kevin/deepseek-harness
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/master' into worktree/web-multimodal-image-input

Browse Source 
# Conflicts:
#	docs/architecture.i18n.yaml
#	docs/architecture.md
#	docs/architecture.zh.md
#	docs/config-catalog.md
#	docs/core-data-structures/core.i18n.yaml
#	docs/core-data-structures/llm-streaming.i18n.yaml
#	docs/module-graph.md
#	examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl
#	packages/README.i18n.yaml
#	packages/client/connection/src/client/fixture.ts
#	packages/client/connection/src/index.ts
#	packages/client/runtime/README.i18n.yaml
#	packages/client/runtime/README.md
#	packages/client/runtime/README.zh.md
#	packages/client/runtime/src/client/sessions/conversation.ts
#	packages/client/ui-conversation/README.i18n.yaml
#	packages/client/ui-conversation/src/client/apply.ts
#	packages/client/ui-conversation/src/client/chat/ChatView.tsx
#	packages/client/ui-conversation/src/client/chat/MessageItem.tsx
#	packages/client/ui-conversation/src/client/contract/slots.ts
#	packages/client/ui-trajectory/tests/views.spec.tsx
#	packages/compact/compact-basic/README.i18n.yaml
#	packages/cordis/tool-cordis/src/api-catalog.ts
#	packages/host/apiproxy/src/api-proxy.ts
#	packages/host/apiproxy/src/api/index.ts
#	packages/host/apiproxy/src/api/sessions.ts
#	packages/host/apiproxy/src/index.ts
#	packages/host/apiproxy/tests/fetch-carrier.spec.ts
#	packages/llm/llm-deepseek/src/adapter.ts
#	packages/llm/llm-deepseek/tests/adapter.spec.ts
#	packages/llm/llm-deepseek/tests/serialize.spec.ts
#	packages/llm/llm-pi-ai/README.i18n.yaml
#	packages/llm/llm-pi-ai/src/adapter.ts
#	packages/llm/llm-pi-ai/src/index.ts
#	packages/llm/llm-pi-ai/tests/adapter.spec.ts
#	packages/llm/llm/src/types.ts
#	packages/ui/tui/README.i18n.yaml
#	packages/ui/tui/src/index.ts
#	packages/ui/tui/tests/tui.spec.ts
This commit is contained in:
Yichen Jiang
2026-07-28 11:41:40 +08:00
parent a1835c3228 2a46685414
commit 004f598917
1499 changed files with 48621 additions and 21956 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/README.i18n.yaml
+3 -3
View File
@@ -1,6 +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
README.md: 8fd261e624771dc568582b6d22e9985072a06715
README.zh.md: 2ff0d0bef382435588fce01c23aa7b74e1a149b5
# pnpm run verify-translation-pairing --write examples/README.md
README.md: 7f12178d1b67f1ebfac6f4f0e31403c54106e98f
README.zh.md: 72ab92602d0a53cabdbfa8bc34838061df25d1c7
examples/README.md
+2 -2
View File
@@ -22,9 +22,9 @@ An unattended coding agent driven through the Python SDK: JSON-RPC stdio, foregr
## cordis-agent
The **self-referential** demo: the coding spine plus [`@deepseek-ai/dsh-tool-cordis`](../packages/cordis/tool-cordis), whose three tools (`cordis_inspect` / `cordis_mount` / `cordis_unmount`) let the agent inspect the live cordis runtime it runs inside, mount model-written plugins into it (an event listener, a brand-new tool for itself, or a service another mount injects), and dispose them again — all dynamic mounts grouped under one `cordis-dynamic` fiber subtree. The `ctx.fs`/`ctx.web` services ride along provider-only, as the capabilities those plugins build on.
The **self-referential** demo: the coding spine plus [`@deepseek-ai/dsh-tool-cordis`](../packages/cordis/tool-cordis), whose three tools (`cordis_inspect` / `cordis_mount` / `cordis_unmount`) let the agent inspect the current DSH process, mount model-written temporary Plugins (an event listener, a brand-new tool, or a service another temporary Plugin injects), and unmount them again. These Plugins exist only in memory and share one internal `cordis-dynamic` fiber subtree; `ctx.fs`/`ctx.web` ride along provider-only as capabilities they can use.
Run with: `pnpm run demo:cordis` (needs `DEEPSEEK_API_KEY`). See [cordis-agent/README.md](cordis-agent/README.md) for the staged demo script and [the toolset Agent Note](../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md) for the design and sandbox caveats.
Run the TUI with `pnpm run demo:cordis`, the browser UI at `http://127.0.0.1:3081` with `pnpm run demo:cordis web`, or the ACP server with `pnpm run demo:cordis acp` (all need `DEEPSEEK_API_KEY`). See [cordis-agent/README.md](cordis-agent/README.md) for the staged demo script and [the toolset Agent Note](../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md) for the design and sandbox caveats.
