 1e1131398b..9bce7d7abc 100644 --- a/examples/acp-agent/tests/snapshots/cancel-tool-calls/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/cancel-tool-calls/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_wait","title":"node -e \"setInterval(() => {}, 1000)\"","kind":"execute","status":"in_progress","rawInput":"node -e \"setInterval(() => {}, 1000)\"","content":[{"type":"content","content":{"type":"text","text":"Wait until cancellation"}}]}}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/cancel/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/cancel/stdout.expected.jsonl index 0277ef2f90..9a5b62c9ff 100644 --- a/examples/acp-agent/tests/snapshots/cancel/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/cancel/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"partial"}}}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.expected.jsonl index 2e06d6839a..99392cc7bd 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md index f1a3b9ff92..9b14172e43 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md @@ -9,6 +9,8 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. + Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). @@ -44,6 +46,15 @@ declare const tools: { /** Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access. */ justification?: string; }): Promise; + /** Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say "create a goal". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority. */ + create_goal(args: { + /** The concrete completion objective inferred from the direct human request. */ + objective: string; + /** Optional positive safe-integer cap; omission uses the goal-domain deployment default. */ + max_goal_rounds?: number; + }): Promise; + /** Read the current same-session goal, including its exact id/revision, durable phase, admitted round count, cap, and live process-local activation. Call this before updating a goal. */ + get_goal(args: Record): Promise; /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */ skill(args: { /** The exact skill name from the available skills list. */ @@ -95,6 +106,19 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; + /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human turn. complete and blocked additionally accept the exact admitted goal round. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds. */ + update_goal(args: { + /** Exact id returned by get_goal. */ + goal_id: string; + /** Exact positive revision returned by get_goal. */ + revision: number; + /** edit | pause | resume | complete | blocked */ + action: "edit" | "pause" | "resume" | "complete" | "blocked"; + /** Replacement objective; valid only with action edit. */ + objective?: string; + /** Replacement cap; valid only with action edit. */ + max_goal_rounds?: number; + }): Promise; /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ workflow(args: { /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */ diff --git a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/stdout.expected.jsonl index a41a9b8b3b..ce8ff9559c 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md index cc8e2d1301..ec0b4430e1 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md @@ -15,6 +15,8 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. + Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). @@ -50,6 +52,13 @@ declare const tools: { /** Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access. */ justification?: string; }): Promise; + /** Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say "create a goal". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority. */ + create_goal(args: { + /** The concrete completion objective inferred from the direct human request. */ + objective: string; + /** Optional positive safe-integer cap; omission uses the goal-domain deployment default. */ + max_goal_rounds?: number; + }): Promise; /** Edit an existing UTF-8 text file by replacing literal text. */ edit(args: { /** Path to edit, resolved by the filesystem backend. */ @@ -61,6 +70,8 @@ declare const tools: { /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */ replace_all?: boolean; }): Promise; + /** Read the current same-session goal, including its exact id/revision, durable phase, admitted round count, cap, and live process-local activation. Call this before updating a goal. */ + get_goal(args: Record): Promise; /** Read a UTF-8 text file and return line-numbered content. */ read(args: { /** Path to read, resolved by the filesystem backend. */ @@ -121,6 +132,19 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; + /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human turn. complete and blocked additionally accept the exact admitted goal round. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds. */ + update_goal(args: { + /** Exact id returned by get_goal. */ + goal_id: string; + /** Exact positive revision returned by get_goal. */ + revision: number; + /** edit | pause | resume | complete | blocked */ + action: "edit" | "pause" | "resume" | "complete" | "blocked"; + /** Replacement objective; valid only with action edit. */ + objective?: string; + /** Replacement cap; valid only with action edit. */ + max_goal_rounds?: number; + }): Promise; /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ workflow(args: { /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */ diff --git a/examples/acp-agent/tests/snapshots/config-options/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/config-options/stdout.expected.jsonl index 4e2f95accf..bea7a201ab 100644 --- a/examples/acp-agent/tests/snapshots/config-options/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/config-options/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":4,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} diff --git a/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl index 50c05a4d18..36e8f5a465 100644 --- a/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"inspect-tools-api","title":"Inspect cordis runtime: api: tools","kind":"read","status":"in_progress"}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"inspect-tools-api","status":"completed","content":[{"type":"content","content":{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n /**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - the tool schema, execution, and optional presentation functions.\n * @returns the exact disposer that unregisters the tool.\n */\n register(definition: ToolDefinition): () => void\n /**\n * Restrict global tools for the calling agent scope. Empty filters, unknown\n * names, scope-local names, and reserved transport names fail. Restrictions\n * intersect; scoped registrations remain visible.\n * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n * @returns the exact disposer that lifts this restriction.\n */\n restrict(filter: ToolRestriction): () => void\n /**\n * Register a monotonic guard after the extensible `tools/pre-execute`\n * waterfall. A plain-context guard applies globally; one registered through\n * `agent.ctx` applies only to that agent. Any matching guard may deny by\n * returning a reason, while no guard can force-allow a call another guard\n * denied. The exact effect disposer is returned for ordered ownership and\n * HMR cleanup.\n * @param guard - synchronous check; a returned string denies the execution.\n * @returns the exact disposer that unregisters the guard.\n */\n guard(guard: ToolGuard): () => void\n /**\n * Look up a tool as one scope sees it (scoped\n * shadows global; a restricted-away global reads as absent). Presenters pass\n * the calling agent so the rendered card matches the definition that\n * actually executed.\n * @param name - the tool name as registered.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns the definition the scope resolves, or undefined when none is visible.\n */\n get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n /**\n * Project visible definitions onto the allowlisted model-facing schema fields,\n * excluding execution and presentation callbacks.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns one deep-cloned schema per visible tool.\n */\n schemas(scope?: ScopeKey): ToolSchema[]\n /**\n * Classify a pending call through the caller's visible tool definition. Only\n * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n * throwing classifiers are exclusive.\n * @param exec - call name, parsed arguments, and optional agent scope.\n * @returns the fail-closed scheduling mode.\n */\n executionMode(exec: ToolExecutionInput): ToolExecutionMode\n /**\n * Execute through pre-policy, guards, around-dispatch, post-policy, and final\n * notification. Tool and listener failures resolve as materialized error\n * results; an invisible tool reports `UNKNOWN_TOOL`. The returned outcome is\n * the same lossless, frozen snapshot final observers receive.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */\n async execute(exec: ToolExecutionInput): Promise\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n send(content: ContentBlock[], options?: SendOptions): void;\n steer(content: ContentBlock[], options?: SendOptions): void;\n inject(content: ContentBlock[], options?: InjectOptions): void;\n cancel(reason?: string): void;\n whenIdle(): Promise;\n }\n export interface AgentOptions {\n provider?: string;\n model?: string;\n }\n export type AgentStatus = 'idle' | 'running' | 'disposed';\n export type Branded = string & {\n readonly [BRAND]: B;\n };\n export type CallId = Branded<'CallId'>;\n export type ContextEnvelope = 'context' | 'raw';\n export interface DiffCallView {\n card: 'diff';\n title: string;\n diffs: FileDiff[];\n locations?: FileLocation[];\n }\n export interface DiffResultView {\n card: 'diff';\n title?: string;\n diffs: FileDiff[];\n }\n export interface FileDiff {\n path: string;\n oldText: string | null;\n newText: string;\n }\n export interface FileLocation {\n path: string;\n line?: number;\n }\n export interface GenericCallView {\n card: 'generic';\n title: string;\n kind?: ToolCallKind;\n rawInput?: unknown;\n content?: ContentBlock[];\n locations?: FileLocation[];\n }\n export interface GenericResultView {\n card: 'generic';\n title?: string;\n content?: ContentBlock[];\n }\n export interface HookContext {\n content: ContentBlock[];\n source: MessageSource;\n envelope?: ContextEnvelope;\n meta?: JsonValue;\n }\n export interface InjectOptions extends SendOptions {\n envelope?: ContextEnvelope;\n meta?: JsonValue;\n }\n export type JsonValue = null | boolean | number | string | JsonValue[] | {\n [key: string]: JsonValue;\n };\n export type MessageSource = MessageSourceMap[keyof MessageSourceMap];\n export interface MessageSourceMap {\n user: {\n kind: 'user';\n };\n plugin: {\n kind: 'plugin';\n plugin: string;\n };\n }\n export type ScopeKey = object;\n export interface SendOptions {\n source?: MessageSource;\n }\n export type SessionId = Branded<'SessionId'>;\n export interface TerminalCallView {\n card: 'terminal';\n title: string;\n description?: string;\n cwd?: string;\n }\n export interface TerminalResultView {\n card: 'terminal';\n title?: string;\n output?: string;\n exitCode?: number;\n signal?: string;\n }\n export type ToolCallKind = 'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other';\n export type ToolCallView = GenericCallView | TerminalCallView | DiffCallView;\n export interface ToolDefinition extends ToolSchema {\n execute(args: unknown, exec: ToolRunContext): Promise;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n }\n export interface ToolErrorInfo {\n name: string;\n code: string;\n }\n export type ToolExecuteReturn = ContentBlock[] | {\n content: ContentBlock[];\n meta?: unknown;\n };\n export interface ToolExecution extends ToolExecutionInput {\n readonly token: ToolExecutionToken;\n }\n export interface ToolExecutionInput {\n readonly callId: CallId;\n readonly name: string;\n readonly arguments: unknown;\n readonly agent?: Agent;\n readonly parent?: ToolExecutionToken;\n signal?: AbortSignal;\n }\n export type ToolExecutionMode = {\n kind: 'parallel';\n } | {\n kind: 'exclusive';\n };\n export interface ToolExecutionResult {\n content: ContentBlock[];\n isError: boolean;\n error?: ToolErrorInfo;\n additionalContexts?: HookContext[];\n meta?: unknown;\n }\n export type ToolExecutionToken = symbol & {\n readonly [toolExecutionTokenBrand]: true;\n };\n export type ToolGuard = (execution: Readonly) => string | undefined;\n export interface ToolRestriction {\n readonly allow?: readonly string[];\n readonly deny?: readonly string[];\n }\n export interface ToolResult {\n content: ContentBlock[];\n isError: boolean;\n meta?: unknown;\n }\n export type ToolResultView = GenericResultView | TerminalResultView | DiffResultView;\n export interface ToolRunContext extends ToolExecution {\n deferContext(context: HookContext): void;\n }\n export interface ToolSchema {\n name: string;\n description: string;\n parameters: Record;\n }"}}]}}} diff --git a/examples/acp-agent/tests/snapshots/error-finish/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/error-finish/stdout.expected.jsonl index 80ab62b674..ffbd04b32e 100644 --- a/examples/acp-agent/tests/snapshots/error-finish/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/error-finish/stdout.expected.jsonl @@ -1,4 +1,4 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"error":{"code":-32603,"message":"Internal error: turn failed: simulated provider error (HTTP 401)"}} diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/stdout.expected.jsonl index e169016a1c..4373d324d7 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-approved/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} diff --git a/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.expected.jsonl index 5a60174abb..5e6bedf862 100644 --- a/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-edit/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/fs-edit/stdout.expected.jsonl index 451fe781dd..59550792de 100644 --- a/examples/acp-agent/tests/snapshots/fs-edit/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-edit/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.expected.jsonl index 39ddf764de..4775a2a4cb 100644 --- a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.expected.jsonl index 2f2e1bc667..f8986d5e02 100644 --- a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/fs-read/stdout.expected.jsonl index 3fed936cfc..b553d503b5 100644 --- a/examples/acp-agent/tests/snapshots/fs-read/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.expected.jsonl index 51bb5f7c65..c24f5b4383 100644 --- a/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.expected.jsonl index 9e0d057b2a..7517f30768 100644 --- a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/fs-write/stdout.expected.jsonl index 927bb99975..8d0043ab6b 100644 --- a/examples/acp-agent/tests/snapshots/fs-write/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/goal-command-status/input.json b/examples/acp-agent/tests/snapshots/goal-command-status/input.json new file mode 100644 index 0000000000..0bc0192c93 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/goal-command-status/input.json @@ -0,0 +1,7 @@ +{ + "steps": [ + { "op": "initialize" }, + { "op": "newSession" }, + { "op": "prompt", "text": "/goal" } + ] +} diff --git a/examples/acp-agent/tests/snapshots/goal-command-status/session.jsonl b/examples/acp-agent/tests/snapshots/goal-command-status/session.jsonl new file mode 100644 index 0000000000..a6f73319bc --- /dev/null +++ b/examples/acp-agent/tests/snapshots/goal-command-status/session.jsonl @@ -0,0 +1 @@ +{"type":"session","version":0,"id":"00000000-0000-0000-0000-000000000000","createdAt":0} diff --git a/examples/acp-agent/tests/snapshots/goal-command-status/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/goal-command-status/stdout.expected.jsonl new file mode 100644 index 0000000000..568b5a8f46 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/goal-command-status/stdout.expected.jsonl @@ -0,0 +1,5 @@ +{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"No goal is currently set.\nUsage: /goal [|clear|edit |pause|resume]"}}}} +{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} diff --git a/examples/acp-agent/tests/snapshots/handshake/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/handshake/stdout.expected.jsonl index 1390e424d6..54ed9b292e 100644 --- a/examples/acp-agent/tests/snapshots/handshake/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/handshake/stdout.expected.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.expected.jsonl index 89e476b3e8..9d3e34dd57 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.expected.jsonl index b13a498bc0..d50c69954e 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.expected.jsonl index 5acbeb7202..8addaad274 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.expected.jsonl index 623127e083..d28e38a28e 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.expected.jsonl index 19ec84b738..dfb95675e7 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.expected.jsonl @@ -1,4 +1,4 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.expected.jsonl index 3f75a15f57..12cc700248 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.expected.jsonl index bf478888b4..87d4aa1b16 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.expected.jsonl index b8b6abe2c3..2ce2a388b8 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.expected.jsonl index c8c34ab6ec..f59c72c0b4 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.expected.jsonl index 8e303806a9..4a75fac864 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.expected.jsonl index 19ec84b738..dfb95675e7 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.expected.jsonl @@ -1,4 +1,4 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.expected.jsonl index 6107da23da..72bce49963 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.expected.jsonl index ef02915d01..c308028ff2 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/model-switching/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/model-switching/stdout.expected.jsonl index e3a5aacbeb..e236bfee60 100644 --- a/examples/acp-agent/tests/snapshots/model-switching/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/model-switching/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/model-switching/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/model-switching/system-prompt.expected.md index b9701e538c..f81876701a 100644 --- a/examples/acp-agent/tests/snapshots/model-switching/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/model-switching/system-prompt.expected.md @@ -9,6 +9,8 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. + Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). @@ -27,6 +29,8 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. + Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/model-switching/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/model-switching/tool-schemas.expected.json index 7c814257fb..bae7be5f6b 100644 --- a/examples/acp-agent/tests/snapshots/model-switching/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/model-switching/tool-schemas.expected.json @@ -45,6 +45,34 @@ ] } }, + { + "name": "create_goal", + "description": "Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say \"create a goal\". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority.", + "parameters": { + "type": "object", + "properties": { + "objective": { + "type": "string", + "description": "The concrete completion objective inferred from the direct human request." + }, + "max_goal_rounds": { + "type": "number", + "description": "Optional positive safe-integer cap; omission uses the goal-domain deployment default." + } + }, + "required": [ + "objective" + ] + } + }, + { + "name": "get_goal", + "description": "Read the current same-session goal, including its exact id/revision, durable phase, admitted round count, cap, and live process-local activation. Call this before updating a goal.", + "parameters": { + "type": "object", + "properties": {} + } + }, { "name": "skill", "description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.", @@ -201,6 +229,47 @@ ] } }, + { + "name": "update_goal", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human turn. complete and blocked additionally accept the exact admitted goal round. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "parameters": { + "type": "object", + "properties": { + "goal_id": { + "type": "string", + "description": "Exact id returned by get_goal." + }, + "revision": { + "type": "number", + "description": "Exact positive revision returned by get_goal." + }, + "action": { + "type": "string", + "description": "edit | pause | resume | complete | blocked", + "enum": [ + "edit", + "pause", + "resume", + "complete", + "blocked" + ] + }, + "objective": { + "type": "string", + "description": "Replacement objective; valid only with action edit." + }, + "max_goal_rounds": { + "type": "number", + "description": "Replacement cap; valid only with action edit." + } + }, + "required": [ + "goal_id", + "revision", + "action" + ] + } + }, { "name": "workflow", "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.", @@ -320,6 +389,34 @@ ] } }, + { + "name": "create_goal", + "description": "Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say \"create a goal\". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority.", + "parameters": { + "type": "object", + "properties": { + "objective": { + "type": "string", + "description": "The concrete completion objective inferred from the direct human request." + }, + "max_goal_rounds": { + "type": "number", + "description": "Optional positive safe-integer cap; omission uses the goal-domain deployment default." + } + }, + "required": [ + "objective" + ] + } + }, + { + "name": "get_goal", + "description": "Read the current same-session goal, including its exact id/revision, durable phase, admitted round count, cap, and live process-local activation. Call this before updating a goal.", + "parameters": { + "type": "object", + "properties": {} + } + }, { "name": "skill", "description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.", @@ -476,6 +573,47 @@ ] } }, + { + "name": "update_goal", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human turn. complete and blocked additionally accept the exact admitted goal round. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "parameters": { + "type": "object", + "properties": { + "goal_id": { + "type": "string", + "description": "Exact id returned by get_goal." + }, + "revision": { + "type": "number", + "description": "Exact positive revision returned by get_goal." + }, + "action": { + "type": "string", + "description": "edit | pause | resume | complete | blocked", + "enum": [ + "edit", + "pause", + "resume", + "complete", + "blocked" + ] + }, + "objective": { + "type": "string", + "description": "Replacement objective; valid only with action edit." + }, + "max_goal_rounds": { + "type": "number", + "description": "Replacement cap; valid only with action edit." + } + }, + "required": [ + "goal_id", + "revision", + "action" + ] + } + }, { "name": "workflow", "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.", diff --git a/examples/acp-agent/tests/snapshots/multi-turn/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/multi-turn/stdout.expected.jsonl index 57dd33f320..d3a40dad97 100644 --- a/examples/acp-agent/tests/snapshots/multi-turn/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/multi-turn/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.expected.jsonl index 53048fa11d..0961149943 100644 --- a/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_read_a","title":"Read a.txt","kind":"read","status":"in_progress","locations":[{"path":"a.txt","line":1}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_read_b","title":"Read b.txt","kind":"read","status":"in_progress","locations":[{"path":"b.txt","line":1}]}}} diff --git a/examples/acp-agent/tests/snapshots/permission-switching/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/stdout.expected.jsonl index 2232cd3a1c..ea46e09493 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/permission-switching/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} diff --git a/examples/acp-agent/tests/snapshots/permission-switching/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/permission-switching/system-prompt.expected.md index 622bc4e23a..82335a7f1e 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/permission-switching/system-prompt.expected.md @@ -9,6 +9,8 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. + Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls. @@ -26,6 +28,8 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. + Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.expected.json index 7c814257fb..bae7be5f6b 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.expected.json @@ -45,6 +45,34 @@ ] } }, + { + "name": "create_goal", + "description": "Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say \"create a goal\". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority.", + "parameters": { + "type": "object", + "properties": { + "objective": { + "type": "string", + "description": "The concrete completion objective inferred from the direct human request." + }, + "max_goal_rounds": { + "type": "number", + "description": "Optional positive safe-integer cap; omission uses the goal-domain deployment default." + } + }, + "required": [ + "objective" + ] + } + }, + { + "name": "get_goal", + "description": "Read the current same-session goal, including its exact id/revision, durable phase, admitted round count, cap, and live process-local activation. Call this before updating a goal.", + "parameters": { + "type": "object", + "properties": {} + } + }, { "name": "skill", "description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.", @@ -201,6 +229,47 @@ ] } }, + { + "name": "update_goal", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human turn. complete and blocked additionally accept the exact admitted goal round. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "parameters": { + "type": "object", + "properties": { + "goal_id": { + "type": "string", + "description": "Exact id returned by get_goal." + }, + "revision": { + "type": "number", + "description": "Exact positive revision returned by get_goal." + }, + "action": { + "type": "string", + "description": "edit | pause | resume | complete | blocked", + "enum": [ + "edit", + "pause", + "resume", + "complete", + "blocked" + ] + }, + "objective": { + "type": "string", + "description": "Replacement objective; valid only with action edit." + }, + "max_goal_rounds": { + "type": "number", + "description": "Replacement cap; valid only with action edit." + } + }, + "required": [ + "goal_id", + "revision", + "action" + ] + } + }, { "name": "workflow", "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.", @@ -320,6 +389,34 @@ ] } }, + { + "name": "create_goal", + "description": "Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say \"create a goal\". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority.", + "parameters": { + "type": "object", + "properties": { + "objective": { + "type": "string", + "description": "The concrete completion objective inferred from the direct human request." + }, + "max_goal_rounds": { + "type": "number", + "description": "Optional positive safe-integer cap; omission uses the goal-domain deployment default." + } + }, + "required": [ + "objective" + ] + } + }, + { + "name": "get_goal", + "description": "Read the current same-session goal, including its exact id/revision, durable phase, admitted round count, cap, and live process-local activation. Call this before updating a goal.", + "parameters": { + "type": "object", + "properties": {} + } + }, { "name": "skill", "description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.", @@ -476,6 +573,47 @@ ] } }, + { + "name": "update_goal", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human turn. complete and blocked additionally accept the exact admitted goal round. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "parameters": { + "type": "object", + "properties": { + "goal_id": { + "type": "string", + "description": "Exact id returned by get_goal." + }, + "revision": { + "type": "number", + "description": "Exact positive revision returned by get_goal." + }, + "action": { + "type": "string", + "description": "edit | pause | resume | complete | blocked", + "enum": [ + "edit", + "pause", + "resume", + "complete", + "blocked" + ] + }, + "objective": { + "type": "string", + "description": "Replacement objective; valid only with action edit." + }, + "max_goal_rounds": { + "type": "number", + "description": "Replacement cap; valid only with action edit." + } + }, + "required": [ + "goal_id", + "revision", + "action" + ] + } + }, { "name": "workflow", "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.", diff --git a/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.expected.jsonl index bc40beb3fe..d1b75d0d98 100644 --- a/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_1","title":"Update todo list","kind":"other","status":"in_progress","rawInput":[{"content":"watch the kettle boil","status":"in_progress"}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"plan","entries":[{"content":"watch the kettle boil","priority":"medium","status":"in_progress"}]}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/skill-load/stdout.expected.jsonl index 8436971982..1259c06086 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Load the requested skill."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_skill_load","title":"Load skill snapshot-skill","kind":"read","status":"in_progress","rawInput":"snapshot-skill"}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md index 43ecb9746f..87818d5b6d 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md @@ -9,6 +9,8 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. + Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json index e422a063da..0680b50e05 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json @@ -45,6 +45,34 @@ ] } }, + { + "name": "create_goal", + "description": "Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say \"create a goal\". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority.", + "parameters": { + "type": "object", + "properties": { + "objective": { + "type": "string", + "description": "The concrete completion objective inferred from the direct human request." + }, + "max_goal_rounds": { + "type": "number", + "description": "Optional positive safe-integer cap; omission uses the goal-domain deployment default." + } + }, + "required": [ + "objective" + ] + } + }, + { + "name": "get_goal", + "description": "Read the current same-session goal, including its exact id/revision, durable phase, admitted round count, cap, and live process-local activation. Call this before updating a goal.", + "parameters": { + "type": "object", + "properties": {} + } + }, { "name": "skill", "description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.", @@ -201,6 +229,47 @@ ] } }, + { + "name": "update_goal", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human turn. complete and blocked additionally accept the exact admitted goal round. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "parameters": { + "type": "object", + "properties": { + "goal_id": { + "type": "string", + "description": "Exact id returned by get_goal." + }, + "revision": { + "type": "number", + "description": "Exact positive revision returned by get_goal." + }, + "action": { + "type": "string", + "description": "edit | pause | resume | complete | blocked", + "enum": [ + "edit", + "pause", + "resume", + "complete", + "blocked" + ] + }, + "objective": { + "type": "string", + "description": "Replacement objective; valid only with action edit." + }, + "max_goal_rounds": { + "type": "number", + "description": "Replacement cap; valid only with action edit." + } + }, + "required": [ + "goal_id", + "revision", + "action" + ] + } + }, { "name": "workflow", "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.", diff --git a/examples/acp-agent/tests/snapshots/subagent-fork/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/subagent-fork/stdout.expected.jsonl index a332ea7a7c..15ae069004 100644 --- a/examples/acp-agent/tests/snapshots/subagent-fork/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-fork/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.expected.jsonl index ded1ec01cc..d4007eb8be 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/stdout.expected.jsonl index d25e78d0db..eca8dc0fc8 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.expected.jsonl index d1f79bacac..9ab55a7389 100644 --- a/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/text-turn/stdout.expected.jsonl index dc7b4dbe25..20c758bc59 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md index 43ecb9746f..87818d5b6d 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md @@ -9,6 +9,8 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. + Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json index e422a063da..0680b50e05 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json @@ -45,6 +45,34 @@ ] } }, + { + "name": "create_goal", + "description": "Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say \"create a goal\". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority.", + "parameters": { + "type": "object", + "properties": { + "objective": { + "type": "string", + "description": "The concrete completion objective inferred from the direct human request." + }, + "max_goal_rounds": { + "type": "number", + "description": "Optional positive safe-integer cap; omission uses the goal-domain deployment default." + } + }, + "required": [ + "objective" + ] + } + }, + { + "name": "get_goal", + "description": "Read the current same-session goal, including its exact id/revision, durable phase, admitted round count, cap, and live process-local activation. Call this before updating a goal.", + "parameters": { + "type": "object", + "properties": {} + } + }, { "name": "skill", "description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.", @@ -201,6 +229,47 @@ ] } }, + { + "name": "update_goal", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human turn. complete and blocked additionally accept the exact admitted goal round. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "parameters": { + "type": "object", + "properties": { + "goal_id": { + "type": "string", + "description": "Exact id returned by get_goal." + }, + "revision": { + "type": "number", + "description": "Exact positive revision returned by get_goal." + }, + "action": { + "type": "string", + "description": "edit | pause | resume | complete | blocked", + "enum": [ + "edit", + "pause", + "resume", + "complete", + "blocked" + ] + }, + "objective": { + "type": "string", + "description": "Replacement objective; valid only with action edit." + }, + "max_goal_rounds": { + "type": "number", + "description": "Replacement cap; valid only with action edit." + } + }, + "required": [ + "goal_id", + "revision", + "action" + ] + } + }, { "name": "workflow", "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.", diff --git a/examples/acp-agent/tests/snapshots/todo-plan/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/todo-plan/stdout.expected.jsonl index 0cae765592..0a32a02746 100644 --- a/examples/acp-agent/tests/snapshots/todo-plan/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/todo-plan/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.expected.jsonl index dce9237834..8f4bc536fa 100644 --- a/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/workflow-run/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/workflow-run/stdout.expected.jsonl index 73604add34..37626e6b7d 100644 --- a/examples/acp-agent/tests/snapshots/workflow-run/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/workflow-run/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/workspace-context/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/workspace-context/stdout.expected.jsonl index 8108f47bb0..707d7a1c48 100644 --- a/examples/acp-agent/tests/snapshots/workspace-context/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/workspace-context/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_workspace_read","title":"Read nested/task.txt","kind":"read","status":"in_progress","locations":[{"path":"nested/task.txt","line":1}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_workspace_read","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/nested/task.txt\nfile\n\n1: snapshot task\n\n(End of file - total 1 lines)\n"}}]}}} diff --git a/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md index b1fc71924b..6f49fcf1c2 100644 --- a/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md @@ -15,6 +15,8 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. + Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json index 4b08a1e365..0ef5307126 100644 --- a/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json @@ -45,6 +45,26 @@ ] } }, + { + "name": "create_goal", + "description": "Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say \"create a goal\". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority.", + "parameters": { + "type": "object", + "properties": { + "objective": { + "type": "string", + "description": "The concrete completion objective inferred from the direct human request." + }, + "max_goal_rounds": { + "type": "number", + "description": "Optional positive safe-integer cap; omission uses the goal-domain deployment default." + } + }, + "required": [ + "objective" + ] + } + }, { "name": "edit", "description": "Edit an existing UTF-8 text file by replacing literal text.", @@ -75,6 +95,14 @@ ] } }, + { + "name": "get_goal", + "description": "Read the current same-session goal, including its exact id/revision, durable phase, admitted round count, cap, and live process-local activation. Call this before updating a goal.", + "parameters": { + "type": "object", + "properties": {} + } + }, { "name": "read", "description": "Read a UTF-8 text file and return line-numbered content.", @@ -255,6 +283,47 @@ ] } }, + { + "name": "update_goal", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human turn. complete and blocked additionally accept the exact admitted goal round. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "parameters": { + "type": "object", + "properties": { + "goal_id": { + "type": "string", + "description": "Exact id returned by get_goal." + }, + "revision": { + "type": "number", + "description": "Exact positive revision returned by get_goal." + }, + "action": { + "type": "string", + "description": "edit | pause | resume | complete | blocked", + "enum": [ + "edit", + "pause", + "resume", + "complete", + "blocked" + ] + }, + "objective": { + "type": "string", + "description": "Replacement objective; valid only with action edit." + }, + "max_goal_rounds": { + "type": "number", + "description": "Replacement cap; valid only with action edit." + } + }, + "required": [ + "goal_id", + "revision", + "action" + ] + } + }, { "name": "workflow", "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.", diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.expected.jsonl index ff2610f1f5..81087ddd50 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.expected.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.expected.md index ddf502a773..4af39f6b4b 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.expected.md @@ -15,6 +15,8 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. + Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.expected.json index 4b08a1e365..0ef5307126 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.expected.json @@ -45,6 +45,26 @@ ] } }, + { + "name": "create_goal", + "description": "Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say \"create a goal\". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority.", + "parameters": { + "type": "object", + "properties": { + "objective": { + "type": "string", + "description": "The concrete completion objective inferred from the direct human request." + }, + "max_goal_rounds": { + "type": "number", + "description": "Optional positive safe-integer cap; omission uses the goal-domain deployment default." + } + }, + "required": [ + "objective" + ] + } + }, { "name": "edit", "description": "Edit an existing UTF-8 text file by replacing literal text.", @@ -75,6 +95,14 @@ ] } }, + { + "name": "get_goal", + "description": "Read the current same-session goal, including its exact id/revision, durable phase, admitted round count, cap, and live process-local activation. Call this before updating a goal.", + "parameters": { + "type": "object", + "properties": {} + } + }, { "name": "read", "description": "Read a UTF-8 text file and return line-numbered content.", @@ -255,6 +283,47 @@ ] } }, + { + "name": "update_goal", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human turn. complete and blocked additionally accept the exact admitted goal round. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "parameters": { + "type": "object", + "properties": { + "goal_id": { + "type": "string", + "description": "Exact id returned by get_goal." + }, + "revision": { + "type": "number", + "description": "Exact positive revision returned by get_goal." + }, + "action": { + "type": "string", + "description": "edit | pause | resume | complete | blocked", + "enum": [ + "edit", + "pause", + "resume", + "complete", + "blocked" + ] + }, + "objective": { + "type": "string", + "description": "Replacement objective; valid only with action edit." + }, + "max_goal_rounds": { + "type": "number", + "description": "Replacement cap; valid only with action edit." + } + }, + "required": [ + "goal_id", + "revision", + "action" + ] + } + }, { "name": "workflow", "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.", diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index 80d085c32b..0ab78067e9 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -523,7 +523,7 @@ describe('steering from late extension points is never stranded', () => { expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('one more thing') }) - it('steer() from a step/end session-event listener forces a SAME-TURN next step (/goal pattern)', async () => { + it('steer() from a step/end session-event listener forces a SAME-TURN next step', async () => { // Assert the same-turn shape; content alone cannot distinguish re-enqueue. const adapter = new MockAdapter([ textResponse('no tools, would stop'), diff --git a/packages/examples/README.md b/packages/examples/README.md index 58cffeabac..32e287456d 100644 --- a/packages/examples/README.md +++ b/packages/examples/README.md @@ -4,10 +4,10 @@ Pre-composed plugin bundles a thin leaf `cordis.yml` loads instead of assembling | Package | npm name | Role | |---|---|---| -| `agent-spine-demo/` | `@deepseek-ai/dsh-agent-spine-demo` | The executor-less/UI-less agent spine as one bundle plugin (`timer` + `llm` + sessions + system-prompt + tools + skills + agents + invariants + `tool-bash` + workspace-context + `tool-skill` + `agent-loop`) | -| `stdio-demo/` | `@deepseek-ai/dsh-stdio-demo` | Terminal chat app: the spine + command registry + JSONL persistence + TTY-selected `dsh-tui`/`dsh-stdio` front door + a pre-created `main` agent, with a boot `bin` | +| `agent-spine-demo/` | `@deepseek-ai/dsh-agent-spine-demo` | The executor-less/UI-less agent spine as one bundle plugin, with an opt-in persisted-goal stack | +| `stdio-demo/` | `@deepseek-ai/dsh-stdio-demo` | Terminal chat app: the spine + persisted goals + `/goal` command + JSONL persistence + TTY-selected `dsh-tui`/`dsh-stdio` front door + a pre-created `main` agent, with a boot `bin` | | `cli-demo/` | `@deepseek-ai/dsh-cli-demo` | Headless one-shot app: the spine + JSONL persistence + a pre-created `main` agent, with text and DSH-native JSON output | -| `acp-demo/` | `@deepseek-ai/dsh-acp-demo` | ACP server app: the spine + command registry + JSONL persistence + the [`acp`](../ui/acp/README.md) bridge (no stdout logger), with a boot `bin` | +| `acp-demo/` | `@deepseek-ai/dsh-acp-demo` | ACP server app: the spine + persisted goals + `/goal` command + JSONL persistence + the [`acp`](../ui/acp/README.md) bridge (no stdout logger), with a boot `bin` | | `jsonrpc-demo/` | `@deepseek-ai/dsh-jsonrpc-demo` | Bin-only runtime that boots an external `cordis.yml` for the stdio JSON-RPC SDK client | `agent-spine-demo` is the shared bundle; `stdio-demo`, `cli-demo`, and `acp-demo` compose it with terminal, headless one-shot, and ACP front doors and own their boot bins. `jsonrpc-demo` mounts no composition of its own — it boots whatever tree the deployment's `cordis.yml` names, and is what the Python SDK runtime launches. diff --git a/packages/examples/acp-demo/README.md b/packages/examples/acp-demo/README.md index d215cbcbbe..80593e38ec 100644 --- a/packages/examples/acp-demo/README.md +++ b/packages/examples/acp-demo/README.md @@ -12,6 +12,7 @@ stdout is the ACP JSON-RPC channel, so the cluster is defined as much by what it |---|---| | `@deepseek-ai/dsh-agent-spine-demo` | the spine, pre-creating **no** agents (ACP `session/new` creates them on demand) | | `@deepseek-ai/dsh-commands` | the human-command registry used for ACP discovery and direct slash dispatch | +| `@deepseek-ai/dsh-command-goal` | the discoverable direct `/goal` producer; the app enables the spine's persisted-goal stack with it | | `@deepseek-ai/dsh-user-interaction` | the human question/answer seam used by clients that can complete ACP elicitation requests | | `@deepseek-ai/dsh-session-persistence-jsonl` | durable JSONL session log (the bridge advertises `loadSession`) | | `@deepseek-ai/dsh-acp` | the bridge that owns stdout for JSON-RPC and provides ACP-backed user answers when a leaf explicitly exposes a user-question tool | @@ -36,6 +37,7 @@ Because the package wires no logger entry, an ACP leaf has **nothing to get wron | `skills` | owner defaults | registry-cache, local-provider, and model-facing skill-tool config, routed through `dsh-agent-spine-demo` | | `toolBash` | owner defaults | model-facing bash config routed through `dsh-agent-spine-demo`, including bash's producer-local `enableRunInBackground` | | `toolTasks` | owner defaults | generic `task_output` wait bounds routed through `dsh-agent-spine-demo` | +| `goals` | owner defaults | persisted goal-domain and model-tool config; `false` removes the goal stack and `/goal` producer | | `persistenceRoot` | `./.sessions` | the JSONL backend's root directory | The leaf supplies the swappable backends: an LLM adapter (`llm-deepseek` for the real model, `llm-replay` for keyless snapshot replay) and a bash executor. @@ -54,7 +56,7 @@ All diagnostics go to **stderr** — stdout is the protocol. ## Model Experience -Indirectly, through `dsh-agent-spine-demo` and `dsh-acp`, which compose each ACP agent's prompt, tools, and message history; this app bundle adds no model-bound content itself. +Indirectly, through `dsh-agent-spine-demo` and `dsh-acp`, which compose each ACP agent's prompt, goal tools, and message history. Direct `/goal` input and output remain outside the model, while accepted mutations append domain-owned model-visible snapshots. #### KV Cache effect diff --git a/packages/examples/acp-demo/package.json b/packages/examples/acp-demo/package.json index f74617f306..1343e9f713 100644 --- a/packages/examples/acp-demo/package.json +++ b/packages/examples/acp-demo/package.json @@ -35,6 +35,7 @@ "@deepseek-ai/dsh-app-boot": "^0.0.1", "@deepseek-ai/dsh-acp": "^0.0.1", "@deepseek-ai/dsh-commands": "^0.0.1", + "@deepseek-ai/dsh-command-goal": "^0.0.1", "@deepseek-ai/dsh-agent-spine-demo": "^0.0.1", "@deepseek-ai/dsh-workspace-context": "^0.0.1", "@deepseek-ai/dsh-session-persistence-jsonl": "^0.0.1", @@ -49,6 +50,7 @@ "@deepseek-ai/dsh-app-boot": "workspace:^", "@deepseek-ai/dsh-acp": "workspace:^", "@deepseek-ai/dsh-commands": "workspace:^", + "@deepseek-ai/dsh-command-goal": "workspace:^", "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-spine-demo": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", diff --git a/packages/examples/acp-demo/src/index.ts b/packages/examples/acp-demo/src/index.ts index 4000954c72..e44135d8d1 100644 --- a/packages/examples/acp-demo/src/index.ts +++ b/packages/examples/acp-demo/src/index.ts @@ -13,6 +13,7 @@ import type { Context } from 'cordis' import z from 'schemastery' import * as acp from '@deepseek-ai/dsh-acp' import CommandService from '@deepseek-ai/dsh-commands' +import * as commandGoal from '@deepseek-ai/dsh-command-goal' import * as agentCore from '@deepseek-ai/dsh-agent-spine-demo' import * as workspaceContext from '@deepseek-ai/dsh-workspace-context' import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools' @@ -56,6 +57,8 @@ export interface Config { toolBash?: NonNullable /** Generic background-task controls forwarded through agent-core; set false to omit their tool surface. */ toolTasks?: NonNullable + /** Persisted same-session goals; owner defaults enable them, or false disables the stack and command. */ + goals?: agentCore.GoalConfig | false } // Each front door owns a complete, directly readable config schema; extracting @@ -77,6 +80,7 @@ export const Config: z = z.object({ skills: agentCore.SkillConfigSchema, toolBash: agentCore.ToolBashConfigSchema, toolTasks: z.union([z.const(false), agentCore.ToolTasksConfigSchema]), + goals: z.union([z.const(false), agentCore.GoalConfigSchema]), }) /* jscpd:ignore-end */ @@ -88,8 +92,10 @@ export const Config: z = z.object({ * from the provider/model pair. No logger, no `hmr` — stdout stays pure. */ export function apply(ctx: Context, config: Config): void { + const goals = config.goals ?? {} ctx.plugin(CommandService) - ctx.plugin(agentCore, agentCore.pickSpineConfig(config)) + if (goals !== false) ctx.plugin(commandGoal) + ctx.plugin(agentCore, { ...agentCore.pickSpineConfig(config), goals }) ctx.plugin(UserInteractionService) ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? DEFAULT_PERSISTENCE_ROOT }) ctx.plugin(acp, { provider: config.provider, model: config.model }) diff --git a/packages/examples/acp-demo/tests/acp-agent.spec.ts b/packages/examples/acp-demo/tests/acp-agent.spec.ts index 10ee749f8c..a9a1d6178d 100644 --- a/packages/examples/acp-demo/tests/acp-agent.spec.ts +++ b/packages/examples/acp-demo/tests/acp-agent.spec.ts @@ -77,11 +77,30 @@ describe('dsh-acp-demo composition', () => { expect(ctx.get('agentLoop')).toBeDefined() expect(ctx.get('userInteraction')).toBeDefined() expect(ctx.get('tools')?.get('ask_user_question')).toBeUndefined() + expect(ctx.get('goals')).toBeDefined() + expect(ctx.get('tools')?.get('get_goal')).toBeDefined() // No pre-created agents — ACP session/new creates them on demand. expect(ctx.get('agents')!.list()).toHaveLength(0) await ctx.fiber.dispose() }) + it('can explicitly omit the persisted-goal stack and its command', async () => { + const ctx = await mount({ + provider: 'mock', + model: 'mock', + goals: false, + workspaceContext: false, + }) + expect(ctx.get('goals')).toBeUndefined() + const handle = await ctx.agents.create({ + sessionId: 'disabled-goals' as import('@deepseek-ai/dsh-session').SessionId, + agentOptions: { provider: 'mock', model: 'mock' }, + }) + expect(ctx.commands.find(handle.agent, 'acp', 'goal')).toBeUndefined() + await handle.dispose() + await ctx.fiber.dispose() + }) + it('defaults the persistence root when omitted', async () => { // Exercises the `DEFAULT_PERSISTENCE_ROOT` fallback for a direct-apply caller that // bypasses the schema's `.default(...)`: call `apply` directly (not via @@ -179,7 +198,17 @@ describe('dsh-acp-demo composition', () => { }) } const assembly = await ctx.get('systemPrompt')!.assemble() - expect(assembly.tools.map(tool => tool.name)).toEqual(['zulu', 'alpha', 'skill', 'task_kill', 'task_list', 'task_output']) + expect(assembly.tools.map(tool => tool.name)).toEqual([ + 'zulu', + 'alpha', + 'create_goal', + 'get_goal', + 'skill', + 'task_kill', + 'task_list', + 'task_output', + 'update_goal', + ]) await ctx.fiber.dispose() }) diff --git a/packages/examples/acp-demo/tsconfig.json b/packages/examples/acp-demo/tsconfig.json index 78090f6273..d3fc190640 100644 --- a/packages/examples/acp-demo/tsconfig.json +++ b/packages/examples/acp-demo/tsconfig.json @@ -26,6 +26,9 @@ { "path": "../../ui/commands" }, + { + "path": "../../goal/command-goal" + }, { "path": "../../core/agent" }, diff --git a/packages/examples/agent-spine-demo/README.md b/packages/examples/agent-spine-demo/README.md index 76efd77845..89573a2fc9 100644 --- a/packages/examples/agent-spine-demo/README.md +++ b/packages/examples/agent-spine-demo/README.md @@ -17,6 +17,9 @@ Read this package for the whole plugin tree and its composition order. @deepseek-ai/dsh-skill skill provider registry @deepseek-ai/dsh-skill-local local filesystem skill provider @deepseek-ai/dsh-agent agent registry + initiator scope + agent/* events +@deepseek-ai/dsh-goal optional persisted same-session goal domain +@deepseek-ai/dsh-tool-goal optional model-facing goal controls +@deepseek-ai/dsh-goal-session optional same-session goal-round driver @deepseek-ai/dsh-tasks generic background-task registry @deepseek-ai/dsh-invariants dev-mode event-contract assertions @deepseek-ai/dsh-tool-bash the model-facing bash schema @@ -42,11 +45,11 @@ This is the [interface/implementation/consumer seam](../../../docs/rfc/implement ```ts import type { Config } from '@deepseek-ai/dsh-agent-spine-demo' -// { agents?, maxParallelToolCalls?, persona?, toolOrder?, tools?, dshHome?, skills?, workspaceContext, toolBash?, toolTasks? } +// { agents?, maxParallelToolCalls?, persona?, toolOrder?, tools?, dshHome?, skills?, workspaceContext, toolBash?, toolTasks?, goals? } // workspaceContext requires { maxBytes } or false; the other owner schemas supply defaults. ``` -The bundle FORWARDS each field to the child that owns it: `agents` and `maxParallelToolCalls` to `agent-loop` (`agents` defaults to `[]`; the cap defaults there), so each app supplies its own pre-created agents — a stdio app pre-creates `main`, while the ACP app creates agents on demand at `session/new`; `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer; the required `workspaceContext` choice to `dsh-workspace-context` (`{ maxBytes }` enables loading and `false` disables it); and `toolBash`/`toolTasks` to the two model-facing tool plugins the bundle owns. Set `skills.enabled: false` to omit both the local provider and model-facing skill tool, and set `toolTasks: false` to retain the task service for foreground producers without exposing `task_output` / `task_list` / `task_kill`. It resolves `dshHome` once through [`@deepseek-ai/dsh-home`](../../util/home/README.md) and forwards that absolute value to tool-bash's managed environment and enabled local skill discovery. An absent top-level `dshHome` adopts `skills.local.dshHome`; supplying both with different resolved paths fails loudly. `toolBash.enableRunInBackground` controls only the bash producer; independently loaded producers keep their own config. Workspace instructions register before the skill catalog so their session-prefix message renders first. App packages use `pickSpineConfig()` to copy only these bundle-owned fields. +The bundle FORWARDS each field to the child that owns it: `agents` and `maxParallelToolCalls` to `agent-loop` (`agents` defaults to `[]`; the cap defaults there), so each app supplies its own pre-created agents — a stdio app pre-creates `main`, while the ACP app creates agents on demand at `session/new`; `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer; the required `workspaceContext` choice to `dsh-workspace-context` (`{ maxBytes }` enables loading and `false` disables it); and `toolBash`/`toolTasks` to the two model-facing tool plugins the bundle owns. A `goals` object opts into the persisted domain, model tools, and same-session driver while forwarding `goals.domain` and `goals.tool` to their owners; omission or `false` leaves the stack absent so headless callers retain one-turn settlement. Set `skills.enabled: false` to omit both the local provider and model-facing skill tool, and set `toolTasks: false` to retain the task service for foreground producers without exposing `task_output` / `task_list` / `task_kill`. It resolves `dshHome` once through [`@deepseek-ai/dsh-home`](../../util/home/README.md) and forwards that absolute value to tool-bash's managed environment and enabled local skill discovery. An absent top-level `dshHome` adopts `skills.local.dshHome`; supplying both with different resolved paths fails loudly. `toolBash.enableRunInBackground` controls only the bash producer; independently loaded producers keep their own config. Workspace instructions register before the skill catalog so their session-prefix message renders first. App packages use `pickSpineConfig()` to copy only these bundle-owned fields. ## Why a code bundle, not a shared YAML include @@ -54,7 +57,7 @@ A YAML include can deduplicate config but cannot own a bin or provide front-door ## Model Experience -Indirectly, through `dsh-system-prompt`, `dsh-tool-skill`, `dsh-tool-bash`, and `dsh-tools`, which this bundle mounts without adding model-bound wrapper content. +Indirectly, through `dsh-system-prompt`, `dsh-tool-skill`, `dsh-tool-bash`, and `dsh-tools`, plus `dsh-tool-goal` and goal-round prompts when `goals` is enabled. The bundle adds no model-bound wrapper content of its own. #### KV Cache effect @@ -62,5 +65,5 @@ No direct invalidation; the named consumer owns any request-prefix changes. ## Known Limitations and Deferred Work -- **Most of the spine set is fixed in code** — `apply()` always mounts the core services and `tool-bash`; config can omit the bundled skills and task-control tools, but swapping the loop or dropping another spine member means composing a different bundle. +- **Most of the spine set is fixed in code** — `apply()` always mounts the core services and `tool-bash`; config can omit bundled goals, skills, and task-control tools, but swapping the loop or dropping another spine member means composing a different bundle. - **`dsh-invariants` mounts unconditionally** — this bundle has no toggle, so every composition using it pays the dev-mode relational assertions; Session's always-on validation and freezing are separate. diff --git a/packages/examples/agent-spine-demo/package.json b/packages/examples/agent-spine-demo/package.json index 772d6c059b..f1efc86de4 100644 --- a/packages/examples/agent-spine-demo/package.json +++ b/packages/examples/agent-spine-demo/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-agent-spine-demo", - "description": "The default executor-less/UI-less agent spine as one Cordis bundle plugin (timer + llm + sessions + system-prompt + tools + skills + agents + tasks + invariants + tool-bash + workspace-context + tool-skill + tool-tasks + agent-loop)", + "description": "The default executor-less/UI-less agent spine as one Cordis bundle plugin with optional persisted goals", "version": "0.0.1", "private": true, "type": "module", @@ -25,6 +25,8 @@ "@cordisjs/plugin-timer": "^1.1.2", "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-agent-loop": "^0.0.1", + "@deepseek-ai/dsh-goal": "^0.0.1", + "@deepseek-ai/dsh-goal-session": "^0.0.1", "@deepseek-ai/dsh-invariants": "^0.0.1", "@deepseek-ai/dsh-home": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", @@ -35,6 +37,7 @@ "@deepseek-ai/dsh-system-prompt": "^0.0.1", "@deepseek-ai/dsh-tasks": "^0.0.1", "@deepseek-ai/dsh-tool-bash": "^0.0.1", + "@deepseek-ai/dsh-tool-goal": "^0.0.1", "@deepseek-ai/dsh-tool-skill": "^0.0.1", "@deepseek-ai/dsh-tool-tasks": "^0.0.1", "@deepseek-ai/dsh-tools": "^0.0.1", @@ -44,6 +47,8 @@ "@cordisjs/plugin-timer": "workspace:^", "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", + "@deepseek-ai/dsh-goal": "workspace:^", + "@deepseek-ai/dsh-goal-session": "workspace:^", "@deepseek-ai/dsh-fs-local": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-home": "workspace:^", @@ -55,6 +60,7 @@ "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-tasks": "workspace:^", "@deepseek-ai/dsh-tool-bash": "workspace:^", + "@deepseek-ai/dsh-tool-goal": "workspace:^", "@deepseek-ai/dsh-tool-skill": "workspace:^", "@deepseek-ai/dsh-tool-tasks": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", diff --git a/packages/examples/agent-spine-demo/src/index.ts b/packages/examples/agent-spine-demo/src/index.ts index 74ba5e0cc9..b7d7e96507 100644 --- a/packages/examples/agent-spine-demo/src/index.ts +++ b/packages/examples/agent-spine-demo/src/index.ts @@ -1,6 +1,6 @@ /** * Default executor-less, UI-less agent spine. It bundles the common services, - * background-task registry and controls, concrete loop, local skill and + * background-task registry and controls, optional persisted goals, concrete loop, local skill and * workspace-context providers, and model-facing bash/skill consumers; * deployments still choose the LLM adapter, bash executor, and presentation. * The plugin intentionally exposes named exports only because Loader default @@ -18,6 +18,9 @@ import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools import SkillService, { type Config as SkillRegistryConfig } from '@deepseek-ai/dsh-skill' import * as SkillLocal from '@deepseek-ai/dsh-skill-local' import AgentRegistry from '@deepseek-ai/dsh-agent' +import GoalService, { type Config as GoalDomainConfig } from '@deepseek-ai/dsh-goal' +import * as goalSession from '@deepseek-ai/dsh-goal-session' +import * as toolGoal from '@deepseek-ai/dsh-tool-goal' import TaskService from '@deepseek-ai/dsh-tasks' import * as invariants from '@deepseek-ai/dsh-invariants' import * as toolBash from '@deepseek-ai/dsh-tool-bash' @@ -41,6 +44,14 @@ export interface SkillConfig { tool?: toolSkill.Config } +/** Persisted goal domain, model-tool policy, and same-session driver config. */ +export interface GoalConfig { + /** Goal-domain creation defaults. */ + domain?: GoalDomainConfig + /** Model-facing goal-tool authority policy. */ + tool?: toolGoal.Config +} + /** * Bundle config: each field forwarded verbatim to the child that owns it — * `agents` to the agent loop (an app that pre-creates no agents, like the ACP @@ -50,7 +61,8 @@ export interface SkillConfig { * `dshHome` to bash environment and local skill discovery, `skills` to the * skill registry/local provider/tool consumer, `workspaceContext` to the * workspace-context loader, and `toolBash`/`toolTasks` to the model-facing tool - * plugins this bundle owns. Owner schemas supply defaults for optional input; + * plugins this bundle owns. `goals` opts into and configures the persisted goal + * domain plus its model tool and same-session driver. Owner schemas supply defaults for optional input; * workspace context instead requires an explicit byte budget or `false` because * it changes model-visible input. Producer opt-in stays producer-local: * `toolBash` configures bash only; independently composed producers keep their @@ -77,6 +89,8 @@ export interface Config { toolBash?: toolBash.Config /** Generic background-task controls; set false to keep the task service without model-facing task tools. */ toolTasks?: toolTasks.Config | false + /** Opt-in persisted same-session goal stack; set false or omit to leave it unmounted. */ + goals?: GoalConfig | false } /** The skill config schema exported for app packages that forward `skills`. */ @@ -93,6 +107,12 @@ export const ToolBashConfigSchema: z = toolBash.Config /** The task-control-tool config schema exported for app packages that forward `toolTasks`. */ export const ToolTasksConfigSchema: z = toolTasks.Config +/** The persisted-goal config schema exported for app packages that opt in. */ +export const GoalConfigSchema: z = z.object({ + domain: GoalService.Config, + tool: toolGoal.Config, +}) + /** Intersect