## acp-agent
examples/README.zh.md
+2 -2
View File
@@ -22,9 +22,9 @@
## cordis-agent
**自指** 演示：编码主干加 [`@deepseek-ai/dsh-tool-cordis`](../packages/cordis/tool-cordis)，其三个工具（`cordis_inspect`/`cordis_mount`/`cordis_unmount`）使 agent 可以检查自身所在的实时 cordis 运行时，将模型编写的插件挂载到其中（事件监听器、一个专为自身创建的全新工具，或一个供另一挂载项注入的服务），并再次释放它们。所有动态挂载都归入同一 `cordis-dynamic` fiber 子树。`ctx.fs`/`ctx.web` 服务仅作为提供方随行，是这些插件构建所依赖的能力。
**自指** 演示：编码主干加 [`@deepseek-ai/dsh-tool-cordis`](../packages/cordis/tool-cordis)，其三个工具（`cordis_inspect`/`cordis_mount`/`cordis_unmount`）使 agent 可以检查当前 DSH 进程、挂载模型编写的临时 Plugin（事件监听器、一个全新工具，或一个供另一临时 Plugin 注入的服务），并再次卸载它们。这些 Plugin 只存在于内存中，共享一个内部 `cordis-dynamic` fiber 子树；`ctx.fs`/`ctx.web` 仅作为它们可用的能力提供方。
运行：`pnpm run demo:cordis`（需要 `DEEPSEEK_API_KEY`）。分阶段演示脚本详见 [cordis-agent/README.md](cordis-agent/README.md)，设计与沙箱注意事项详见[工具集 Agent Note](../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)。
使用 `pnpm run demo:cordis` 运行 TUI，使用 `pnpm run demo:cordis web` 在 `http://127.0.0.1:3081` 启动浏览器 UI，或使用 `pnpm run demo:cordis acp` 启动 ACP 服务器（三者均需 `DEEPSEEK_API_KEY`）。分阶段演示脚本详见 [cordis-agent/README.md](cordis-agent/README.md)，设计与沙箱注意事项详见[工具集 Agent Note](../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)。
## acp-agent
examples/acp-agent/README.i18n.yaml
+2 -2
View File
@@ -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
README.md: 4b3d86b00613cc7c37a8898ef3b39d40a167e66b
README.zh.md: 5bcd85f2b4ae34a11b980bf196d3401f764004d8
README.md: 0d63ec1f2d9165b9faf0817bd94fbe15b97fa961
README.zh.md: 0c5f8866ea640843513fd9a4c15a17ed4db59d3b
examples/acp-agent/README.md
+1 -1
View File
@@ -9,7 +9,7 @@ pnpm run demo:acp # needs DEEPSEEK_API_KEY (repo-root .env or env)
pnpm run demo:code-mode acp # same protocol with the Code Mode tool transport
```
The leaf loads the ACP app, DeepSeek adapter, sandboxed bash and filesystem stacks, one-shot approval policy, compaction, subagents, workflows, hooks, a derived session-query index, and repeat guard. The app creates one fresh agent per `session/new`, persists sessions to JSONL, and keeps stdout protocol-pure. [`session-query.cordis.yml`](session-query.cordis.yml) explicitly opts into the workspace-authorized query tools and generic timeout/spill policies for their dedicated snapshot; [`fs.cordis.yml`](fs.cordis.yml) adds spill storage for filesystem scenarios, while [`code-mode.cordis.yml`](code-mode.cordis.yml) adds `run_code` and its generated TypeScript SDK.
The leaf loads the ACP app, DeepSeek adapter, sandboxed bash and filesystem stacks, one-shot approval policy, compaction, subagents, workflows, hooks, a derived session-query index, and repeat guard. The app creates one fresh agent per `session/new`, persists sessions to JSONL, and keeps stdout protocol-pure. [`session-query.cordis.yml`](session-query.cordis.yml) explicitly opts into the workspace-authorized query tools and generic timeout/spill policies for their dedicated snapshot; [`fs.cordis.yml`](fs.cordis.yml) adds spill storage for filesystem scenarios, [`code-mode.cordis.yml`](code-mode.cordis.yml) adds `run_code` and its generated TypeScript SDK, and [`web.cordis.yml`](web.cordis.yml) adds the web seam, the local fetch provider, `web_fetch`, and a loopback HTML fixture server for the web-fetch snapshot.
## Protocol channel
examples/acp-agent/README.zh.md
+1 -1
View File
@@ -9,7 +9,7 @@ pnpm run demo:acp # needs DEEPSEEK_API_KEY (repo-root .env or env)
pnpm run demo:code-mode acp # same protocol with the Code Mode tool transport
```
该叶节点加载 ACP 应用、DeepSeek 适配器、受沙箱限制的 bash 与文件系统栈、一次性批准策略、压缩（compaction）、subagent、工作流、钩子、派生会话查询索引和重复守卫。应用为每次 `session/new` 创建一个新 agent，将会话持久化到 JSONL，并保持 stdout 只含协议内容。[`session-query.cordis.yml`](session-query.cordis.yml) 为其专用快照显式选用 workspace 授权的查询工具和通用超时／溢出策略；[`fs.cordis.yml`](fs.cordis.yml) 为文件系统场景添加溢出存储，[`code-mode.cordis.yml`](code-mode.cordis.yml) 则添加 `run_code` 及其生成的 TypeScript SDK。
该叶节点加载 ACP 应用、DeepSeek 适配器、受沙箱限制的 bash 与文件系统栈、一次性批准策略、压缩（compaction）、subagent、工作流、钩子、派生会话查询索引和重复守卫。应用为每次 `session/new` 创建一个新 agent，将会话持久化到 JSONL，并保持 stdout 只含协议内容。[`session-query.cordis.yml`](session-query.cordis.yml) 为其专用快照显式选用 workspace 授权的查询工具和通用超时／溢出策略；[`fs.cordis.yml`](fs.cordis.yml) 为文件系统场景添加溢出存储，[`code-mode.cordis.yml`](code-mode.cordis.yml) 添加 `run_code` 及其生成的 TypeScript SDK，[`web.cordis.yml`](web.cordis.yml) 则为 web-fetch 快照添加 web seam、本地抓取提供方、`web_fetch` 与一个回环 HTML fixture 服务器。
## 协议通道
examples/acp-agent/composition.md
+3
View File
@@ -14,6 +14,8 @@ flowchart LR
cfg --> plugin_acp_sandbox
plugin_acp_sandbox_policy["sandbox-policy<br/>@deepseek-ai/dsh-sandbox-policy"]
cfg --> plugin_acp_sandbox_policy
plugin_acp_subprocess["subprocess<br/>@deepseek-ai/dsh-subprocess-local"]
cfg --> plugin_acp_subprocess
plugin_acp_bash["bash<br/>@deepseek-ai/dsh-bash-sandbox"]
cfg --> plugin_acp_bash
plugin_acp_approval["approval<br/>@deepseek-ai/dsh-user-approval"]
@@ -68,6 +70,7 @@ flowchart LR
| `llm-deepseek` | `@deepseek-ai/dsh-llm-deepseek` |
| `sandbox` | `@deepseek-ai/dsh-sandbox-local` |
| `sandbox-policy` | `@deepseek-ai/dsh-sandbox-policy` |
| `subprocess` | `@deepseek-ai/dsh-subprocess-local` |
| `bash` | `@deepseek-ai/dsh-bash-sandbox` |
| `approval` | `@deepseek-ai/dsh-user-approval` |
| `acp-agent` | `@deepseek-ai/dsh-acp-demo` |
examples/acp-agent/cordis-tools.cordis.yml
+10
View File
@@ -0,0 +1,10 @@
# Add the self-referential Cordis tools without changing the base ACP tool
# presentation mode.
- id: base
name: '@cordisjs/plugin-include'
config:
path: ./cordis.yml
patches:
- insert:
- id: tool-cordis
name: '@deepseek-ai/dsh-tool-cordis'
examples/acp-agent/cordis.yml
+4
View File
@@ -33,6 +33,10 @@
mode: !!js "process.env.DSH_PERMISSION_MODE ?? (process.env.DSH_SNAPSHOT === undefined ? 'workspace-write' : 'danger-full-access')"
workspaceRoot: !!js process.cwd()
# Managed child-process groups for the bash executor (spawn/kill/output plumbing).
- id: subprocess
name: '@deepseek-ai/dsh-subprocess-local'
- id: bash
name: '@deepseek-ai/dsh-bash-sandbox'
config:
examples/acp-agent/pty.cordis.yml
+1
View File
@@ -14,6 +14,7 @@
pollIntervalMs: 10
exactProbeAfterMs: 20
idleSilenceMs: 250
handoffGraceMs: 250
timeoutMs: 2000
disposeGraceMs: 500
- id: tool-pty
examples/acp-agent/retry.cordis.snapshot.yml
+10 -9
View File
@@ -1,8 +1,7 @@
# Keyless replay for the retry overlay: disable the key-requiring DeepSeek
# adapter, insert `llm-replay`, and restate the app config with the same
# deterministic 1 ms zero-jitter retry policy as the live sibling. A config
# patch replaces the whole app config, so the base fields are restated
# verbatim (raw JSONL persistence so the harness can harvest the log).
# adapter, insert `llm-replay`, and give its provider the same deterministic
# 1 ms zero-jitter retry policy as the live sibling. The app patch still
# restates its whole config for raw JSONL persistence and the recorded model.
- id: base
name: '@cordisjs/plugin-include'
config:
@@ -20,11 +19,6 @@
persistenceCompression: none
workspaceContext:
maxBytes: 65536
llmRetry:
maxTransientRetries: 2
initialDelayMs: 1
maxDelayMs: 1
jitterRatio: 0
persona: |
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug.