the owners' schemas so validation + defaulting stay identical. */ export const Config = z.intersect([ AgentLoop.Config, @@ -104,7 +124,8 @@ export const Config = z.intersect([ workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(), toolBash: ToolBashConfigSchema, toolTasks: z.union([z.const(false), ToolTasksConfigSchema]), - }) as unknown as z>, + goals: z.union([z.const(false), GoalConfigSchema]), + }) as unknown as z>, ]) as unknown as z /** @@ -123,6 +144,7 @@ export function pickSpineConfig(config: Omit): Omit { expect(ctx.get('agents')).toBeDefined() expect(ctx.get('tasks')).toBeDefined() expect(ctx.get('agentLoop')).toBeDefined() + expect(ctx.get('goals')).toBeUndefined() + await ctx.fiber.dispose() + }) + + it('opts into the configured persisted-goal domain, tools, and same-session driver', async () => { + const ctx = await mount({ + workspaceContext: false, + goals: { + domain: { defaultMaxGoalRounds: 17 }, + tool: { blockedAfterConsecutiveRounds: 5 }, + }, + }) + expect(ctx.goals.resolveCreate({ objective: 'configured' })).toEqual({ + objective: 'configured', + maxGoalRounds: 17, + }) + expect(['create_goal', 'get_goal', 'update_goal'].map(name => ctx.tools.get(name)?.name)) + .toEqual(['create_goal', 'get_goal', 'update_goal']) + expect((await ctx.systemPrompt.assemble()).sections.find(section => section.name === 'tool:goal')?.text) + .toContain('at least 5 consecutive goal rounds') + await ctx.fiber.dispose() + }) + + it('accepts an explicit false goal composition without mounting it', async () => { + const ctx = await mount({ workspaceContext: false, goals: false }) + expect(ctx.get('goals')).toBeUndefined() + expect(ctx.tools.get('get_goal')).toBeUndefined() await ctx.fiber.dispose() }) @@ -170,6 +197,18 @@ describe('dsh-agent-spine-demo bundle', () => { await ctx.fiber.dispose() }) + it('uses owner defaults for a schema-bypassing empty goal opt-in', async () => { + const ctx = new Context() + agentCore.apply(ctx, { workspaceContext: false, goals: {} }) + await new Promise(resolve => setTimeout(resolve, 50)) + expect(ctx.goals.resolveCreate({ objective: 'defaulted' })).toEqual({ + objective: 'defaulted', + maxGoalRounds: 256, + }) + expect(ctx.tools.get('get_goal')).toBeDefined() + await ctx.fiber.dispose() + }) + it('loads workspace instructions into requests through the bundled spine', async () => { const root = await mkdtemp(join(tmpdir(), 'dsh-agent-spine-demo-workspace-context-')) try { diff --git a/packages/examples/agent-spine-demo/tsconfig.json b/packages/examples/agent-spine-demo/tsconfig.json index 89cb2accd8..ba9d69e841 100644 --- a/packages/examples/agent-spine-demo/tsconfig.json +++ b/packages/examples/agent-spine-demo/tsconfig.json @@ -41,6 +41,15 @@ { "path": "../../core/agent" }, + { + "path": "../../goal/goal" + }, + { + "path": "../../goal/tool-goal" + }, + { + "path": "../../goal/goal-session" + }, { "path": "../../context/workspace-context" }, diff --git a/packages/examples/stdio-demo/README.md b/packages/examples/stdio-demo/README.md index f145ccaf16..313e5f47ed 100644 --- a/packages/examples/stdio-demo/README.md +++ b/packages/examples/stdio-demo/README.md @@ -12,6 +12,7 @@ A terminal chat always wants the same cluster, so the package owns it rather tha |---|---| | `@deepseek-ai/dsh-agent-spine-demo` | the spine, pre-creating a `main` agent from this app's provider/model pair with `process.cwd()` as the fresh session cwd and carrying its `persona` | | `@deepseek-ai/dsh-commands` | the human-command registry consumed by the TUI front door and optional command plugins | +| `@deepseek-ai/dsh-command-goal` | the direct `/goal` producer; the app enables the spine's persisted-goal stack with it | | `@deepseek-ai/dsh-session-persistence-jsonl` | durable JSONL session log under `persistenceRoot` | | `@deepseek-ai/dsh-user-interaction` | the human question/answer seam used by confirmation tools | | `@deepseek-ai/dsh-tool-ask-user` | the model-facing `ask_user_question` tool | @@ -37,6 +38,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `skills` | owner defaults | registry-cache, local-provider, and model-facing skill-tool config, routed through `dsh-agent-spine-demo` | | `toolBash` | owner defaults | model-facing bash config routed through `dsh-agent-spine-demo`, including bash's producer-local `enableRunInBackground` | | `toolTasks` | owner defaults | generic `task_output` wait bounds routed through `dsh-agent-spine-demo` | +| `goals` | owner defaults | persisted goal-domain and model-tool config; `false` removes the goal stack and `/goal` producer | | `persistenceRoot` | `./.sessions` | the JSONL backend's root directory | | `welcome` | `ready.` | terminal banner / TUI subtitle | | `ui` | `{ mode: 'auto' }` | terminal mode (`auto` / `readline` / `tui`) and nested TUI presentation config | @@ -82,7 +84,7 @@ Swap `llm-deepseek` for a `mock-llm` leaf plugin and you have the echo demo — #### What the model sees -Through `dsh-agent-spine-demo`, the `main` agent receives the harness identity, configured persona, skill catalog, and visible tools; this app also composes the generated [`ask_user_question` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-ask-user). Each ordinary terminal submission becomes a user message; submissions made while the agent runs steer the active turn. TUI commands and their results remain outside model context. +Through `dsh-agent-spine-demo`, the `main` agent receives the harness identity, configured persona, skill catalog, visible tools, and the enabled goal policy/tools; this app also composes the generated [`ask_user_question` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-ask-user). Each ordinary terminal submission becomes a user message; submissions made while the agent runs steer the active turn. TUI commands and their direct results remain outside model context, while accepted `/goal` mutations append the goal domain's model-visible snapshot. #### Token effect @@ -109,5 +111,6 @@ Append-only; newly visible content follows the reusable request prefix and does ## Known Limitations and Deferred Work - **One pre-created `main` agent drives the selected terminal UI** — there is no multi-session or concurrent-agent surface in this app; a run is one conversation. +- **Direct commands require TUI mode** — the line-oriented fallback does not consume `ctx.commands`; an ordinary `/goal` prompt there may instead be interpreted through the model-facing goal tools. - **The front-door cluster is fixed in code** — the JSONL persistence backend and the ask-user tooling are baked; a different composition is a leaf-level sibling entry or another app package. - **The question tool is not an approval answerer** — this app mounts `user-interaction` and `ask_user_question`, but not `ctx.approval`; a `tools/pre-execute` `ask` therefore fails closed unless the leaf composes an approval service and terminal answerer. diff --git a/packages/examples/stdio-demo/package.json b/packages/examples/stdio-demo/package.json index b8285dc351..17fbe8396d 100644 --- a/packages/examples/stdio-demo/package.json +++ b/packages/examples/stdio-demo/package.json @@ -37,6 +37,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-agent-loop": "^0.0.1", "@deepseek-ai/dsh-commands": "^0.0.1", + "@deepseek-ai/dsh-command-goal": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-agent-spine-demo": "^0.0.1", "@deepseek-ai/dsh-workspace-context": "^0.0.1", @@ -58,6 +59,7 @@ "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-commands": "workspace:^", + "@deepseek-ai/dsh-command-goal": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-agent-spine-demo": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", diff --git a/packages/examples/stdio-demo/src/index.ts b/packages/examples/stdio-demo/src/index.ts index c8fa7b5fd0..307a0db483 100644 --- a/packages/examples/stdio-demo/src/index.ts +++ b/packages/examples/stdio-demo/src/index.ts @@ -17,6 +17,7 @@ import z from 'schemastery' import { SessionId } from '@deepseek-ai/dsh-session' import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools' import CommandService from '@deepseek-ai/dsh-commands' +import * as commandGoal from '@deepseek-ai/dsh-command-goal' import * as agentCore from '@deepseek-ai/dsh-agent-spine-demo' import * as workspaceContext from '@deepseek-ai/dsh-workspace-context' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' @@ -100,6 +101,8 @@ export interface Config { toolBash?: NonNullable /** Generic background-task controls forwarded through agent-core; set false to omit their tool surface. */ toolTasks?: NonNullable + /** Persisted same-session goals; owner defaults enable them, or false disables the stack and command. */ + goals?: agentCore.GoalConfig | false /** * If set, the pre-created agent RESUMES this persisted session id instead of * starting fresh. Sourced from an env var in the leaf `cordis.yml` @@ -127,6 +130,7 @@ export const Config: z = z.object({ skills: agentCore.SkillConfigSchema, toolBash: agentCore.ToolBashConfigSchema, toolTasks: z.union([z.const(false), agentCore.ToolTasksConfigSchema]), + goals: z.union([z.const(false), agentCore.GoalConfigSchema]), resumeSessionId: z.string(), workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(), }) @@ -145,8 +149,10 @@ export function composeTerminalApp(ctx: Context, config: Config, isTTY: boolean) const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId const sessionId = SessionId(resumeSessionId ?? `main-session-${randomUUID()}`) const mode = resolveTerminalMode(config.ui, isTTY) + const goals = config.goals ?? {} if (mode === 'readline') ctx.plugin(ConsoleExporter) ctx.plugin(CommandService) + if (goals !== false) ctx.plugin(commandGoal) ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? DEFAULT_PERSISTENCE_ROOT }) ctx.plugin(UserInteractionService) if (mode === 'tui') { @@ -163,6 +169,7 @@ export function composeTerminalApp(ctx: Context, config: Config, isTTY: boolean) } ctx.plugin(agentCore, { ...agentCore.pickSpineConfig(config), + goals, agents: [{ id: SessionId('main'), provider: config.provider, diff --git a/packages/examples/stdio-demo/tests/stdio-agent.spec.ts b/packages/examples/stdio-demo/tests/stdio-agent.spec.ts index c8ca063151..f20860f1eb 100644 --- a/packages/examples/stdio-demo/tests/stdio-agent.spec.ts +++ b/packages/examples/stdio-demo/tests/stdio-agent.spec.ts @@ -90,6 +90,7 @@ describe('dsh-stdio-demo app', () => { ui: { mode: 'tui', tui: { color: false, maxToolOutputLines: 3 } }, }, true) expect(calls.map(call => call.name)).toContain('ui-tui') + expect(calls.map(call => call.name)).toContain('command-goal') expect(calls.map(call => call.name)).not.toContain('ui-stdio') expect(calls.map(call => call.name)).not.toContain('ConsoleExporter') const tuiConfig = calls.find(call => call.name === 'ui-tui')?.config as { sessionId: string } @@ -99,6 +100,7 @@ describe('dsh-stdio-demo app', () => { agents: Array<{ id: string; sessionId?: string; resumeSessionId?: string }> } expect(spineConfig.agents[0]).toMatchObject({ id: 'main', sessionId: tuiConfig.sessionId }) + expect(spineConfig).toMatchObject({ goals: {} }) calls.length = 0 stdioAgent.composeTerminalApp(ctx, { @@ -116,11 +118,13 @@ describe('dsh-stdio-demo app', () => { calls.length = 0 stdioAgent.composeTerminalApp(ctx, { - provider: 'mock', model: 'mock', workspaceContext: false, ui: { mode: 'readline' }, + provider: 'mock', model: 'mock', workspaceContext: false, goals: false, ui: { mode: 'readline' }, }, false) expect(calls.map(call => call.name)).toContain('ui-stdio') expect(calls.map(call => call.name)).toContain('ConsoleExporter') expect(calls.map(call => call.name)).not.toContain('ui-tui') + expect(calls.map(call => call.name)).not.toContain('command-goal') + expect(calls.find(call => call.name === 'agent-spine-demo')?.config).toMatchObject({ goals: false }) }) it('composes the spine + front-door cluster and pre-creates the main agent', async () => { @@ -131,6 +135,8 @@ describe('dsh-stdio-demo app', () => { expect(ctx.get('sessionPersistence')).toBeDefined() expect(ctx.get('userInteraction')).toBeDefined() expect(ctx.get('tools')?.get('ask_user_question')).toBeDefined() + expect(ctx.get('goals')).toBeDefined() + expect(ctx.get('tools')?.get('get_goal')).toBeDefined() // The sole pre-created agent the UI drives. `main` is its stable config // label; each fresh process mints a durable combined agent/session id. await expect.poll(() => ctx.get('agents')?.list()).toHaveLength(1) @@ -139,6 +145,7 @@ describe('dsh-stdio-demo app', () => { expect(agent?.id).toBe(agent?.session.id) expect(agent?.id).toMatch(/^main-session-/) expect(agent?.session.header.cwd).toBe(process.cwd()) + expect(ctx.commands.find(agent!, 'tui', 'goal')).toBeDefined() await ctx.fiber.dispose() }) @@ -273,7 +280,18 @@ describe('dsh-stdio-demo app', () => { }) } const assembly = await ctx.get('systemPrompt')!.assemble() - expect(assembly.tools.map(tool => tool.name)).toEqual(['zulu', 'alpha', 'ask_user_question', 'skill', 'task_kill', 'task_list', 'task_output']) + expect(assembly.tools.map(tool => tool.name)).toEqual([ + 'zulu', + 'alpha', + 'ask_user_question', + 'create_goal', + 'get_goal', + 'skill', + 'task_kill', + 'task_list', + 'task_output', + 'update_goal', + ]) await ctx.fiber.dispose() }) diff --git a/packages/examples/stdio-demo/tsconfig.json b/packages/examples/stdio-demo/tsconfig.json index 61646af70f..16d1108e20 100644 --- a/packages/examples/stdio-demo/tsconfig.json +++ b/packages/examples/stdio-demo/tsconfig.json @@ -32,6 +32,9 @@ { "path": "../../ui/commands" }, + { + "path": "../../goal/command-goal" + }, { "path": "../agent-spine-demo" }, diff --git a/packages/goal/README.md b/packages/goal/README.md index fd0b94f321..95cd975b69 100644 --- a/packages/goal/README.md +++ b/packages/goal/README.md @@ -7,5 +7,6 @@ The goal family owns durable objective state independently of the model-facing t | `goal/` | Event-sourced goal lifecycle, replay fold, compare-and-set mutations, and process-local activation | `ctx.goals` | | `goal-session/` | Same-session goal-round admission, outcome mapping, and lifecycle race fencing | — | | `tool-goal/` | Model-facing read/create/update tools with execution-time authority checks | — | +| `command-goal/` | Human-facing `/goal` status and lifecycle control over the command plane | — | Goal state is part of the owning session log. Consumers depend on `dsh-goal`, not on the concrete agent loop; continuation behavior belongs in a separate plugin on the public agent seams. diff --git a/packages/goal/command-goal/README.md b/packages/goal/command-goal/README.md new file mode 100644 index 0000000000..d592b51637 --- /dev/null +++ b/packages/goal/command-goal/README.md @@ -0,0 +1,56 @@ +# @deepseek-ai/dsh-command-goal + +Human-facing `/goal` control over [`ctx.goals`](../goal/README.md). The plugin registers one global command through [`ctx.commands`](../../ui/commands/README.md); TUI and ACP discover and execute it without a model turn. The [human goal-command RFC](../../../docs/rfc/implemented/feature/2026-07-19-human-goal-command.md) owns the UX and composition decisions. + +## Command contract + +| Input | Result | +|---|---| +| `/goal` | Show the current objective, durable phase, round count/cap, process-local activation, and valid next commands; show usage when no goal exists. | +| `/goal ` | Create and arm a goal, or replace a completed goal with a fresh identity. An unfinished goal is never replaced without an explicit clear. | +| `/goal edit ` | Edit the current objective without changing its phase or activation. Editing a completed goal creates a fresh active goal. | +| `/goal pause` | Pause an active goal and disarm continuation. | +| `/goal resume` | Resume a stopped goal or rearm an active goal after session resume/fork, subject to its remaining round cap. | +| `/goal clear` | Clear the current pointer while retaining its durable history and tombstone. | + +Control words are case-insensitive only when they occupy the complete input. Every other non-empty suffix is an objective, so `/goal pause after verification` creates that literal objective. The goal domain trims and validates objectives. Because the generic command plane has no modal editor or confirmation primitive, `edit` takes its replacement inline and an unfinished replacement returns a direct error instructing the user to edit or clear. + +Expected domain rejections become direct command errors. Unexpected implementation failures still reject dispatch so adapters can report them as command failures. Generic command text and output remain live UI state; every accepted mutation is persisted and made model-visible by `dsh-goal` rather than by this plugin. + +## Composition + +The producer injects `commands` and `goals`. A custom app mounts their owners plus this plugin; automatic continuation remains an independent choice: + +```yaml +- id: commands + name: '@deepseek-ai/dsh-commands' +- id: goal + name: '@deepseek-ai/dsh-goal' +- id: command-goal + name: '@deepseek-ai/dsh-command-goal' +``` + +The terminal and ACP demo apps enable the complete persisted-goal stack and this command by default; `goals: false` removes both. The UI-less `agent-spine-demo` requires an explicit `goals: {}` so headless one-shot callers do not silently change from one physical turn to a multi-round operation. + +## Model Experience + +### Human `/goal` control + +#### What the model sees + +The slash input and direct status/error output are absent from model requests. An accepted mutation later appears through the goal domain's raw `` snapshot or clear tombstone; this preserves the model-visible-is-logged invariant without logging presentation text. + +#### Token effect + +Reading status or receiving a direct command error adds no model tokens. Each accepted mutation adds the goal domain's retained full snapshot, and an enabled same-session driver may add later goal-round prompts. + +#### KV Cache effect + +Command discovery and direct output do not affect the cache. A mutation appends after the reusable history prefix; later compaction may replace the derived-history suffix. + +## Known Limitations and Deferred Work + +- **Plain-text interaction only** — the generic command registry has no modal edit form or replacement-confirmation callback; inline edit and explicit clear keep destructive intent deterministic on both TUI and ACP. +- **No per-command round-cap argument** — `defaultMaxGoalRounds` remains deployment config, while a direct human request may ask the model to edit `max_goal_rounds` through the separately authorized goal tool. +- **No continuous status widget** — bare `/goal` is the portable observation surface; adapter-specific badges and reconnectable command output remain future UI work. +- **TUI and ACP only** — the line-oriented stdio and JSON-RPC adapters do not consume `ctx.commands`. Their ordinary human prompts can still authorize the model-facing goal tools when those are composed. diff --git a/packages/goal/command-goal/package.json b/packages/goal/command-goal/package.json new file mode 100644 index 0000000000..87da2ffaea --- /dev/null +++ b/packages/goal/command-goal/package.json @@ -0,0 +1,38 @@ +{ + "name": "@deepseek-ai/dsh-command-goal", + "description": "Human-facing slash command for persisted same-session goals", + "version": "0.0.1", + "private": true, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./src/*": "./src/*", + "./package.json": "./package.json" + }, + "files": [ + "lib/index.js", + "lib/types/**/*.d.ts", + "lib/types/**/*.d.ts.map", + "src" + ], + "license": "BSD-3-Clause", + "peerDependencies": { + "@deepseek-ai/dsh-commands": "^0.0.1", + "@deepseek-ai/dsh-goal": "^0.0.1", + "cordis": "^4.0.0-rc.7" + }, + "devDependencies": { + "@cordisjs/plugin-loader": "workspace:^", + "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-commands": "workspace:^", + "@deepseek-ai/dsh-goal": "workspace:^", + "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", + "cordis": "^4.0.0-rc.7" + } +} diff --git a/packages/goal/command-goal/src/index.ts b/packages/goal/command-goal/src/index.ts new file mode 100644 index 0000000000..3fff035adc --- /dev/null +++ b/packages/goal/command-goal/src/index.ts @@ -0,0 +1,165 @@ +/** + * Human-facing `/goal` command over the persisted same-session goal domain. + * @module @deepseek-ai/dsh-command-goal + */ + +import type { Context } from 'cordis' +import type { CommandInvocation, CommandResult } from '@deepseek-ai/dsh-commands' +import { GoalError } from '@deepseek-ai/dsh-goal' +import type { GoalPhase, GoalRef, GoalView } from '@deepseek-ai/dsh-goal' + +export const name = 'command-goal' +export const inject = ['commands', 'goals'] + +const USAGE = 'Usage: /goal [|clear|edit |pause|resume]' + +type GoalCommand = + | { readonly kind: 'show' } + | { readonly kind: 'create'; readonly objective: string } + | { readonly kind: 'edit'; readonly objective: string } + | { readonly kind: 'invalid-edit' } + | { readonly kind: 'pause' } + | { readonly kind: 'resume' } + | { readonly kind: 'clear' } + +/** Fail loudly if a locally closed union gains an unhandled member. */ +/* v8 ignore start -- closed-union backstop is unreachable without violating the TypeScript contract */ +function assertNever(value: never, label: string): never { + throw new TypeError(`unknown ${label}: ${String(value)}`) +} +/* v8 ignore stop */ + +/** Parse only the grammar owned by `/goal`; arbitrary other input is an objective. */ +function parseGoalCommand(rawInput: string): GoalCommand { + const input = rawInput.trim() + if (input.length === 0) return { kind: 'show' } + const control = input.toLowerCase() + if (control === 'clear') return { kind: 'clear' } + if (control === 'pause') return { kind: 'pause' } + if (control === 'resume') return { kind: 'resume' } + if (control === 'edit') return { kind: 'invalid-edit' } + if (/^edit(?