@@ -36,6 +30,13 @@
providers:
- id: deepseek
name: DeepSeek
retryPolicy:
mode: normal
maxRetries: 2
backoff:
initialDelayMs: 1
maxDelayMs: 1
jitterRatio: 0
models:
- id: deepseek-v4-flash
- id: deepseek-v4-pro
examples/acp-agent/retry.cordis.yml
+21 -8
View File
@@ -2,14 +2,32 @@
# deterministic 1 ms zero-jitter delay so the durable `llm/retry` event
# (`delayMs`) and replay wall time stay reproducible. The overlay changes no
# tool or prompt composition, so its scenarios share the default header class.
# A config patch replaces the whole app config, so the base fields are restated
# verbatim; the model is re-pinned to `deepseek-v4-flash` like the other
# snapshot overlays because the recorded corpus was captured on flash.
# Config patches replace whole plugin configs: the provider patch restates its
# adapter fields around `retryPolicy`, while the app patch re-pins the recorded
# flash model and restates its base fields.
- id: base
name: '@cordisjs/plugin-include'
config:
path: ./cordis.yml
patches:
- id: llm-deepseek
name: '@deepseek-ai/dsh-llm-deepseek'
config:
apiKey: !!js process.env.DEEPSEEK_API_KEY
baseURL: !!js process.env.DEEPSEEK_BASE_URL
thinking: enabled
reasoningEffort: max
defaultContextWindow: 256000
retryPolicy:
mode: normal
maxRetries: 2
backoff:
initialDelayMs: 1
maxDelayMs: 1
jitterRatio: 0
models:
- id: deepseek-v4-flash
- id: deepseek-v4-pro
- id: acp-agent
name: '@deepseek-ai/dsh-acp-demo'
config:
@@ -19,11 +37,6 @@
persistenceCompression: !!js "process.env.DSH_SNAPSHOT === undefined ? 'zstd' : 'none'"
workspaceContext:
maxBytes: 65536
llmRetry:
maxTransientRetries: 2
initialDelayMs: 1
maxDelayMs: 1
jitterRatio: 0
persona: |
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug.
examples/acp-agent/tests/acp.snapshot.ts
+14 -7
View File
@@ -40,6 +40,7 @@ const DEPTH_TWO_CONFIG = fileURLToPath(new URL('../depth-two.cordis.yml', import
const SESSION_SANDBOX_ROOT_CONFIG = fileURLToPath(new URL('../session-sandbox-root.cordis.yml', import.meta.url))
const RETRY_CONFIG = fileURLToPath(new URL('../retry.cordis.yml', import.meta.url))
const LSP_CONFIG = fileURLToPath(new URL('./lsp.cordis.yml', import.meta.url))
const WEB_CONFIG = fileURLToPath(new URL('../web.cordis.yml', import.meta.url))
const SNAPSHOTS_DIR = join(dirname(fileURLToPath(import.meta.url)), 'snapshots')
const PACKED_CHUNKS_SOURCE = 'hook-cc-pretool-deny'
@@ -109,6 +110,12 @@ const SCENARIOS: Scenario[] = [
{ name: 'todo-write', hasModelTurn: true, recorded: true },
{ name: 'skill-load', hasModelTurn: true, recorded: false, pinsHeader: true, headerClass: 'skill' },
{ name: 'lsp-definition', hasModelTurn: true, recorded: false, pinsHeader: true, headerClass: 'lsp', configPath: LSP_CONFIG },
// web_fetch markdown rendering end to end: the overlay's loopback fixture
// server supplies deterministic HTML (entities, a GFM table, nesting), the
// REAL local fetch provider retrieves it, and the tool result pins the
// turndown conversion. The fetched URL (fixed port) is part of the recorded
// transcript; replay re-executes the real fetch against the same fixture.
{ name: 'web-fetch', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'web', configPath: WEB_CONFIG },
{
name: 'workspace-edit',
hasModelTurn: true,
@@ -124,10 +131,10 @@ const SCENARIOS: Scenario[] = [
{ name: 'error-finish', hasModelTurn: true, recorded: false, overridden: true },
// Keyless, authored (like error-finish): a live provider cannot be coaxed
// into a degenerate empty completion, so the fixture scripts the adapters'
// EMPTY_RESPONSE error finish (step 1) followed by the recovered reply
// (step 2), proving the default retry policy end to end: the durable
// EMPTY_RESPONSE error finish in turn 1 followed by the recovered reply
// in retry turn 2, proving the default retry policy end to end: the durable
// llm/retry event, no ACP output for the discarded attempt, the recovered
// reply, and a clean completed turn. Its overlay only pins a deterministic
// reply, and a clean completed retry turn. Its overlay only pins a deterministic
// 1 ms zero-jitter delay, so it shares the default header class.
{ name: 'empty-response-retry', hasModelTurn: true, recorded: false, configPath: RETRY_CONFIG },
// Keyless, authored (like error-finish/cancel): deterministically forcing a
@@ -188,10 +195,10 @@ const SCENARIOS: Scenario[] = [
headerClass: 'advanced',
configPath: ADVANCED_CONFIG,
},
// Prompt-submit blocks are authored keylessly: they persist a rejected turn
// and hook events without starting a model step, so their logs still compare.
{ name: 'hook-cc-promptsubmit-block', hasModelTurn: false, comparesLog: true, recorded: false },
{ name: 'hook-codex-promptsubmit-block', hasModelTurn: false, comparesLog: true, recorded: false },
// Prompt-submit blocks are authored keylessly. Admission rejects before a
// turn opens, so only the ACP stop reason is observable and no log is harvested.
{ name: 'hook-cc-promptsubmit-block', hasModelTurn: false, recorded: false },
{ name: 'hook-codex-promptsubmit-block', hasModelTurn: false, recorded: false },
// The mid-turn seams fire during a real model turn, so each is recorded with its hook active
// (the model's reaction to a deny/block/force-continue is part of the captured transcript).
// SessionStart/SubagentStart are excluded because detached injection races log
examples/acp-agent/tests/fixtures/subagent/subagent-acp/cordis.yml
Vendored
+4
View File
@@ -10,6 +10,10 @@
- id: subagent
name: '@deepseek-ai/dsh-subagent'
# The out-of-process ACP backend spawns its child through the subprocess seam.
- id: subprocess
name: '@deepseek-ai/dsh-subprocess-local'
- id: subagent-acp
name: '@deepseek-ai/dsh-subagent-acp'
config:
examples/acp-agent/tests/goal-snapshots/goal-session/input.json
+2 -1
View File
@@ -8,6 +8,7 @@
"waitForText": "GOAL ROUND ONE"
},
{ "op": "waitForTurnStart", "minimumTurn": 3 },
{ "op": "cancel", "waitForFile": { "path": ".dsh-snapshot-goal-cancel-ready" } }
{ "op": "cancel", "waitForFile": { "path": ".dsh-snapshot-goal-cancel-ready" } },
{ "op": "waitForTurnEnd" }
]
}
examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl
+4 -4
View File
@@ -12,7 +12,7 @@
{"type":"assistant/message","seq":10,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}
{"type":"tool/call","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}}
{"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","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\"}"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"}
{"type":"user/message","seq":13,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":2},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0},"meta":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the ACP goal-session snapshot proof","phase":"active","maxGoalRounds":2},"roundsStarted":0,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"}
{"type":"user/message","seq":13,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":2},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0,"change":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the ACP goal-session snapshot proof","phase":"active","maxGoalRounds":2},"roundsStarted":0,"createdAt":0,"updatedAt":0}}},"surfaceOp":"append"}
{"type":"step/end","seq":14,"time":0,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":15,"time":0,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
@@ -49,6 +49,6 @@
{"type":"step/start","seq":47,"time":0,"data":{"turn":3,"step":1}}
{"type":"assistant/chunk","seq":48,"time":0,"data":{"turn":3,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":49,"time":0,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":0,"text":"partial"}}}
{"type":"user/message","seq":50,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":2,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"paused\",\"maxGoalRounds\":2},\"roundsStarted\":2,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":2,"round":0},"meta":{"kind":"goal/change","version":1,"operation":"pause","goal":{"id":"goal-{{sessionId}}","revision":2,"objective":"Finish the ACP goal-session snapshot proof","phase":"paused","maxGoalRounds":2},"roundsStarted":2,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"}
{"type":"step/end","seq":51,"time":0,"data":{"turn":3,"step":1}}
{"type":"turn/end","seq":52,"time":0,"data":{"turn":3,"reason":{"kind":"aborted"}}}
{"type":"step/end","seq":50,"time":0,"data":{"turn":3,"step":1}}
{"type":"turn/end","seq":51,"time":0,"data":{"turn":3,"reason":{"kind":"aborted"}}}
{"type":"user/message","seq":52,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":2,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"paused\",\"maxGoalRounds\":2},\"roundsStarted\":2,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":2,"round":0,"change":{"kind":"goal/change","version":1,"operation":"pause","goal":{"id":"goal-{{sessionId}}","revision":2,"objective":"Finish the ACP goal-session snapshot proof","phase":"paused","maxGoalRounds":2},"roundsStarted":2,"createdAt":0,"updatedAt":0}}},"surfaceOp":"append"}
examples/acp-agent/tests/snapshots/advanced-toolchain/input.json
+1 -1
View File
@@ -2,6 +2,6 @@
"steps": [
{ "op": "initialize" },
{ "op": "newSession" },
{ "op": "prompt", "text": "Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK." }
{ "op": "prompt", "text": "Run this advanced flow exactly once: try a no-op temporary Cordis Plugin named snapshot-marker; use run_code to inspect the live temporary Plugins through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; stop dyn-1; then reply with exactly ADVANCED_ACP_OK." }
]
}
examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl
+10 -10
View File
@@ -1,6 +1,6 @@
{"type":"session","version":0,"id":"11111111-1111-4111-8111-111111111111","createdAt":1783950000000,"cwd":"/tmp/advanced-acp","delegationDepth":0}
{"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
{"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: try a no-op temporary Cordis Plugin named snapshot-marker; use run_code to inspect the live temporary Plugins through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; stop dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"session/title","seq":2,"time":1783957884479,"data":{"title":"Run this advanced flow exactly","messageSeqs":[1],"source":{"kind":"fallback"}}}