=\s)/iu.test(input)) return { kind: 'edit', objective: input.slice(4).trim() } + return { kind: 'create', objective: input } +} + +/** Human label for one durable goal phase. */ +function phaseLabel(phase: GoalPhase): string { + switch (phase) { + case 'active': return 'active' + case 'paused': return 'paused' + case 'blocked': return 'blocked' + case 'usage-limited': return 'usage limited' + case 'budget-limited': return 'limited by round budget' + case 'complete': return 'complete' + /* v8 ignore next 2 -- GoalPhase is closed and every member is handled above */ + default: return assertNever(phase, 'goal phase') + } +} + +/** Commands that are meaningful from one exact live state. */ +function commandHint(goal: GoalView): string { + if (goal.phase === 'active') { + return goal.activation === 'armed' + ? '/goal edit , /goal pause, /goal clear' + : '/goal edit , /goal resume, /goal clear' + } + switch (goal.phase) { + case 'paused': + case 'blocked': + case 'usage-limited': + return '/goal edit , /goal resume, /goal clear' + case 'budget-limited': + return '/goal edit , /goal clear' + case 'complete': + return '/goal , /goal clear' + /* v8 ignore next 2 -- the active branch and every non-active phase are handled above */ + default: return assertNever(goal.phase, 'goal phase') + } +} + +/** Render direct UI output without exposing compare-and-set internals. */ +function renderGoal(title: string, goal: GoalView): CommandResult { + return { + kind: 'success', + text: [ + title, + `Status: ${phaseLabel(goal.phase)}`, + `Objective: ${goal.objective}`, + `Rounds: ${goal.roundsStarted}/${goal.maxGoalRounds}`, + `Activation: ${goal.activation}`, + '', + `Commands: ${commandHint(goal)}`, + ].join('\n'), + } +} + +/** Exact current compare-and-set ref. */ +function goalRef(goal: GoalView): GoalRef { + return { id: goal.id, revision: goal.revision } +} + +/** Direct error for an operation that requires a current goal. */ +function missingGoal(action: string): CommandResult { + return { + kind: 'error', + text: `No goal is currently set; /goal ${action} requires one. ${USAGE}`, + } +} + +/** Execute one parsed human command through the domain that owns persistence. */ +function executeGoalCommand(ctx: Context, invocation: CommandInvocation): CommandResult { + const command = parseGoalCommand(invocation.rawInput) + try { + const current = ctx.goals.get(invocation.agent) + switch (command.kind) { + case 'show': + return current === undefined + ? { kind: 'success', text: `No goal is currently set.\n${USAGE}` } + : renderGoal('Goal', current) + case 'invalid-edit': + return { kind: 'error', text: `Goal editing requires a replacement objective.\n${USAGE}` } + case 'create': + if (current !== undefined && current.phase !== 'complete') { + return { + kind: 'error', + text: `A goal is already ${phaseLabel(current.phase)}. Use /goal edit to change it or /goal clear before replacing it.`, + } + } + return renderGoal('Goal created', ctx.goals.create(invocation.agent, { objective: command.objective })) + case 'edit': + if (current === undefined) return missingGoal('edit') + if (current.phase === 'complete') { + return renderGoal('Goal created', ctx.goals.create(invocation.agent, { objective: command.objective })) + } + return renderGoal( + 'Goal updated', + ctx.goals.edit(invocation.agent, goalRef(current), { objective: command.objective }), + ) + case 'pause': + if (current === undefined) return missingGoal('pause') + return renderGoal('Goal paused', ctx.goals.pause(invocation.agent, goalRef(current))) + case 'resume': + if (current === undefined) return missingGoal('resume') + return renderGoal('Goal resumed', ctx.goals.resume(invocation.agent, goalRef(current))) + case 'clear': + if (current === undefined) return { kind: 'success', text: 'No goal to clear.' } + ctx.goals.clear(invocation.agent, goalRef(current)) + return { kind: 'success', text: 'Goal cleared.' } + /* v8 ignore next 2 -- GoalCommand is closed and every member is handled above */ + default: return assertNever(command, 'goal command') + } + } catch (error: unknown) { + if (error instanceof GoalError) return { kind: 'error', text: error.message } + throw error + } +} + +/** Register the Codex-shaped `/goal` human command on TUI and ACP surfaces. */ +export function apply(ctx: Context): void { + ctx.commands.register({ + name: 'goal', + description: 'set or view the goal for a long-running task', + input: { hint: '[|clear|edit |pause|resume]' }, + handler: invocation => executeGoalCommand(ctx, invocation), + }) +} diff --git a/packages/goal/command-goal/tests/command-goal.spec.ts b/packages/goal/command-goal/tests/command-goal.spec.ts new file mode 100644 index 0000000000..e13f5e9822 --- /dev/null +++ b/packages/goal/command-goal/tests/command-goal.spec.ts @@ -0,0 +1,254 @@ +import { describe, expect, it, vi } from 'vitest' +import { Context } from 'cordis' +import Loader from '@cordisjs/plugin-loader' +import AgentRegistry from '@deepseek-ai/dsh-agent' +import type { Agent, AgentStatus, InjectOptions } from '@deepseek-ai/dsh-agent' +import CommandService from '@deepseek-ai/dsh-commands' +import GoalService from '@deepseek-ai/dsh-goal' +import type { GoalRef } from '@deepseek-ai/dsh-goal' +import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm' +import { Session, SessionId } from '@deepseek-ai/dsh-session' +import * as commandGoal from '@deepseek-ai/dsh-command-goal' + +interface Harness { + readonly ctx: Context + readonly agent: Agent + readonly session: Session + readonly plugin: Awaited> +} + +/** Number the next balanced injection or message turn. */ +function nextTurn(session: Session): number { + return session.events.reduce( + (maximum, event) => event.type === 'turn/start' ? Math.max(maximum, event.data.turn) : maximum, + 0, + ) + 1 +} + +/** Append one idle injection using the public Agent contract's balanced shape. */ +function appendInjection(session: Session, content: ContentBlock[], options?: InjectOptions): void { + const source: MessageSource = options?.source ?? { kind: 'user' } + const turn = nextTurn(session) + session.append('turn/start', { turn, trigger: { kind: 'injection', source } }) + session.append('context/message', { + content, + source, + ...options?.envelope === undefined ? {} : { envelope: options.envelope }, + ...options?.meta === undefined ? {} : { meta: options.meta }, + }, { surfaceOp: 'append' }) + session.append('turn/end', { turn, reason: { kind: 'completed' } }) +} + +/** Build a live idle agent accepted by the exact-identity goal service. */ +function stubAgent(id: string): { agent: Agent; session: Session } { + const session = new Session(SessionId(id)) + let status: AgentStatus = 'idle' + const agent: Agent = { + id: session.id, + options: {}, + session, + ctx: new Context(), + get status() { return status }, + send() {}, + steer() {}, + inject(content, options) { appendInjection(session, content, options) }, + cancel() { status = 'idle' }, + whenIdle() { return Promise.resolve() }, + } + return { agent, session } +} + +/** Mount the real command registry, goal domain, and producer. */ +async function harness(): Promise { + const ctx = new Context() + await ctx.plugin(CommandService) + await ctx.plugin(AgentRegistry) + await ctx.plugin(GoalService) + const plugin = await ctx.plugin(commandGoal) + const { agent, session } = stubAgent(`command-goal-${Math.random()}`) + ctx.agents.register(agent) + return { ctx, agent, session, plugin } +} + +/** Execute `/goal` through the same registry boundary as a UI adapter. */ +async function run(test: Harness, suffix = ''): Promise>>> { + const result = await test.ctx.commands.execute( + test.agent, + 'tui', + `/goal${suffix}`, + new AbortController().signal, + ) + if (result === undefined) throw new Error('goal command was not registered') + return result +} + +/** Current exact compare-and-set ref. */ +function ref(goal: NonNullable>): GoalRef { + return { id: goal.id, revision: goal.revision } +} + +/** Append one admitted goal round for budget-limited presentation coverage. */ +function appendRound(test: Harness, goal: NonNullable>): void { + const source = { kind: 'goal', goalId: goal.id, revision: goal.revision, round: 1 } as const + const turn = nextTurn(test.session) + test.session.append('turn/start', { turn, trigger: { kind: 'message', source } }) + test.session.append('user/message', { + content: [{ type: 'text', text: 'goal round' }], + source, + }, { surfaceOp: 'append' }) + test.session.append('turn/end', { turn, reason: { kind: 'completed' } }) +} + +describe('@deepseek-ai/dsh-command-goal registration', () => { + it('registers one global TUI/ACP command with Loader-safe exports and disposes it', async () => { + const test = await harness() + expect(commandGoal.name).toBe('command-goal') + expect(commandGoal.inject).toEqual(['commands', 'goals']) + expect('default' in commandGoal).toBe(false) + const loader = Object.create(Loader.prototype) as Loader + expect(loader.unwrapExports(commandGoal)).toBe(commandGoal) + + expect(test.ctx.commands.list(test.agent, 'tui')).toContainEqual({ + name: 'goal', + description: 'set or view the goal for a long-running task', + input: { hint: '[|clear|edit |pause|resume]' }, + surfaces: ['tui', 'acp'], + }) + expect(test.ctx.commands.find(test.agent, 'acp', 'goal')).toBeDefined() + + await test.plugin.dispose() + expect(test.ctx.commands.find(test.agent, 'tui', 'goal')).toBeUndefined() + }) +}) + +describe('/goal human command', () => { + it('shows an empty status without mutating the session', async () => { + const test = await harness() + await expect(run(test)).resolves.toEqual({ + kind: 'success', + text: 'No goal is currently set.\nUsage: /goal [|clear|edit |pause|resume]', + }) + expect(test.session.events).toEqual([]) + }) + + it('creates a trimmed objective and refuses silent replacement of unfinished work', async () => { + const test = await harness() + const created = await run(test, '\n finish the release ') + expect(created.kind).toBe('success') + expect(created.text).toContain('Goal created\nStatus: active') + expect(created.text).toContain('Objective: finish the release') + expect(created.text).toContain('Rounds: 0/256') + expect(created.text).toContain('Activation: armed') + expect(test.ctx.goals.get(test.agent)?.objective).toBe('finish the release') + expect(test.session.events.map(event => event.type)).toEqual(['turn/start', 'context/message', 'turn/end']) + + const count = test.session.events.length + await expect(run(test, ' replacement')).resolves.toEqual({ + kind: 'error', + text: 'A goal is already active. Use /goal edit to change it or /goal clear before replacing it.', + }) + expect(test.session.events).toHaveLength(count) + }) + + it('treats only exact control words as controls', async () => { + const test = await harness() + await run(test, ' pause everything only after verification') + expect(test.ctx.goals.get(test.agent)?.objective).toBe('pause everything only after verification') + }) + + it('edits inline, requires an objective, and starts a new goal when the old one is complete', async () => { + const empty = await harness() + const invalidEdit = await run(empty, ' edit') + expect(invalidEdit.kind).toBe('error') + expect(invalidEdit.text).toContain('requires a replacement objective') + const missingEdit = await run(empty, ' edit replacement') + expect(missingEdit.kind).toBe('error') + expect(missingEdit.text).toContain('/goal edit requires one') + + const test = await harness() + await run(test, ' first') + const first = test.ctx.goals.get(test.agent)! + const updated = await run(test, ' EDIT\n second ') + expect(updated.kind).toBe('success') + expect(updated.text).toContain('Goal updated') + expect(test.ctx.goals.get(test.agent)).toMatchObject({ id: first.id, objective: 'second', revision: 2 }) + + const current = test.ctx.goals.get(test.agent)! + test.ctx.goals.complete(test.agent, ref(current)) + const replacement = await run(test, ' edit third') + expect(replacement.kind).toBe('success') + expect(replacement.text).toContain('Goal created') + expect(test.ctx.goals.get(test.agent)).toMatchObject({ objective: 'third', revision: 1 }) + expect(test.ctx.goals.get(test.agent)?.id).not.toBe(first.id) + }) + + it('returns direct missing-state results for pause, resume, and clear', async () => { + const test = await harness() + const missingPause = await run(test, ' pause') + expect(missingPause.kind).toBe('error') + expect(missingPause.text).toContain('/goal pause requires one') + const missingResume = await run(test, ' resume') + expect(missingResume.kind).toBe('error') + expect(missingResume.text).toContain('/goal resume requires one') + await expect(run(test, ' clear')).resolves.toEqual({ kind: 'success', text: 'No goal to clear.' }) + }) + + it('pauses, resumes, clears, and converts expected domain rejections to command errors', async () => { + const test = await harness() + await run(test, ' work') + const redundantResume = await run(test, ' RESUME') + expect(redundantResume.kind).toBe('error') + expect(redundantResume.text).toContain('already active and armed') + const paused = await run(test, ' PAUSE') + expect(paused.kind).toBe('success') + expect(paused.text).toContain('Goal paused') + expect(test.ctx.goals.get(test.agent)).toMatchObject({ phase: 'paused', activation: 'disarmed' }) + const resumed = await run(test, ' resume') + expect(resumed.kind).toBe('success') + expect(resumed.text).toContain('Goal resumed') + expect(test.ctx.goals.get(test.agent)).toMatchObject({ phase: 'active', activation: 'armed' }) + await expect(run(test, ' clear')).resolves.toEqual({ kind: 'success', text: 'Goal cleared.' }) + expect(test.ctx.goals.get(test.agent)).toBeUndefined() + }) + + it('shows every durable phase and distinguishes disarmed active state', async () => { + const test = await harness() + test.ctx.goals.create(test.agent, { objective: 'state matrix', maxGoalRounds: 1 }) + test.ctx.goals.disarm(test.agent) + expect((await run(test)).text) + .toContain('Status: active\nObjective: state matrix\nRounds: 0/1\nActivation: disarmed') + expect((await run(test)).text).toContain('/goal resume') + + let goal = test.ctx.goals.get(test.agent)! + goal = test.ctx.goals.resume(test.agent, ref(goal)) + goal = test.ctx.goals.pause(test.agent, ref(goal)) + expect((await run(test)).text).toContain('Status: paused') + + goal = test.ctx.goals.resume(test.agent, ref(goal)) + goal = test.ctx.goals.block(test.agent, ref(goal)) + expect((await run(test)).text).toContain('Status: blocked') + + goal = test.ctx.goals.resume(test.agent, ref(goal)) + goal = test.ctx.goals.markUsageLimited(test.agent, ref(goal)) + expect((await run(test)).text).toContain('Status: usage limited') + + goal = test.ctx.goals.resume(test.agent, ref(goal)) + appendRound(test, goal) + goal = test.ctx.goals.get(test.agent)! + goal = test.ctx.goals.markBudgetLimited(test.agent, ref(goal)) + const limited = await run(test) + expect(limited.text).toContain('Status: limited by round budget') + expect(limited.text).not.toContain('/goal resume') + + goal = test.ctx.goals.complete(test.agent, ref(goal)) + const complete = await run(test) + expect(complete.text).toContain('Status: complete') + expect(complete.text).toContain('Commands: /goal , /goal clear') + }) + + it('does not turn unexpected implementation failures into expected command results', async () => { + const test = await harness() + vi.spyOn(test.ctx.goals, 'get').mockImplementationOnce(() => { throw new Error('unexpected failure') }) + await expect(run(test)).rejects.toThrow('unexpected failure') + }) +}) diff --git a/packages/goal/command-goal/tsconfig.json b/packages/goal/command-goal/tsconfig.json new file mode 100644 index 0000000000..914a50c326 --- /dev/null +++ b/packages/goal/command-goal/tsconfig.json @@ -0,0 +1,24 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": [ + "src" + ], + "references": [ + { + "path": "../../../vendor/cosmokit" + }, + { + "path": "../../../vendor/cordis" + }, + { + "path": "../../ui/commands" + }, + { + "path": "../goal" + } + ] +} diff --git a/packages/goal/tool-goal/README.md b/packages/goal/tool-goal/README.md index b2332307f8..0e6934c2e2 100644 --- a/packages/goal/tool-goal/README.md +++ b/packages/goal/tool-goal/README.md @@ -69,5 +69,5 @@ Schemas are prefix-stable while their definitions and visibility are unchanged. - **Semantic intent remains model judgment** — execution can prove direct human provenance, not whether a request is substantial enough to merit a goal. - **Same-condition blocking remains model judgment** — the runtime enforces distinct admitted-round count, not semantic equivalence of obstacles; an independent evaluator is deferred. -- **No scheduling or UI commands** — these tools mutate state only; the same-session driver and human command surfaces are separate stack layers. +- **No scheduling or direct human rendering** — these tools mutate state only; the same-session driver and [`dsh-command-goal`](../command-goal/README.md) are independent consumers of the same domain. - **Prompt registration is independent of filtering** — a scope may hide the tools while retaining their guidance unless the deployment scopes both registrations together. diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 49cd73a6c4..1a45c8b505 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -676,6 +676,9 @@ importers: '@deepseek-ai/dsh-app-boot': specifier: workspace:^ version: link:../../ui/app-boot + '@deepseek-ai/dsh-command-goal': + specifier: workspace:^ + version: link:../../goal/command-goal '@deepseek-ai/dsh-commands': specifier: workspace:^ version: link:../../ui/commands @@ -719,6 +722,12 @@ importers: '@deepseek-ai/dsh-fs-local': specifier: workspace:^ version: link:../../fs/fs-local + '@deepseek-ai/dsh-goal': + specifier: workspace:^ + version: link:../../goal/goal + '@deepseek-ai/dsh-goal-session': + specifier: workspace:^ + version: link:../../goal/goal-session '@deepseek-ai/dsh-home': specifier: workspace:^ version: link:../../util/home @@ -746,6 +755,9 @@ importers: '@deepseek-ai/dsh-tool-bash': specifier: workspace:^ version: link:../../bash/tool-bash + '@deepseek-ai/dsh-tool-goal': + specifier: workspace:^ + version: link:../../goal/tool-goal '@deepseek-ai/dsh-tool-skill': specifier: workspace:^ version: link:../../skill/tool-skill @@ -837,6 +849,9 @@ importers: '@deepseek-ai/dsh-app-boot': specifier: workspace:^ version: link:../../ui/app-boot + '@deepseek-ai/dsh-command-goal': + specifier: workspace:^ + version: link:../../goal/command-goal '@deepseek-ai/dsh-commands': specifier: workspace:^ version: link:../../ui/commands @@ -1000,6 +1015,30 @@ importers: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) + packages/goal/command-goal: + devDependencies: + '@cordisjs/plugin-loader': + specifier: workspace:^ + version: link:../../../vendor/loader + '@deepseek-ai/dsh-agent': + specifier: workspace:^ + version: link:../../core/agent + '@deepseek-ai/dsh-commands': + specifier: workspace:^ + version: link:../../ui/commands + '@deepseek-ai/dsh-goal': + specifier: workspace:^ + version: link:../goal + '@deepseek-ai/dsh-llm': + specifier: workspace:^ + version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session + cordis: + specifier: ^4.0.0-rc.7 + version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@vendor+loader) + packages/goal/goal: dependencies: schemastery: @@ -2635,6 +2674,12 @@ importers: '@deepseek-ai/dsh-fs-policy': specifier: workspace:^ version: link:../../packages/fs/fs-policy + '@deepseek-ai/dsh-goal': + specifier: workspace:^ + version: link:../../packages/goal/goal + '@deepseek-ai/dsh-goal-session': + specifier: workspace:^ + version: link:../../packages/goal/goal-session '@deepseek-ai/dsh-home': specifier: workspace:^ version: link:../../packages/util/home @@ -2743,6 +2788,9 @@ importers: '@deepseek-ai/dsh-tool-fs': specifier: workspace:^ version: link:../../packages/fs/tool-fs + '@deepseek-ai/dsh-tool-goal': + specifier: workspace:^ + version: link:../../packages/goal/tool-goal '@deepseek-ai/dsh-tool-skill': specifier: workspace:^ version: link:../../packages/skill/tool-skill diff --git a/python/sdk-runtime/package.json b/python/sdk-runtime/package.json index 161c5c3460..e49d7a5a03 100644 --- a/python/sdk-runtime/package.json +++ b/python/sdk-runtime/package.json @@ -24,6 +24,8 @@ "@deepseek-ai/dsh-fs": "workspace:^", "@deepseek-ai/dsh-fs-local": "workspace:^", "@deepseek-ai/dsh-fs-policy": "workspace:^", + "@deepseek-ai/dsh-goal": "workspace:^", + "@deepseek-ai/dsh-goal-session": "workspace:^", "@deepseek-ai/dsh-home": "workspace:^", "@deepseek-ai/dsh-hook-protocol": "workspace:^", "@deepseek-ai/dsh-hooks-claude": "workspace:^", @@ -60,6 +62,7 @@ "@deepseek-ai/dsh-tool-bash": "workspace:^", "@deepseek-ai/dsh-tool-cordis": "workspace:^", "@deepseek-ai/dsh-tool-fs": "workspace:^", + "@deepseek-ai/dsh-tool-goal": "workspace:^", "@deepseek-ai/dsh-tool-skill": "workspace:^", "@deepseek-ai/dsh-tool-subagent": "workspace:^", "@deepseek-ai/dsh-tool-tasks": "workspace:^", diff --git a/tsconfig.json b/tsconfig.json index 0e012a0ed2..085c533130 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -40,6 +40,7 @@ { "path": "./packages/goal/goal" }, { "path": "./packages/goal/tool-goal" }, { "path": "./packages/goal/goal-session" }, + { "path": "./packages/goal/command-goal" }, { "path": "./packages/context/time-context" }, { "path": "./packages/ui/user-interaction" }, { "path": "./packages/ui/user-approval" }, From e958c222a292807aafafb7815eff021f9ca49cad Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 20 Jul 2026 02:01:56 +0800 Subject: [PATCH 2/5] docs(agent-note): normalize goal command heading --- .../implemented/feature/2026-07-19-human-goal-command.i18n.yaml | 2 +- .../implemented/feature/2026-07-19-human-goal-command.zh.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.i18n.yaml b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.i18n.yaml index 14225a7d4f..e1a79533b9 100644 --- a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.i18n.yaml @@ -3,4 +3,4 @@ # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write 2026-07-19-human-goal-command.md: b195cd6d5d6e50672f2433e2f845e650d825a1f9 -2026-07-19-human-goal-command.zh.md: 11ffeb130e20f38c85e49c4109ece8913f3143ba +2026-07-19-human-goal-command.zh.md: 84a920c206b875d14349a69da556e945125b53c3 diff --git a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.zh.md b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.zh.md index 11ffeb130e..84a920c206 100644 --- a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.zh.md +++ b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.zh.md @@ -1,4 +1,4 @@ -# Agent Note：面向人类的 `/goal` 命令 +# Agent Note: 面向人类的 `/goal` 命令 Status: implemented From 491dafc78597100736e80230a42facde7fcb9445 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 20 Jul 2026 12:11:06 +0800 Subject: [PATCH 3/5] fix(goal): close human command surface gaps --- .../2026-07-19-human-goal-command.i18n.yaml | 4 ++-- .../feature/2026-07-19-human-goal-command.md | 10 +++++----- .../feature/2026-07-19-human-goal-command.zh.md | 10 +++++----- docs/config-catalog.md | 2 +- packages/examples/stdio-demo/README.md | 4 ++-- packages/examples/stdio-demo/src/index.ts | 4 ++-- .../stdio-demo/tests/stdio-agent.spec.ts | 16 ++++++++++++---- packages/goal/command-goal/README.md | 4 ++-- packages/goal/command-goal/src/index.ts | 9 +++++++-- .../goal/command-goal/tests/command-goal.spec.ts | 8 +++++--- pnpm-lock.yaml | 3 +++ python/sdk-runtime/package.json | 1 + 12 files changed, 47 insertions(+), 28 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.i18n.yaml b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.i18n.yaml index e1a79533b9..78bb900b27 100644 --- a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-19-human-goal-command.md: b195cd6d5d6e50672f2433e2f845e650d825a1f9 -2026-07-19-human-goal-command.zh.md: 84a920c206b875d14349a69da556e945125b53c3 +2026-07-19-human-goal-command.md: f458feae3bed8ef7b0ace6b8baaf5ae8b43e4cc8 +2026-07-19-human-goal-command.zh.md: 2fd79c2f50490e077cc69e93705a7b7bb242a082 diff --git a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.md b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.md index b195cd6d5d..f458feae3b 100644 --- a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.md +++ b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.md @@ -14,7 +14,7 @@ The command must also respect the goal design's two kinds of state. Durable phas `@deepseek-ai/dsh-command-goal` in `packages/goal/command-goal/` is a command producer over `ctx.commands` and `ctx.goals`. It registers one global `goal` definition for the TUI and ACP surfaces. The handler receives the exact target agent from command dispatch, reads or mutates that agent's goal through the domain service, and returns direct plain-text UI output. It does not import either adapter or the concrete agent loop. -The command follows the compact current Codex shape documented by the [official developer-command reference](https://learn.chatgpt.com/docs/developer-commands?surface=cli): bare status, a free-form objective, and `clear`, `edit`, `pause`, or `resume` controls. This repository keeps its own event-sourced state, round-count policy, and post-resume activation rule rather than copying Codex's SQLite, token budget, or automatic-resume behavior. +The command follows the compact Codex shape in the [public OpenAI Codex TUI dispatcher at commit `678157a`](https://github.com/openai/codex/blob/678157acaa819d5510adfe359abb5d0392cfe461/codex-rs/tui/src/chatwidget/slash_dispatch.rs#L750-L805): bare status, a free-form objective, and `clear`, `edit`, `pause`, or `resume` controls. The commit permalink makes the researched grammar durable even as Codex evolves. This repository keeps its own event-sourced state, round-count policy, and post-resume activation rule rather than copying Codex's SQLite, token budget, or automatic-resume behavior. ### Grammar and lifecycle verbs @@ -30,9 +30,9 @@ Control words are ASCII-case-insensitive after outer whitespace trimming. They a ### Output and failure boundary -Status output omits branded ids and compare-and-set revisions because those are model/plugin coordination details rather than human controls. It includes activation because that fact changes whether work will continue. Command hints are derived from the exact state: an armed active goal offers pause, a disarmed active or resumable stopped goal offers resume, budget-limited and completed states do not advertise an invalid resume. +Status output omits branded ids and compare-and-set revisions because those are model/plugin coordination details rather than human controls. It includes activation because that fact changes whether work will continue. Command hints are derived from the exact state: an armed active goal offers pause, a disarmed active or resumable stopped goal offers resume, a budget-limited goal explains that the agent must raise `maxGoalRounds` before resume, and a completed goal offers replacement or clear. -Expected `GoalError` failures become `CommandResult.error`, so invalid human operations receive a stable direct response and never enter model history. Other exceptions remain adapter-visible command failures; treating programmer faults as ordinary domain errors would hide defects. The command handler performs only synchronous domain mutations, so request cancellation is decided by the command registry before the mutation begins and there is no escaped asynchronous side effect to unwind. +Expected `GoalError` failures become one stable, branded-id-free `CommandResult.error`, so domain diagnostics do not leak compare-and-set internals into the human surface and invalid operations never enter model history. The current status supplies the actionable state-specific recovery. Other exceptions remain adapter-visible command failures; treating programmer faults as ordinary domain errors would hide defects. The command handler performs only synchronous domain mutations, so request cancellation is decided by the command registry before the mutation begins and there is no escaped asynchronous side effect to unwind. Generic slash input, status text, and errors are not persisted. Successful goal mutations use the existing `Agent.inject()` path, producing the raw model-visible goal snapshot or clear tombstone that persistence already owns. The command therefore changes no session format and introduces no second audit record that could disagree with the domain event. @@ -40,11 +40,11 @@ Generic slash input, status text, and errors are not persisted. Successful goal `agent-spine-demo` accepts an optional `goals` composition object containing the goal-domain and model-tool owner configs. Omission or `false` leaves the stack unmounted. This explicit opt-in is important for headless one-shot callers: their result API settles one correlated physical turn and must not silently become a long-running logical goal operation. -The terminal and ACP app bundles make the opposite product choice. They default `goals` to the owner defaults, mount the goal domain, model tools, same-session driver, command registry, and this producer, and accept `goals: false` as one coherent opt-out. The TUI and ACP bridge then discover the same definition through the generic registry. The line-oriented stdio mode does not consume the command plane; a typed `/goal` there remains an ordinary human prompt that the model may interpret through its separately authorized goal tools. +The interactive app bundles make the opposite product choice. ACP defaults `goals` to the owner defaults and mounts the goal domain, model tools, same-session driver, command registry, and this producer. The terminal app enables the same goal stack by default but mounts the producer only for TUI mode; line-oriented stdio does not consume the command plane, so a typed `/goal` there remains an ordinary human prompt that the model may interpret through its separately authorized goal tools. Both apps accept `goals: false` as one coherent stack opt-out. The Python SDK runtime closure ships this producer alongside ACP, commands, and the goal stack so an external `cordis.yml` can compose the same command surface. ## Testing -The producer suite uses the real command registry, goal service, agent registry, and session log. It covers Loader-safe exports, discovery on both surfaces, disposal, empty status, objective parsing, unfinished replacement refusal, inline edit, completed replacement, all missing-state controls, pause/resume/clear, every durable phase, armed/disarmed presentation, round-budget presentation, expected domain errors, unexpected failures, and persisted mutation records. App composition tests cover explicit spine opt-in, terminal/ACP defaults, coherent opt-out, forwarded domain/tool config, command discovery, and the expanded model-tool assembly. The keyless ACP snapshots pin the resulting `/goal` discovery metadata and goal tool schemas in the shipped app composition. +The producer suite uses the real command registry, goal service, agent registry, and session log. It covers Loader-safe exports, discovery on both surfaces, disposal, empty status, objective parsing, unfinished replacement refusal, inline edit, completed replacement, all missing-state controls, pause/resume/clear, every durable phase, armed/disarmed presentation, budget-exhaustion recovery guidance, sanitized domain errors, unexpected failures, and persisted mutation records. App composition tests cover explicit spine opt-in, TUI/ACP defaults, readline producer absence, coherent opt-out, forwarded domain/tool config, command discovery, the packaged-runtime closure, and the expanded model-tool assembly. The keyless ACP snapshots pin the resulting `/goal` discovery metadata and goal tool schemas in the shipped app composition. ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.zh.md b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.zh.md index 84a920c206..2fd79c2f50 100644 --- a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.zh.md +++ b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.zh.md @@ -14,7 +14,7 @@ Status: implemented 位于 `packages/goal/command-goal/` 的 `@deepseek-ai/dsh-command-goal` 是构建在 `ctx.commands` 与 `ctx.goals` 之上的命令生产方。它为 TUI 和 ACP 表面注册一个全局 `goal` 定义。处理器从命令分发接收准确的目标 agent（智能体），通过领域服务读取或改变该 agent 的目标，并返回直接的纯文本 UI 输出。它不导入任何适配器或具体 agent loop（智能体循环）。 -该命令遵循[官方开发者命令参考](https://learn.chatgpt.com/docs/developer-commands?surface=cli)所记录的当前 Codex 紧凑形态：无参数状态查询、自由形式目标描述，以及 `clear`、`edit`、`pause` 或 `resume` 控制。本仓库保留自身的事件溯源状态、回合计数策略与恢复后激活规则，而不复制 Codex 的 SQLite、token 预算或自动恢复行为。 +该命令遵循 [OpenAI Codex 公共仓库 `678157a` 提交中的 TUI 分发实现](https://github.com/openai/codex/blob/678157acaa819d5510adfe359abb5d0392cfe461/codex-rs/tui/src/chatwidget/slash_dispatch.rs#L750-L805)所呈现的紧凑形态：无参数状态查询、自由形式目标描述，以及 `clear`、`edit`、`pause` 或 `resume` 控制。固定到提交的链接使调研所得语法在 Codex 后续演进时仍可核验。本仓库保留自身的事件溯源状态、回合计数策略与恢复后激活规则，而不复制 Codex 的 SQLite、token 预算或自动恢复行为。 ### 语法与生命周期动词 @@ -30,9 +30,9 @@ Status: implemented ### 输出与失败边界 -状态输出省略品牌化 id 与比较并交换修订号，因为它们属于模型/插件协调细节，而不是人类控制项。输出包含激活态，因为该事实会改变工作是否继续。命令提示从准确状态派生：已激活的活跃目标提供暂停，未激活的活跃目标或可恢复的停止目标提供恢复，受预算限制和已完成状态不会宣传非法的恢复操作。 +状态输出省略品牌化 id 与比较并交换修订号，因为它们属于模型/插件协调细节，而不是人类控制项。输出包含激活态，因为该事实会改变工作是否继续。命令提示从准确状态派生：已激活的活跃目标提供暂停，未激活的活跃目标或可恢复的停止目标提供恢复，受预算限制的目标说明 agent 必须先提高 `maxGoalRounds` 才能恢复，已完成目标则提供替换或清除。 -预期的 `GoalError` 失败会变为 `CommandResult.error`，因此非法人类操作会收到稳定的直接响应，且绝不会进入模型历史。其他异常仍是适配器可见的命令失败；若把程序缺陷当成普通领域错误，就会隐藏问题。命令处理器只执行同步领域变更，因此请求取消会在变更开始前由命令注册表决定，不存在需要回滚的外逸异步副作用。 +预期的 `GoalError` 失败会变为一个稳定且不含品牌化 id 的 `CommandResult.error`，使领域诊断不会向人类表面泄露比较并交换内部细节，非法操作也绝不会进入模型历史。当前状态负责提供针对具体状态且可执行的恢复路径。其他异常仍是适配器可见的命令失败；若把程序缺陷当成普通领域错误，就会隐藏问题。命令处理器只执行同步领域变更，因此请求取消会在变更开始前由命令注册表决定，不存在需要回滚的外逸异步副作用。 通用斜杠输入、状态文本与错误不会持久化。成功的目标变更使用现有 `Agent.inject()` 路径，产出持久化本就拥有的原始模型可见目标快照或清除墓碑。因此该命令不会改变会话格式，也不会引入可能与领域事件不一致的第二份审计记录。 @@ -40,11 +40,11 @@ Status: implemented `agent-spine-demo` 接受可选的 `goals` 组合对象，其中包含目标领域与模型工具的所有者配置。省略或设为 `false` 时不会挂载该栈。对无头单次调用方而言，明确选择加入非常重要：它们的结果 API 会在一个相关物理轮次后结束，不能静默变成长时间运行的逻辑目标操作。 -终端和 ACP 应用包作出相反的产品选择。它们默认让 `goals` 使用所有者默认值，挂载目标领域、模型工具、同会话驱动器、命令注册表与本生产方，并接受 `goals: false` 作为一致的整体退出选项。随后，TUI 与 ACP 桥通过通用注册表发现同一个定义。行式 stdio 模式不消费命令平面；在那里输入的 `/goal` 仍是普通人类提示词，模型可以通过独立授权的目标工具解释它。 +交互式应用包作出相反的产品选择。ACP 默认让 `goals` 使用所有者默认值，并挂载目标领域、模型工具、同会话驱动器、命令注册表与本生产方。终端应用默认启用相同目标栈，但只在 TUI 模式挂载本生产方；行式 stdio 不消费命令平面，因此在那里输入的 `/goal` 仍是普通人类提示词，模型可以通过独立授权的目标工具解释它。两个应用都接受 `goals: false` 作为一致的整体退出选项。Python SDK 运行时闭包把本生产方与 ACP、命令及目标栈一并交付，使外部 `cordis.yml` 能组合相同命令表面。 ## 测试 -生产方测试套件使用真实命令注册表、目标服务、agent 注册表与会话日志。它覆盖 Loader 安全导出、两个表面的发现、资源释放、空状态、目标描述解析、拒绝未完成目标替换、行内编辑、已完成目标替换、所有缺失状态控制、暂停/恢复/清除、每个持久阶段、已激活/未激活展示、回合预算展示、预期领域错误、意外失败与持久变更记录。应用组合测试覆盖显式主干选择加入、终端/ACP 默认值、一致退出、转发的领域/工具配置、命令发现与扩展后的模型工具组装。无密钥 ACP 快照固定了交付应用组合中的 `/goal` 发现元数据和目标工具 schema。 +生产方测试套件使用真实命令注册表、目标服务、agent 注册表与会话日志。它覆盖 Loader 安全导出、两个表面的发现、资源释放、空状态、目标描述解析、拒绝未完成目标替换、行内编辑、已完成目标替换、所有缺失状态控制、暂停/恢复/清除、每个持久阶段、已激活/未激活展示、预算耗尽恢复提示、经净化的领域错误、意外失败与持久变更记录。应用组合测试覆盖显式主干选择加入、TUI/ACP 默认值、readline 不挂载生产方、一致退出、转发的领域/工具配置、命令发现、打包运行时闭包与扩展后的模型工具组装。无密钥 ACP 快照固定了交付应用组合中的 `/goal` 发现元数据和目标工具 schema。 ## 考虑过的替代方案 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 0087f417dd..a8840b2bca 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -891,7 +891,7 @@ export interface Config { toolBash?: NonNullable /** Generic background-task controls forwarded through agent-core; set false to omit their tool surface. */ toolTasks?: NonNullable - /** Persisted same-session goals; owner defaults enable them, or false disables the stack and command. */ + /** Persisted same-session goals; owner defaults enable them, or false disables the stack and TUI command. */ goals?: agentCore.GoalConfig | false /** * If set, the pre-created agent RESUMES this persisted session id instead of diff --git a/packages/examples/stdio-demo/README.md b/packages/examples/stdio-demo/README.md index 4f452aa6d9..0f275485b0 100644 --- a/packages/examples/stdio-demo/README.md +++ b/packages/examples/stdio-demo/README.md @@ -12,7 +12,7 @@ A terminal chat always wants the same cluster, so the package owns it rather tha |---|---| | `@deepseek-ai/dsh-agent-spine-demo` | the spine, pre-creating a `main` agent from this app's provider/model pair with `process.cwd()` as the fresh session cwd and carrying its `persona` | | `@deepseek-ai/dsh-commands` | the human-command registry consumed by the TUI front door and optional command plugins | -| `@deepseek-ai/dsh-command-goal` | the direct `/goal` producer; the app enables the spine's persisted-goal stack with it | +| `@deepseek-ai/dsh-command-goal` | the direct `/goal` producer mounted only for the TUI front door; readline retains the model-mediated goal path | | `@deepseek-ai/dsh-session-persistence-jsonl` | durable JSONL session log under `persistenceRoot` | | `@deepseek-ai/dsh-user-interaction` | the human question/answer seam used by confirmation tools | | `@deepseek-ai/dsh-tool-ask-user` | the model-facing `ask_user_question` tool | @@ -38,7 +38,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `skills` | owner defaults | registry-cache, local-provider, and model-facing skill-tool config, routed through `dsh-agent-spine-demo` | | `toolBash` | owner defaults | model-facing bash config routed through `dsh-agent-spine-demo`, including bash's producer-local `enableRunInBackground` | | `toolTasks` | owner defaults | generic `task_output` wait bounds routed through `dsh-agent-spine-demo` | -| `goals` | owner defaults | persisted goal-domain and model-tool config; `false` removes the goal stack and `/goal` producer | +| `goals` | owner defaults | persisted goal-domain and model-tool config; `false` removes the goal stack and the TUI `/goal` producer | | `persistenceRoot` | `./.sessions` | the JSONL backend's root directory | | `welcome` | `ready.` | terminal banner / TUI subtitle | | `ui` | `{ mode: 'auto' }` | terminal mode (`auto` / `readline` / `tui`) and nested TUI presentation config | diff --git a/packages/examples/stdio-demo/src/index.ts b/packages/examples/stdio-demo/src/index.ts index 307a0db483..5e399a56ca 100644 --- a/packages/examples/stdio-demo/src/index.ts +++ b/packages/examples/stdio-demo/src/index.ts @@ -101,7 +101,7 @@ export interface Config { toolBash?: NonNullable /** Generic background-task controls forwarded through agent-core; set false to omit their tool surface. */ toolTasks?: NonNullable - /** Persisted same-session goals; owner defaults enable them, or false disables the stack and command. */ + /** Persisted same-session goals; owner defaults enable them, or false disables the stack and TUI command. */ goals?: agentCore.GoalConfig | false /** * If set, the pre-created agent RESUMES this persisted session id instead of @@ -152,7 +152,7 @@ export function composeTerminalApp(ctx: Context, config: Config, isTTY: boolean) const goals = config.goals ?? {} if (mode === 'readline') ctx.plugin(ConsoleExporter) ctx.plugin(CommandService) - if (goals !== false) ctx.plugin(commandGoal) + if (mode === 'tui' && goals !