{"type":"step/start","seq":3,"time":1783957884486,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":4,"time":1783957884486,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
@@ -11,19 +11,19 @@
{"type":"assistant/chunk","seq":9,"time":1783950000009,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":10,"time":1783957884487,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}
{"type":"tool/call","seq":11,"time":1783957884487,"data":{"turn":1,"step":1,"callId":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}
{"type":"tool/result","seq":12,"time":1783957884488,"data":{"turn":1,"step":1,"callId":"advanced-mount","content":[{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"}
{"type":"tool/result","seq":12,"time":1783957884488,"data":{"turn":1,"step":1,"callId":"advanced-mount","content":[{"type":"text","text":"Temporary Plugin dyn-1 is running (plugin \"snapshot-marker\"; available until unmounted or DSH restarts)."}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"}
{"type":"step/end","seq":13,"time":1783957884489,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":14,"time":1783957884489,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":15,"time":1783950000015,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":16,"time":1783950000016,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-code","name":"run_code","argumentsDelta":"{\"code\": \"return await tools.cordis_inspect({ what: 'dynamic' })\", \"description\": \"Run the scripted inspection program\"}"}}}
{"type":"assistant/chunk","seq":17,"time":1783950000017,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'dynamic' })\", \"description\": \"Run the scripted inspection program\"}"}}}}
{"type":"assistant/chunk","seq":16,"time":1783950000016,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-code","name":"run_code","argumentsDelta":"{\"code\": \"return await tools.cordis_inspect({ what: 'temporary' })\", \"description\": \"Run the scripted inspection program\"}"}}}
{"type":"assistant/chunk","seq":17,"time":1783950000017,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'temporary' })\", \"description\": \"Run the scripted inspection program\"}"}}}}
{"type":"assistant/chunk","seq":18,"time":1783950000018,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
{"type":"assistant/chunk","seq":19,"time":1783950000019,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":20,"time":1783957884490,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'dynamic' })\", \"description\": \"Run the scripted inspection program\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}
{"type":"tool/call","seq":21,"time":1783957884490,"data":{"turn":1,"step":2,"callId":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'dynamic' })\", \"description\": \"Run the scripted inspection program\"}"}}
{"type":"tool/code-dispatch-start","seq":22,"time":1785036891166,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"dynamic"}}}
{"type":"tool/code-dispatch","seq":23,"time":1785036891167,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"dynamic"},"isError":false,"content":[{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}]}}
{"type":"tool/result","seq":24,"time":1785036891170,"data":{"turn":1,"step":2,"callId":"advanced-code","content":[{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}],"isError":false},"sourceEventSeqs":[21],"surfaceOp":"append"}
{"type":"assistant/message","seq":20,"time":1783957884490,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'temporary' })\", \"description\": \"Run the scripted inspection program\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}
{"type":"tool/call","seq":21,"time":1783957884490,"data":{"turn":1,"step":2,"callId":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'temporary' })\", \"description\": \"Run the scripted inspection program\"}"}}
{"type":"tool/code-dispatch-start","seq":22,"time":1785036891166,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"temporary"}}}
{"type":"tool/code-dispatch","seq":23,"time":1785036891167,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"temporary"},"isError":false,"content":[{"type":"text","text":"## Temporary Plugins\n- Temporary Plugin dyn-1: snapshot-marker [running] — provides: none; waiting for: none; lifetime: until unmounted or DSH restarts"}]}}
{"type":"tool/result","seq":24,"time":1785036891170,"data":{"turn":1,"step":2,"callId":"advanced-code","content":[{"type":"text","text":"## Temporary Plugins\n- Temporary Plugin dyn-1: snapshot-marker [running] — provides: none; waiting for: none; lifetime: until unmounted or DSH restarts"}],"isError":false},"sourceEventSeqs":[21],"surfaceOp":"append"}
{"type":"step/end","seq":25,"time":1785036891171,"data":{"turn":1,"step":2}}
{"type":"step/start","seq":26,"time":1785036891175,"data":{"turn":1,"step":3}}
{"type":"assistant/chunk","seq":27,"time":1783950000027,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
@@ -53,7 +53,7 @@
{"type":"assistant/chunk","seq":51,"time":1785036891795,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":52,"time":1785036891796,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[47,48,49,50,51],"surfaceOp":"append"}
{"type":"tool/call","seq":53,"time":1785036891796,"data":{"turn":1,"step":5,"callId":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}
{"type":"tool/result","seq":54,"time":1785036891798,"data":{"turn":1,"step":5,"callId":"advanced-unmount","content":[{"type":"text","text":"unmounted dyn-1 (plugin \"snapshot-marker\")"}],"isError":false},"sourceEventSeqs":[53],"surfaceOp":"append"}
{"type":"tool/result","seq":54,"time":1785036891798,"data":{"turn":1,"step":5,"callId":"advanced-unmount","content":[{"type":"text","text":"Temporary Plugin dyn-1 was unmounted and removed."}],"isError":false},"sourceEventSeqs":[53],"surfaceOp":"append"}
{"type":"step/end","seq":55,"time":1785036891799,"data":{"turn":1,"step":5}}
{"type":"step/start","seq":56,"time":1785036891801,"data":{"turn":1,"step":6}}
{"type":"assistant/chunk","seq":57,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md
+7 -7
View File
@@ -56,21 +56,21 @@ interface ToolArgsMap {
/** Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access. */
justification?: string;
} & Record<string, JsonValue>;
/** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:"api"` or `what:"events"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */
/** Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:"api"` or `what:"events"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */
cordis_inspect: {
/** Limit the report to one section. Omit for all sections. */
what?: "services" | "plugins" | "tools" | "dynamic" | "api" | "events";
what?: "services" | "plugins" | "tools" | "temporary" | "api" | "events";
/** Exact service key or event name whose original JSDoc to include; valid only with what:"api" or what:"events". */
name?: string;
} & Record<string, JsonValue>;
/** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:"api" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:"events"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:"api" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */
/** Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement a normal local, project, or repository Plugin through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:"api" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:"events"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:"api" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */
cordis_mount: {
/** Body of an async JS function; must `return` the plugin to mount. */
/** JavaScript body returning a temporary Plugin; evaluated now and saved nowhere. */
code: string;
} & Record<string, JsonValue>;
/** Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop). */
/** Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins. */
cordis_unmount: {
/** The dynamic mount id returned by cordis_mount (e.g. "dyn-1"). */
/** The temporary Plugin id returned by cordis_mount (for example "dyn-1"); valid only in this process and invalid after unmount or restart. */
id: string;
} & Record<string, JsonValue>;
/** 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. */
@@ -162,7 +162,7 @@ interface ToolArgsMap {
content: string;
/** pending (not started) | in_progress (now) | completed (done). */
status: "pending" | "in_progress" | "completed";
} & Record<string, JsonValue>)[];
})[];
} & Record<string, JsonValue>;
/** 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: {
examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json
+7 -7
View File
@@ -47,7 +47,7 @@
},
{
"name": "cordis_inspect",
"description": "Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.",
"description": "Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.",
"parameters": {
"type": "object",
"properties": {
@@ -58,7 +58,7 @@
"services",
"plugins",
"tools",
"dynamic",
"temporary",
"api",
"events"
]
@@ -72,13 +72,13 @@
},
{
"name": "cordis_mount",
"description": "Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.",
"description": "Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement a normal local, project, or repository Plugin through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.",
"parameters": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "Body of an async JS function; must `return` the plugin to mount."
"description": "JavaScript body returning a temporary Plugin; evaluated now and saved nowhere."
}
},
"required": [
@@ -88,13 +88,13 @@
},
{
"name": "cordis_unmount",
"description": "Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).",
"description": "Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins.",
"parameters": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."
"description": "The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart."
}
},
"required": [
@@ -366,7 +366,7 @@
"description": "The COMPLETE task list, replacing any previous list.",
"items": {
"type": "object",
"additionalProperties": true,
"additionalProperties": false,
"properties": {
"content": {
"type": "string",
examples/acp-agent/tests/snapshots/bash-spill/session.jsonl
+1 -1
View File
@@ -11,7 +11,7 @@
{"type":"assistant/chunk","seq":9,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":10,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_spill","name":"bash","arguments":"{\"command\":\"node -e \\\"process.stdout.write('SPILL_START-' + 'x'.repeat(2000) + '-SPILL_END')\\\"\",\"description\":\"Print large deterministic output\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}
{"type":"tool/call","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_spill","name":"bash","arguments":"{\"command\":\"node -e \\\"process.stdout.write('SPILL_START-' + 'x'.repeat(2000) + '-SPILL_END')\\\"\",\"description\":\"Print large deterministic output\"}"}}
{"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"call_spill","content":[{"type":"text","text":"SPILL_START-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx-SPILL_END\n\n(Omitted 1417 bytes. Full formatted result stored at: /tmp/dsh-acp-snap-ee77dff02/session-5747fa727e10/57c2f8c3fbf2-bash.txt. Use read with offset/limit, or grep this path to search within it.)"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"}