== false) ctx.plugin(commandGoal) ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? DEFAULT_PERSISTENCE_ROOT }) ctx.plugin(UserInteractionService) if (mode === 'tui') { diff --git a/packages/examples/stdio-demo/tests/stdio-agent.spec.ts b/packages/examples/stdio-demo/tests/stdio-agent.spec.ts index f20860f1eb..2480cb704d 100644 --- a/packages/examples/stdio-demo/tests/stdio-agent.spec.ts +++ b/packages/examples/stdio-demo/tests/stdio-agent.spec.ts @@ -118,17 +118,25 @@ describe('dsh-stdio-demo app', () => { calls.length = 0 stdioAgent.composeTerminalApp(ctx, { - provider: 'mock', model: 'mock', workspaceContext: false, goals: false, ui: { mode: 'readline' }, + provider: 'mock', model: 'mock', workspaceContext: false, goals: false, ui: { mode: 'tui' }, + }, true) + expect(calls.map(call => call.name)).toContain('ui-tui') + expect(calls.map(call => call.name)).not.toContain('command-goal') + expect(calls.find(call => call.name === 'agent-spine-demo')?.config).toMatchObject({ goals: false }) + + calls.length = 0 + stdioAgent.composeTerminalApp(ctx, { + provider: 'mock', model: 'mock', workspaceContext: false, ui: { mode: 'readline' }, }, false) expect(calls.map(call => call.name)).toContain('ui-stdio') expect(calls.map(call => call.name)).toContain('ConsoleExporter') expect(calls.map(call => call.name)).not.toContain('ui-tui') expect(calls.map(call => call.name)).not.toContain('command-goal') - expect(calls.find(call => call.name === 'agent-spine-demo')?.config).toMatchObject({ goals: false }) + expect(calls.find(call => call.name === 'agent-spine-demo')?.config).toMatchObject({ goals: {} }) }) it('composes the spine + front-door cluster and pre-creates the main agent', async () => { - const ctx = await mount({ provider: 'mock', model: 'mock', persona: 'hi', persistenceRoot: '/tmp/dsh-stdio-demo-spec', skills: await isolatedSkillsConfig(), workspaceContext: false }) + const ctx = await mount({ provider: 'mock', model: 'mock', persona: 'hi', persistenceRoot: '/tmp/dsh-stdio-demo-spec', skills: await isolatedSkillsConfig(), workspaceContext: false, ui: { mode: 'readline' } }) // The spine services (brought up by the agent-spine-demo bundle) are all present. expect(ctx.get('agents')).toBeDefined() expect(ctx.get('agentLoop')).toBeDefined() @@ -145,7 +153,7 @@ describe('dsh-stdio-demo app', () => { expect(agent?.id).toBe(agent?.session.id) expect(agent?.id).toMatch(/^main-session-/) expect(agent?.session.header.cwd).toBe(process.cwd()) - expect(ctx.commands.find(agent!, 'tui', 'goal')).toBeDefined() + expect(ctx.commands.find(agent!, 'tui', 'goal')).toBeUndefined() await ctx.fiber.dispose() }) diff --git a/packages/goal/command-goal/README.md b/packages/goal/command-goal/README.md index c971297cd3..2fa7323789 100644 --- a/packages/goal/command-goal/README.md +++ b/packages/goal/command-goal/README.md @@ -15,7 +15,7 @@ Human-facing `/goal` control over [`ctx.goals`](../goal/README.md). The plugin r Control words are case-insensitive only when they occupy the complete input. Every other non-empty suffix is an objective, so `/goal pause after verification` creates that literal objective. The goal domain trims and validates objectives. Because the generic command plane has no modal editor or confirmation primitive, `edit` takes its replacement inline and an unfinished replacement returns a direct error instructing the user to edit or clear. -Expected domain rejections become direct command errors. Unexpected implementation failures still reject dispatch so adapters can report them as command failures. Generic command text and output remain live UI state; every accepted mutation is persisted and made model-visible by `dsh-goal` rather than by this plugin. +Expected domain rejections become stable direct command errors without exposing branded ids or revisions. Unexpected implementation failures still reject dispatch so adapters can report them as command failures. Generic command text and output remain live UI state; every accepted mutation is persisted and made model-visible by `dsh-goal` rather than by this plugin. ## Composition @@ -30,7 +30,7 @@ The producer injects `commands` and `goals`. A custom app mounts their owners pl name: '@deepseek-ai/dsh-command-goal' ``` -The terminal and ACP demo apps enable the complete persisted-goal stack and this command by default; `goals: false` removes both. The UI-less `agent-spine-demo` requires an explicit `goals: {}` so headless one-shot callers do not silently change from one physical turn to a multi-round operation. +The TUI and ACP demo apps enable the complete persisted-goal stack and this command by default; `goals: false` removes both. The terminal app's readline mode keeps the model-mediated goal stack but does not mount this producer because that front door does not consume commands. The UI-less `agent-spine-demo` requires an explicit `goals: {}` so headless one-shot callers do not silently change from one physical turn to a multi-round operation. ## Model Experience diff --git a/packages/goal/command-goal/src/index.ts b/packages/goal/command-goal/src/index.ts index 3fff035adc..a8e73cba7e 100644 --- a/packages/goal/command-goal/src/index.ts +++ b/packages/goal/command-goal/src/index.ts @@ -69,7 +69,7 @@ function commandHint(goal: GoalView): string { case 'usage-limited': return '/goal edit , /goal resume, /goal clear' case 'budget-limited': - return '/goal edit , /goal clear' + return '/goal edit , /goal clear; after the agent raises the round cap, /goal resume' case 'complete': return '/goal , /goal clear' /* v8 ignore next 2 -- the active branch and every non-active phase are handled above */ @@ -149,7 +149,12 @@ function executeGoalCommand(ctx: Context, invocation: CommandInvocation): Comman default: return assertNever(command, 'goal command') } } catch (error: unknown) { - if (error instanceof GoalError) return { kind: 'error', text: error.message } + if (error instanceof GoalError) { + return { + kind: 'error', + text: 'The goal command is not valid for the current state. Run /goal to view available commands.', + } + } throw error } } diff --git a/packages/goal/command-goal/tests/command-goal.spec.ts b/packages/goal/command-goal/tests/command-goal.spec.ts index e13f5e9822..a3d48857c4 100644 --- a/packages/goal/command-goal/tests/command-goal.spec.ts +++ b/packages/goal/command-goal/tests/command-goal.spec.ts @@ -197,8 +197,10 @@ describe('/goal human command', () => { const test = await harness() await run(test, ' work') const redundantResume = await run(test, ' RESUME') - expect(redundantResume.kind).toBe('error') - expect(redundantResume.text).toContain('already active and armed') + expect(redundantResume).toEqual({ + kind: 'error', + text: 'The goal command is not valid for the current state. Run /goal to view available commands.', + }) const paused = await run(test, ' PAUSE') expect(paused.kind).toBe('success') expect(paused.text).toContain('Goal paused') @@ -238,7 +240,7 @@ describe('/goal human command', () => { goal = test.ctx.goals.markBudgetLimited(test.agent, ref(goal)) const limited = await run(test) expect(limited.text).toContain('Status: limited by round budget') - expect(limited.text).not.toContain('/goal resume') + expect(limited.text).toContain('after the agent raises the round cap, /goal resume') goal = test.ctx.goals.complete(test.agent, ref(goal)) const complete = await run(test) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 1a45c8b505..9ff42e490e 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -2656,6 +2656,9 @@ importers: '@deepseek-ai/dsh-code-runtime-worker': specifier: workspace:^ version: link:../../packages/code-runtime/code-runtime-worker + '@deepseek-ai/dsh-command-goal': + specifier: workspace:^ + version: link:../../packages/goal/command-goal '@deepseek-ai/dsh-commands': specifier: workspace:^ version: link:../../packages/ui/commands diff --git a/python/sdk-runtime/package.json b/python/sdk-runtime/package.json index e49d7a5a03..d189399e21 100644 --- a/python/sdk-runtime/package.json +++ b/python/sdk-runtime/package.json @@ -18,6 +18,7 @@ "@deepseek-ai/dsh-brand": "workspace:^", "@deepseek-ai/dsh-code-runtime": "workspace:^", "@deepseek-ai/dsh-code-runtime-worker": "workspace:^", + "@deepseek-ai/dsh-command-goal": "workspace:^", "@deepseek-ai/dsh-commands": "workspace:^", "@deepseek-ai/dsh-compact": "workspace:^", "@deepseek-ai/dsh-compact-basic": "workspace:^", From 015ad420af375aa17280962d15265351997ccdcf Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 20 Jul 2026 18:06:22 +0800 Subject: [PATCH 4/5] fix(goal): align human commands with blocker reasons --- .../2026-07-19-human-goal-command.i18n.yaml | 4 +- .../feature/2026-07-19-human-goal-command.md | 8 ++-- .../2026-07-19-human-goal-command.zh.md | 8 ++-- ...26-07-19-model-facing-goal-tools.i18n.yaml | 4 +- .../examples/acp-demo/tests/acp-agent.spec.ts | 2 +- .../agent-spine-demo/tests/agent-core.spec.ts | 21 ++++++--- .../stdio-demo/tests/stdio-agent.spec.ts | 2 +- packages/goal/command-goal/README.md | 4 +- packages/goal/command-goal/src/index.ts | 12 ++--- .../command-goal/tests/command-goal.spec.ts | 44 +++++-------------- 10 files changed, 48 insertions(+), 61 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.i18n.yaml b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.i18n.yaml index 78bb900b27..3505cfabca 100644 --- a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-19-human-goal-command.md: f458feae3bed8ef7b0ace6b8baaf5ae8b43e4cc8 -2026-07-19-human-goal-command.zh.md: 2fd79c2f50490e077cc69e93705a7b7bb242a082 +2026-07-19-human-goal-command.md: e2a59c3bddd7e135b0878cb59c964c3e7be64002 +2026-07-19-human-goal-command.zh.md: 0d6a0e22de091cd7a4a00ef59f1ac1b936c930f9 diff --git a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.md b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.md index f458feae3b..e2a59c3bdd 100644 --- a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.md +++ b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.md @@ -12,7 +12,7 @@ The command must also respect the goal design's two kinds of state. Durable phas ## Decision -`@deepseek-ai/dsh-command-goal` in `packages/goal/command-goal/` is a command producer over `ctx.commands` and `ctx.goals`. It registers one global `goal` definition for the TUI and ACP surfaces. The handler receives the exact target agent from command dispatch, reads or mutates that agent's goal through the domain service, and returns direct plain-text UI output. It does not import either adapter or the concrete agent loop. +`@deepseek-ai/dsh-command-goal` in `packages/goal/command-goal/` is a command producer over `ctx.commands` and `ctx.goals`. It registers one global `goal` definition, so every command adapter in the composition discovers the same command; an incompatible app omits this producer rather than masking its registration at an adapter. The handler receives the exact target agent from command dispatch, reads or mutates that agent's goal through the domain service, and returns direct plain-text UI output. It does not import either adapter or the concrete agent loop. The command follows the compact Codex shape in the [public OpenAI Codex TUI dispatcher at commit `678157a`](https://github.com/openai/codex/blob/678157acaa819d5510adfe359abb5d0392cfe461/codex-rs/tui/src/chatwidget/slash_dispatch.rs#L750-L805): bare status, a free-form objective, and `clear`, `edit`, `pause`, or `resume` controls. The commit permalink makes the researched grammar durable even as Codex evolves. This repository keeps its own event-sourced state, round-count policy, and post-resume activation rule rather than copying Codex's SQLite, token budget, or automatic-resume behavior. @@ -30,7 +30,7 @@ Control words are ASCII-case-insensitive after outer whitespace trimming. They a ### Output and failure boundary -Status output omits branded ids and compare-and-set revisions because those are model/plugin coordination details rather than human controls. It includes activation because that fact changes whether work will continue. Command hints are derived from the exact state: an armed active goal offers pause, a disarmed active or resumable stopped goal offers resume, a budget-limited goal explains that the agent must raise `maxGoalRounds` before resume, and a completed goal offers replacement or clear. +Status output omits branded ids and compare-and-set revisions because those are model/plugin coordination details rather than human controls. It includes activation because that fact changes whether work will continue, and a blocked goal includes its durable policy code and human-readable explanation. Command hints are derived from the exact state: an armed active goal offers pause, a disarmed active or paused/blocked goal offers resume, and a completed goal offers replacement or clear. Expected `GoalError` failures become one stable, branded-id-free `CommandResult.error`, so domain diagnostics do not leak compare-and-set internals into the human surface and invalid operations never enter model history. The current status supplies the actionable state-specific recovery. Other exceptions remain adapter-visible command failures; treating programmer faults as ordinary domain errors would hide defects. The command handler performs only synchronous domain mutations, so request cancellation is decided by the command registry before the mutation begins and there is no escaped asynchronous side effect to unwind. @@ -40,11 +40,11 @@ Generic slash input, status text, and errors are not persisted. Successful goal `agent-spine-demo` accepts an optional `goals` composition object containing the goal-domain and model-tool owner configs. Omission or `false` leaves the stack unmounted. This explicit opt-in is important for headless one-shot callers: their result API settles one correlated physical turn and must not silently become a long-running logical goal operation. -The interactive app bundles make the opposite product choice. ACP defaults `goals` to the owner defaults and mounts the goal domain, model tools, same-session driver, command registry, and this producer. The terminal app enables the same goal stack by default but mounts the producer only for TUI mode; line-oriented stdio does not consume the command plane, so a typed `/goal` there remains an ordinary human prompt that the model may interpret through its separately authorized goal tools. Both apps accept `goals: false` as one coherent stack opt-out. The Python SDK runtime closure ships this producer alongside ACP, commands, and the goal stack so an external `cordis.yml` can compose the same command surface. +The interactive app bundles make the opposite product choice. ACP defaults `goals` to the owner defaults and mounts the goal domain, model tools, same-session driver, command registry, and this producer. The terminal app enables the same goal stack by default but mounts the producer only for TUI mode; line-oriented stdio does not consume the command plane, so a typed `/goal` there remains an ordinary human prompt that the model may interpret through its separately authorized goal tools. Both apps accept `goals: false` as one coherent stack opt-out. The Python SDK runtime closure ships this producer alongside ACP, commands, and the goal stack so an external `cordis.yml` can compose the same command. ## Testing -The producer suite uses the real command registry, goal service, agent registry, and session log. It covers Loader-safe exports, discovery on both surfaces, disposal, empty status, objective parsing, unfinished replacement refusal, inline edit, completed replacement, all missing-state controls, pause/resume/clear, every durable phase, armed/disarmed presentation, budget-exhaustion recovery guidance, sanitized domain errors, unexpected failures, and persisted mutation records. App composition tests cover explicit spine opt-in, TUI/ACP defaults, readline producer absence, coherent opt-out, forwarded domain/tool config, command discovery, the packaged-runtime closure, and the expanded model-tool assembly. The keyless ACP snapshots pin the resulting `/goal` discovery metadata and goal tool schemas in the shipped app composition. +The producer suite uses the real command registry, goal service, agent registry, and session log. It covers Loader-safe exports, registry discovery, disposal, empty status, objective parsing, unfinished replacement refusal, inline edit, completed replacement, all missing-state controls, pause/resume/clear, every durable phase, blocked code/explanation presentation, armed/disarmed presentation, sanitized domain errors, unexpected failures, and persisted mutation records. App composition tests cover explicit spine opt-in, TUI/ACP defaults, readline producer absence, coherent opt-out, forwarded domain/tool config, command discovery, the packaged-runtime closure, and the expanded model-tool assembly. A keyless snapshot boots the shipped ACP application, observes its advertised `/goal` metadata, invokes `/goal` directly, and pins the no-model-turn result; the surrounding ACP snapshots also pin the goal tool schemas in that composition. ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.zh.md b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.zh.md index 2fd79c2f50..0d6a0e22de 100644 --- a/.agents/notes/implemented/feature/2026-07-19-human-goal-command.zh.md +++ b/.agents/notes/implemented/feature/2026-07-19-human-goal-command.zh.md @@ -12,7 +12,7 @@ Status: implemented ## 决策 -位于 `packages/goal/command-goal/` 的 `@deepseek-ai/dsh-command-goal` 是构建在 `ctx.commands` 与 `ctx.goals` 之上的命令生产方。它为 TUI 和 ACP 表面注册一个全局 `goal` 定义。处理器从命令分发接收准确的目标 agent（智能体），通过领域服务读取或改变该 agent 的目标，并返回直接的纯文本 UI 输出。它不导入任何适配器或具体 agent loop（智能体循环）。 +位于 `packages/goal/command-goal/` 的 `@deepseek-ai/dsh-command-goal` 是构建在 `ctx.commands` 与 `ctx.goals` 之上的命令生产方。它注册一个全局 `goal` 定义，因此组合中的每个命令适配器都会发现同一个命令；不兼容的应用应省略该生产方，而不是在适配器处屏蔽其注册。处理器从命令分发接收准确的目标 agent（智能体），通过领域服务读取或改变该 agent 的目标，并返回直接的纯文本 UI 输出。它不导入任何适配器或具体 agent loop（智能体循环）。 该命令遵循 [OpenAI Codex 公共仓库 `678157a` 提交中的 TUI 分发实现](https://github.com/openai/codex/blob/678157acaa819d5510adfe359abb5d0392cfe461/codex-rs/tui/src/chatwidget/slash_dispatch.rs#L750-L805)所呈现的紧凑形态：无参数状态查询、自由形式目标描述，以及 `clear`、`edit`、`pause` 或 `resume` 控制。固定到提交的链接使调研所得语法在 Codex 后续演进时仍可核验。本仓库保留自身的事件溯源状态、回合计数策略与恢复后激活规则，而不复制 Codex 的 SQLite、token 预算或自动恢复行为。 @@ -30,7 +30,7 @@ Status: implemented ### 输出与失败边界 -状态输出省略品牌化 id 与比较并交换修订号，因为它们属于模型/插件协调细节，而不是人类控制项。输出包含激活态，因为该事实会改变工作是否继续。命令提示从准确状态派生：已激活的活跃目标提供暂停，未激活的活跃目标或可恢复的停止目标提供恢复，受预算限制的目标说明 agent 必须先提高 `maxGoalRounds` 才能恢复，已完成目标则提供替换或清除。 +状态输出省略品牌化 id 与比较并交换修订号，因为它们属于模型/插件协调细节，而不是人类控制项。输出包含激活态，因为该事实会改变工作是否继续；被阻塞的目标还会包含其持久策略代码和面向人类的说明。命令提示从准确状态派生：已激活的活跃目标提供暂停，未激活的活跃目标或已暂停/被阻塞目标提供恢复，已完成目标则提供替换或清除。 预期的 `GoalError` 失败会变为一个稳定且不含品牌化 id 的 `CommandResult.error`，使领域诊断不会向人类表面泄露比较并交换内部细节，非法操作也绝不会进入模型历史。当前状态负责提供针对具体状态且可执行的恢复路径。其他异常仍是适配器可见的命令失败；若把程序缺陷当成普通领域错误，就会隐藏问题。命令处理器只执行同步领域变更，因此请求取消会在变更开始前由命令注册表决定，不存在需要回滚的外逸异步副作用。 @@ -40,11 +40,11 @@ Status: implemented `agent-spine-demo` 接受可选的 `goals` 组合对象，其中包含目标领域与模型工具的所有者配置。省略或设为 `false` 时不会挂载该栈。对无头单次调用方而言，明确选择加入非常重要：它们的结果 API 会在一个相关物理轮次后结束，不能静默变成长时间运行的逻辑目标操作。 -交互式应用包作出相反的产品选择。ACP 默认让 `goals` 使用所有者默认值，并挂载目标领域、模型工具、同会话驱动器、命令注册表与本生产方。终端应用默认启用相同目标栈，但只在 TUI 模式挂载本生产方；行式 stdio 不消费命令平面，因此在那里输入的 `/goal` 仍是普通人类提示词，模型可以通过独立授权的目标工具解释它。两个应用都接受 `goals: false` 作为一致的整体退出选项。Python SDK 运行时闭包把本生产方与 ACP、命令及目标栈一并交付，使外部 `cordis.yml` 能组合相同命令表面。 +交互式应用包作出相反的产品选择。ACP 默认让 `goals` 使用所有者默认值，并挂载目标领域、模型工具、同会话驱动器、命令注册表与本生产方。终端应用默认启用相同目标栈，但只在 TUI 模式挂载本生产方；行式 stdio 不消费命令平面，因此在那里输入的 `/goal` 仍是普通人类提示词，模型可以通过独立授权的目标工具解释它。两个应用都接受 `goals: false` 作为一致的整体退出选项。Python SDK 运行时闭包把本生产方与 ACP、命令及目标栈一并交付，使外部 `cordis.yml` 能组合相同命令。 ## 测试 -生产方测试套件使用真实命令注册表、目标服务、agent 注册表与会话日志。它覆盖 Loader 安全导出、两个表面的发现、资源释放、空状态、目标描述解析、拒绝未完成目标替换、行内编辑、已完成目标替换、所有缺失状态控制、暂停/恢复/清除、每个持久阶段、已激活/未激活展示、预算耗尽恢复提示、经净化的领域错误、意外失败与持久变更记录。应用组合测试覆盖显式主干选择加入、TUI/ACP 默认值、readline 不挂载生产方、一致退出、转发的领域/工具配置、命令发现、打包运行时闭包与扩展后的模型工具组装。无密钥 ACP 快照固定了交付应用组合中的 `/goal` 发现元数据和目标工具 schema。 +生产方测试套件使用真实命令注册表、目标服务、agent 注册表与会话日志。它覆盖 Loader 安全导出、注册表发现、资源释放、空状态、目标描述解析、拒绝未完成目标替换、行内编辑、已完成目标替换、所有缺失状态控制、暂停/恢复/清除、每个持久阶段、阻塞代码/说明展示、已激活/未激活展示、经净化的领域错误、意外失败与持久变更记录。应用组合测试覆盖显式主干选择加入、TUI/ACP 默认值、readline 不挂载生产方、一致退出、转发的领域/工具配置、命令发现、打包运行时闭包与扩展后的模型工具组装。一个无密钥快照会启动交付的 ACP 应用，观察其公布的 `/goal` 元数据，直接调用 `/goal`，并固定不经过模型轮次的结果；周边 ACP 快照还会固定该组合中的目标工具 schema。 ## 考虑过的替代方案 diff --git a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml index fd97351a0e..e53c591aa5 100644 --- a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-19-model-facing-goal-tools.md: 2ef77b53cd8b95c9cdffd12e20c723fb1cff3a5d -2026-07-19-model-facing-goal-tools.zh.md: 08619600355c71ccd30d608e3c4e5a7fba753d4e +2026-07-19-model-facing-goal-tools.md: 7cc3907d708115207e166455ea988120a03d768b +2026-07-19-model-facing-goal-tools.zh.md: 1a381160354d6a2a24f957f41bc9e375c1ab01ca diff --git a/packages/examples/acp-demo/tests/acp-agent.spec.ts b/packages/examples/acp-demo/tests/acp-agent.spec.ts index a9a1d6178d..b6886a7e12 100644 --- a/packages/examples/acp-demo/tests/acp-agent.spec.ts +++ b/packages/examples/acp-demo/tests/acp-agent.spec.ts @@ -96,7 +96,7 @@ describe('dsh-acp-demo composition', () => { sessionId: 'disabled-goals' as import('@deepseek-ai/dsh-session').SessionId, agentOptions: { provider: 'mock', model: 'mock' }, }) - expect(ctx.commands.find(handle.agent, 'acp', 'goal')).toBeUndefined() + expect(ctx.commands.find(handle.agent, 'goal')).toBeUndefined() await handle.dispose() await ctx.fiber.dispose() }) diff --git a/packages/examples/agent-spine-demo/tests/agent-core.spec.ts b/packages/examples/agent-spine-demo/tests/agent-core.spec.ts index acb93f758b..6c8837652d 100644 --- a/packages/examples/agent-spine-demo/tests/agent-core.spec.ts +++ b/packages/examples/agent-spine-demo/tests/agent-core.spec.ts @@ -121,14 +121,16 @@ describe('dsh-agent-spine-demo bundle', () => { it('opts into the configured persisted-goal domain, tools, and same-session driver', async () => { const ctx = await mount({ workspaceContext: false, + agents: [{ id: SessionId('configured-goal'), provider: 'mock', model: 'mock' }], goals: { domain: { defaultMaxGoalRounds: 17 }, tool: { blockedAfterConsecutiveRounds: 5 }, }, }) - expect(ctx.goals.resolveCreate({ objective: 'configured' })).toEqual({ - objective: 'configured', - maxGoalRounds: 17, + const agent = ctx.agents.list()[0] + if (agent === undefined) throw new Error('configured goal test has no live agent') + expect(ctx.goals.create(agent, { objective: 'configured' })).toMatchObject({ + objective: 'configured', maxGoalRounds: 17, }) expect(['create_goal', 'get_goal', 'update_goal'].map(name => ctx.tools.get(name)?.name)) .toEqual(['create_goal', 'get_goal', 'update_goal']) @@ -199,11 +201,16 @@ describe('dsh-agent-spine-demo bundle', () => { it('uses owner defaults for a schema-bypassing empty goal opt-in', async () => { const ctx = new Context() - agentCore.apply(ctx, { workspaceContext: false, goals: {} }) + agentCore.apply(ctx, { + workspaceContext: false, + agents: [{ id: SessionId('defaulted-goal'), provider: 'mock', model: 'mock' }], + goals: {}, + }) await new Promise(resolve => setTimeout(resolve, 50)) - expect(ctx.goals.resolveCreate({ objective: 'defaulted' })).toEqual({ - objective: 'defaulted', - maxGoalRounds: 256, + const agent = ctx.agents.list()[0] + if (agent === undefined) throw new Error('default goal test has no live agent') + expect(ctx.goals.create(agent, { objective: 'defaulted' })).toMatchObject({ + objective: 'defaulted', maxGoalRounds: 256, }) expect(ctx.tools.get('get_goal')).toBeDefined() await ctx.fiber.dispose() diff --git a/packages/examples/stdio-demo/tests/stdio-agent.spec.ts b/packages/examples/stdio-demo/tests/stdio-agent.spec.ts index 2480cb704d..de8481da4f 100644 --- a/packages/examples/stdio-demo/tests/stdio-agent.spec.ts +++ b/packages/examples/stdio-demo/tests/stdio-agent.spec.ts @@ -153,7 +153,7 @@ describe('dsh-stdio-demo app', () => { expect(agent?.id).toBe(agent?.session.id) expect(agent?.id).toMatch(/^main-session-/) expect(agent?.session.header.cwd).toBe(process.cwd()) - expect(ctx.commands.find(agent!, 'tui', 'goal')).toBeUndefined() + expect(ctx.commands.find(agent!, 'goal')).toBeUndefined() await ctx.fiber.dispose() }) diff --git a/packages/goal/command-goal/README.md b/packages/goal/command-goal/README.md index 2fa7323789..f766cd3ece 100644 --- a/packages/goal/command-goal/README.md +++ b/packages/goal/command-goal/README.md @@ -1,12 +1,12 @@ # @deepseek-ai/dsh-command-goal -Human-facing `/goal` control over [`ctx.goals`](../goal/README.md). The plugin registers one global command through [`ctx.commands`](../../ui/commands/README.md); TUI and ACP discover and execute it without a model turn. The [human goal-command Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-human-goal-command.md) owns the UX and composition decisions. +Human-facing `/goal` control over [`ctx.goals`](../goal/README.md). The plugin registers one global command through [`ctx.commands`](../../ui/commands/README.md), so every composed command adapter discovers it; the shipped TUI and ACP execute it without a model turn. The [human goal-command Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-human-goal-command.md) owns the UX and composition decisions. ## Command contract | Input | Result | |---|---| -| `/goal` | Show the current objective, durable phase, round count/cap, process-local activation, and valid next commands; show usage when no goal exists. | +| `/goal` | Show the current objective, durable phase, round count/cap, process-local activation, and valid next commands; a blocked goal also shows its policy code and explanation, while no goal shows usage. | | `/goal ` | Create and arm a goal, or replace a completed goal with a fresh identity. An unfinished goal is never replaced without an explicit clear. | | `/goal edit ` | Edit the current objective without changing its phase or activation. Editing a completed goal creates a fresh active goal. | | `/goal pause` | Pause an active goal and disarm continuation. | diff --git a/packages/goal/command-goal/src/index.ts b/packages/goal/command-goal/src/index.ts index a8e73cba7e..93ed7923b8 100644 --- a/packages/goal/command-goal/src/index.ts +++ b/packages/goal/command-goal/src/index.ts @@ -48,8 +48,6 @@ function phaseLabel(phase: GoalPhase): string { case 'active': return 'active' case 'paused': return 'paused' case 'blocked': return 'blocked' - case 'usage-limited': return 'usage limited' - case 'budget-limited': return 'limited by round budget' case 'complete': return 'complete' /* v8 ignore next 2 -- GoalPhase is closed and every member is handled above */ default: return assertNever(phase, 'goal phase') @@ -66,10 +64,7 @@ function commandHint(goal: GoalView): string { switch (goal.phase) { case 'paused': case 'blocked': - case 'usage-limited': return '/goal edit , /goal resume, /goal clear' - case 'budget-limited': - return '/goal edit , /goal clear; after the agent raises the round cap, /goal resume' case 'complete': return '/goal , /goal clear' /* v8 ignore next 2 -- the active branch and every non-active phase are handled above */ @@ -79,11 +74,16 @@ function commandHint(goal: GoalView): string { /** Render direct UI output without exposing compare-and-set internals. */ function renderGoal(title: string, goal: GoalView): CommandResult { + const reason = goal.phase === 'blocked' ? goal.blockedReason : undefined + /* v8 ignore next -- durable replay guarantees every blocked goal carries its validated reason */ + if (goal.phase === 'blocked' && reason === undefined) throw new TypeError('blocked goal is missing its reason') + const blocker = reason === undefined ? [] : [`Blocker: ${reason.code}: ${reason.message}`] return { kind: 'success', text: [ title, `Status: ${phaseLabel(goal.phase)}`, + ...blocker, `Objective: ${goal.objective}`, `Rounds: ${goal.roundsStarted}/${goal.maxGoalRounds}`, `Activation: ${goal.activation}`, @@ -159,7 +159,7 @@ function executeGoalCommand(ctx: Context, invocation: CommandInvocation): Comman } } -/** Register the Codex-shaped `/goal` human command on TUI and ACP surfaces. */ +/** Register the Codex-shaped `/goal` command for every composed command adapter. */ export function apply(ctx: Context): void { ctx.commands.register({ name: 'goal', diff --git a/packages/goal/command-goal/tests/command-goal.spec.ts b/packages/goal/command-goal/tests/command-goal.spec.ts index a3d48857c4..71b1c59052 100644 --- a/packages/goal/command-goal/tests/command-goal.spec.ts +++ b/packages/goal/command-goal/tests/command-goal.spec.ts @@ -74,7 +74,6 @@ async function harness(): Promise { async function run(test: Harness, suffix = ''): Promise>>> { const result = await test.ctx.commands.execute( test.agent, - 'tui', `/goal${suffix}`, new AbortController().signal, ) @@ -87,20 +86,8 @@ function ref(goal: NonNullable>): GoalRef { return { id: goal.id, revision: goal.revision } } -/** Append one admitted goal round for budget-limited presentation coverage. */ -function appendRound(test: Harness, goal: NonNullable>): void { - const source = { kind: 'goal', goalId: goal.id, revision: goal.revision, round: 1 } as const - const turn = nextTurn(test.session) - test.session.append('turn/start', { turn, trigger: { kind: 'message', source } }) - test.session.append('user/message', { - content: [{ type: 'text', text: 'goal round' }], - source, - }, { surfaceOp: 'append' }) - test.session.append('turn/end', { turn, reason: { kind: 'completed' } }) -} - describe('@deepseek-ai/dsh-command-goal registration', () => { - it('registers one global TUI/ACP command with Loader-safe exports and disposes it', async () => { + it('registers one global command with Loader-safe exports and disposes it', async () => { const test = await harness() expect(commandGoal.name).toBe('command-goal') expect(commandGoal.inject).toEqual(['commands', 'goals']) @@ -108,16 +95,15 @@ describe('@deepseek-ai/dsh-command-goal registration', () => { const loader = Object.create(Loader.prototype) as Loader expect(loader.unwrapExports(commandGoal)).toBe(commandGoal) - expect(test.ctx.commands.list(test.agent, 'tui')).toContainEqual({ + expect(test.ctx.commands.list(test.agent)).toContainEqual({ name: 'goal', description: 'set or view the goal for a long-running task', input: { hint: '[|clear|edit |pause|resume]' }, - surfaces: ['tui', 'acp'], }) - expect(test.ctx.commands.find(test.agent, 'acp', 'goal')).toBeDefined() + expect(test.ctx.commands.find(test.agent, 'goal')).toBeDefined() await test.plugin.dispose() - expect(test.ctx.commands.find(test.agent, 'tui', 'goal')).toBeUndefined() + expect(test.ctx.commands.find(test.agent, 'goal')).toBeUndefined() }) }) @@ -227,22 +213,16 @@ describe('/goal human command', () => { expect((await run(test)).text).toContain('Status: paused') goal = test.ctx.goals.resume(test.agent, ref(goal)) - goal = test.ctx.goals.block(test.agent, ref(goal)) - expect((await run(test)).text).toContain('Status: blocked') + goal = test.ctx.goals.block(test.agent, ref(goal), { + code: 'upstream-unavailable', + message: 'Provider unavailable', + }) + const blocked = await run(test) + expect(blocked.text).toContain('Status: blocked') + expect(blocked.text).toContain('Blocker: upstream-unavailable: Provider unavailable') goal = test.ctx.goals.resume(test.agent, ref(goal)) - goal = test.ctx.goals.markUsageLimited(test.agent, ref(goal)) - expect((await run(test)).text).toContain('Status: usage limited') - - goal = test.ctx.goals.resume(test.agent, ref(goal)) - appendRound(test, goal) - goal = test.ctx.goals.get(test.agent)! - goal = test.ctx.goals.markBudgetLimited(test.agent, ref(goal)) - const limited = await run(test) - expect(limited.text).toContain('Status: limited by round budget') - expect(limited.text).toContain('after the agent raises the round cap, /goal resume') - - goal = test.ctx.goals.complete(test.agent, ref(goal)) + test.ctx.goals.complete(test.agent, ref(goal)) const complete = await run(test) expect(complete.text).toContain('Status: complete') expect(complete.text).toContain('Commands: /goal , /goal clear') From 283c78eec88c3d1e3720c9f2c19dd5de04bf5549 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 20 Jul 2026 18:06:34 +0800 Subject: [PATCH 5/5] test(goal): refresh shipped ACP goal snapshots --- examples/acp-agent/goal.cordis.snapshot.yml | 19 ------------------- examples/acp-agent/goal.cordis.yml | 13 ------------- .../goal-session/stdout.expected.jsonl | 2 +- examples/acp-agent/tests/goal.snapshot.ts | 2 +- .../system-prompt.expected.md | 8 +++++--- .../tool-schemas.expected.json | 8 ++++++-- .../both-mode-turn/system-prompt.expected.md | 8 +++++--- .../both-mode-turn/tool-schemas.expected.json | 8 ++++++-- .../code-mode-turn/system-prompt.expected.md | 8 +++++--- .../system-prompt.expected.md | 8 +++++--- .../model-switching/system-prompt.expected.md | 4 ++-- .../tool-schemas.expected.json | 16 ++++++++++++---- .../system-prompt.expected.md | 4 ++-- .../tool-schemas.expected.json | 16 ++++++++++++---- .../skill-load/system-prompt.expected.md | 2 +- .../skill-load/tool-schemas.expected.json | 8 ++++++-- .../text-turn/system-prompt.expected.md | 2 +- .../text-turn/tool-schemas.expected.json | 8 ++++++-- .../system-prompt.expected.md | 2 +- .../tool-schemas.expected.json | 8 ++++++-- .../workspace-edit/system-prompt.expected.md | 2 +- .../workspace-edit/tool-schemas.expected.json | 8 ++++++-- 22 files changed, 90 insertions(+), 74 deletions(-) delete mode 100644 examples/acp-agent/goal.cordis.snapshot.yml delete mode 100644 examples/acp-agent/goal.cordis.yml diff --git a/examples/acp-agent/goal.cordis.snapshot.yml b/examples/acp-agent/goal.cordis.snapshot.yml deleted file mode 100644 index 89e1078117..0000000000 --- a/examples/acp-agent/goal.cordis.snapshot.yml +++ /dev/null @@ -1,19 +0,0 @@ -# Replay counterpart to goal.cordis.yml; only the live model is replaced. -- id: base - name: '@cordisjs/plugin-include' - config: - path: ./goal.cordis.yml - patches: - - id: llm-deepseek - name: '@deepseek-ai/dsh-llm-deepseek' - disabled: true - - insert: - - id: llm-replay - name: '@deepseek-ai/dsh-llm-replay' - config: - providers: - - id: deepseek - name: DeepSeek - models: - - id: deepseek-v4-flash - - id: deepseek-v4-pro diff --git a/examples/acp-agent/goal.cordis.yml b/examples/acp-agent/goal.cordis.yml deleted file mode 100644 index d077104bb8..0000000000 --- a/examples/acp-agent/goal.cordis.yml +++ /dev/null @@ -1,13 +0,0 @@ -# Add the persisted same-session goal stack to the shipped ACP app. -- id: base - name: '@cordisjs/plugin-include' - config: - path: ./cordis.yml - patches: - - insert: - - id: goal - name: '@deepseek-ai/dsh-goal' - - id: tool-goal - name: '@deepseek-ai/dsh-tool-goal' - - id: goal-session - name: '@deepseek-ai/dsh-goal-session' diff --git a/examples/acp-agent/tests/goal-snapshots/goal-session/stdout.expected.jsonl b/examples/acp-agent/tests/goal-snapshots/goal-session/stdout.expected.jsonl index 61602dc289..40f60aa7fa 100644 --- a/examples/acp-agent/tests/goal-snapshots/goal-session/stdout.expected.jsonl +++ b/examples/acp-agent/tests/goal-snapshots/goal-session/stdout.expected.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_goal_create","title":"Create goal","kind":"other","status":"in_progress","rawInput":"Finish the ACP goal-session snapshot proof"}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_goal_create","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":2},\"activation\":\"armed\"}"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_goal_get","title":"Read current goal","kind":"read","status":"in_progress"}}} diff --git a/examples/acp-agent/tests/goal.snapshot.ts b/examples/acp-agent/tests/goal.snapshot.ts index 42e3041721..4bb01acd16 100644 --- a/examples/acp-agent/tests/goal.snapshot.ts +++ b/examples/acp-agent/tests/goal.snapshot.ts @@ -25,7 +25,7 @@ const refreshing = process.env.DSH_SNAPSHOT === 'refresh' const agent: AgentUnderTest = { binScript: fileURLToPath(new URL('../../../packages/examples/acp-demo/src/bin.ts', import.meta.url)), - configPath: fileURLToPath(new URL('../goal.cordis.yml', import.meta.url)), + configPath: fileURLToPath(new URL('../cordis.yml', import.meta.url)), tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)), } diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md index e130790bdf..acdebe8036 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md @@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). @@ -70,7 +70,7 @@ declare const tools: { /** Optional positive safe-integer limit on automatic continuation rounds. */ max_goal_rounds?: number; }): Promise; - /** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal. */ + /** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal. */ get_goal(args: Record): Promise; /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */ skill(args: { @@ -123,7 +123,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds. */ + /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */ update_goal(args: { /** Exact id returned by get_goal. */ goal_id: string; @@ -135,6 +135,8 @@ declare const tools: { objective?: string; /** Replacement cap; valid only with action edit. */ max_goal_rounds?: number; + /** Concrete blocking condition; required only with action blocked. */ + blocked_reason?: string; }): Promise; /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ workflow(args: { diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json index 55c1398f81..3a4f7ab7d8 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json @@ -124,7 +124,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -304,7 +304,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -334,6 +334,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md index 70de361b1d..271ac5e557 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md @@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). @@ -53,7 +53,7 @@ declare const tools: { /** Optional positive safe-integer limit on automatic continuation rounds. */ max_goal_rounds?: number; }): Promise; - /** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal. */ + /** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal. */ get_goal(args: Record): Promise; /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */ skill(args: { @@ -106,7 +106,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds. */ + /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */ update_goal(args: { /** Exact id returned by get_goal. */ goal_id: string; @@ -118,6 +118,8 @@ declare const tools: { objective?: string; /** Replacement cap; valid only with action edit. */ max_goal_rounds?: number; + /** Concrete blocking condition; required only with action blocked. */ + blocked_reason?: string; }): Promise; /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ workflow(args: { diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json index 50d08b7946..e8a4d432ff 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json @@ -67,7 +67,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -247,7 +247,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -277,6 +277,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md index 70de361b1d..271ac5e557 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md @@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). @@ -53,7 +53,7 @@ declare const tools: { /** Optional positive safe-integer limit on automatic continuation rounds. */ max_goal_rounds?: number; }): Promise; - /** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal. */ + /** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal. */ get_goal(args: Record): Promise; /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */ skill(args: { @@ -106,7 +106,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds. */ + /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */ update_goal(args: { /** Exact id returned by get_goal. */ goal_id: string; @@ -118,6 +118,8 @@ declare const tools: { objective?: string; /** Replacement cap; valid only with action edit. */ max_goal_rounds?: number; + /** Concrete blocking condition; required only with action blocked. */ + blocked_reason?: string; }): Promise; /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ workflow(args: { diff --git a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md index c3fefc8b86..7b64ad8b0d 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md @@ -15,7 +15,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). @@ -70,7 +70,7 @@ declare const tools: { /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */ replace_all?: boolean; }): Promise; - /** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal. */ + /** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal. */ get_goal(args: Record): Promise; /** Read a UTF-8 text file and return line-numbered content. */ read(args: { @@ -132,7 +132,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds. */ + /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */ update_goal(args: { /** Exact id returned by get_goal. */ goal_id: string; @@ -144,6 +144,8 @@ declare const tools: { objective?: string; /** Replacement cap; valid only with action edit. */ max_goal_rounds?: number; + /** Concrete blocking condition; required only with action blocked. */ + blocked_reason?: string; }): Promise; /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ workflow(args: { diff --git a/examples/acp-agent/tests/snapshots/model-switching/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/model-switching/system-prompt.expected.md index f81876701a..abcd608b39 100644 --- a/examples/acp-agent/tests/snapshots/model-switching/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/model-switching/system-prompt.expected.md @@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). @@ -29,7 +29,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/model-switching/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/model-switching/tool-schemas.expected.json index 113459eb86..a4c5307864 100644 --- a/examples/acp-agent/tests/snapshots/model-switching/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/model-switching/tool-schemas.expected.json @@ -67,7 +67,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -231,7 +231,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -261,6 +261,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ @@ -411,7 +415,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -575,7 +579,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -605,6 +609,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ diff --git a/examples/acp-agent/tests/snapshots/permission-switching/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/permission-switching/system-prompt.expected.md index 82335a7f1e..04d1fbe817 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/permission-switching/system-prompt.expected.md @@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. @@ -28,7 +28,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.expected.json index 113459eb86..a4c5307864 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.expected.json @@ -67,7 +67,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -231,7 +231,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -261,6 +261,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ @@ -411,7 +415,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -575,7 +579,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -605,6 +609,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ diff --git a/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md index 87818d5b6d..4cd64a91f8 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md @@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json index 0d8966ec14..21542887b1 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json @@ -67,7 +67,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -231,7 +231,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -261,6 +261,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ diff --git a/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md index 87818d5b6d..4cd64a91f8 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md @@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json index 0d8966ec14..21542887b1 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json @@ -67,7 +67,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -231,7 +231,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -261,6 +261,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ diff --git a/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md index 6f49fcf1c2..dd965e4933 100644 --- a/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md @@ -15,7 +15,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json index ab8c4a3d20..322ac0eb8d 100644 --- a/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json @@ -97,7 +97,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -285,7 +285,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -315,6 +315,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [ diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.expected.md index 4af39f6b4b..5879f004af 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.expected.md @@ -15,7 +15,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering. -Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked. +Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.expected.json index ab8c4a3d20..322ac0eb8d 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.expected.json @@ -97,7 +97,7 @@ }, { "name": "get_goal", - "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", "parameters": { "type": "object", "properties": {} @@ -285,7 +285,7 @@ }, { "name": "update_goal", - "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", "parameters": { "type": "object", "properties": { @@ -315,6 +315,10 @@ "max_goal_rounds": { "type": "number", "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." } }, "required": [