{"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"call_spill","content":[{"type":"text","text":"SPILL_START-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx-SPILL_END\n\n(Omitted 1417 bytes. Full formatted result stored at: /tmp/dsh-acp-snap-ee77dff02/session-5e53dc8acfe4/2ce9d7a31a38-bash.txt. Use read with offset/limit, or grep this path to search within it.)"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"}
{"type":"step/end","seq":13,"time":0,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":14,"time":0,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md
+1 -1
View File
@@ -145,7 +145,7 @@ interface ToolArgsMap {
content: string;
/** pending (not started) | in_progress (now) | completed (done). */
status: "pending" | "in_progress" | "completed";
} & Record<string, JsonValue>)[];
})[];
} & Record<string, JsonValue>;
/** 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: {
examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json
+1 -1
View File
@@ -309,7 +309,7 @@
"description": "The COMPLETE task list, replacing any previous list.",
"items": {
"type": "object",
"additionalProperties": true,
"additionalProperties": false,
"properties": {
"content": {
"type": "string",
examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md
+1 -1
View File
@@ -145,7 +145,7 @@ interface ToolArgsMap {
content: string;
/** pending (not started) | in_progress (now) | completed (done). */
status: "pending" | "in_progress" | "completed";
} & Record<string, JsonValue>)[];
})[];
} & Record<string, JsonValue>;
/** 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: {
examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl
+30 -29
View File
@@ -2,32 +2,33 @@
{"type":"turn/start","seq":0,"time":1785014475014,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
{"type":"user/message","seq":1,"time":1785014475015,"data":{"content":[{"type":"text","text":"Using ONE run_code program, call tools.read on nested/task.txt. After the program finishes, answer the workspace handshake question using the newly discovered instructions: What is the Code Mode workspace handshake?"}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"session/title","seq":2,"time":1785014475022,"data":{"title":"Using ONE run_code program, call","messageSeqs":[1],"source":{"kind":"fallback"}}}
{"type":"step/start","seq":3,"time":1785014475034,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":4,"time":1785014475035,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":[{"role":"user","content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nWorkspace snapshot root instruction.\n\n</system-reminder>"}]}]},"reason":"initial"}}
{"type":"assistant/chunk","seq":5,"time":1785014475456,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"reasoning-chunks","seq0":6,"time0":1785014475457,"data":{"turn":1,"step":1,"index":0,"dt":[139,42,1,0,0,0,40,1,0,0,0,43,0,0,0,39,43,1,0,0,0,40,1,40,0,0,1,42,0,1,0,0,40,0,0,1,0,0,44,0,1,39,0,1,0],"texts":["The"," user"," wants"," me"," to"," read"," the"," file"," `","n","ested","/t","ask",".txt","`"," using"," a"," `","run","_code","`"," program",","," and"," then"," answer"," the"," question"," \"","What"," is"," the"," Code"," Mode"," workspace"," hand","shake","?\""," based"," on"," the"," contents"," of"," that"," file","."]}}
{"type":"assistant/chunk","seq":52,"time":1785014476183,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
{"type":"tool-call-chunks","seq0":53,"time0":1785014476183,"data":{"turn":1,"step":1,"index":1,"dt":[41,1,0,0,41,0,0,1,41,1,0,0,40,0,42,0,0,0,1,0,40,1,0,0,0,0,41,0,0,42,1,0,41,1,0,0,42,0,0,0,0,41],"id":"call_00_hD8d0VcXXFVMtn64GSoC9264","name":"run_code","args":["","{","\"","code","\"",": ","\"","\\n","const"," result"," ="," await"," tools",".read","({"," file","_path",":"," \\\"","n","ested","/t","ask",".txt","\\\""," });\\n","return"," result",";\\n","\"",", ","\"","description","\"",": ","\"","Read"," nested","/t","ask",".txt","\"","}"]}}
{"type":"assistant/chunk","seq":96,"time":1785014476731,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to read the file `nested/task.txt` using a `run_code` program, and then answer the question \"What is the Code Mode workspace handshake?\" based on the contents of that file."}}}}
{"type":"assistant/chunk","seq":97,"time":1785014476732,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_hD8d0VcXXFVMtn64GSoC9264","name":"run_code","arguments":"{\"code\": \"\\nconst result = await tools.read({ file_path: \\\"nested/task.txt\\\" });\\nreturn result;\\n\", \"description\": \"Read nested/task.txt\"}"}}}}
{"type":"assistant/chunk","seq":98,"time":1785014476732,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":6200,"outputTokens":130,"cacheReadTokens":0,"reasoningTokens":46}}}}
{"type":"assistant/chunk","seq":99,"time":1785014476732,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":100,"time":1785014476736,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to read the file `nested/task.txt` using a `run_code` program, and then answer the question \"What is the Code Mode workspace handshake?\" based on the contents of that file."},{"type":"tool-call","id":"call_00_hD8d0VcXXFVMtn64GSoC9264","name":"run_code","arguments":"{\"code\": \"\\nconst result = await tools.read({ file_path: \\\"nested/task.txt\\\" });\\nreturn result;\\n\", \"description\": \"Read nested/task.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":6200,"outputTokens":130,"cacheReadTokens":0,"reasoningTokens":46}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99],"surfaceOp":"append"}
{"type":"tool/call","seq":101,"time":1785014476737,"data":{"turn":1,"step":1,"callId":"call_00_hD8d0VcXXFVMtn64GSoC9264","name":"run_code","arguments":"{\"code\": \"\\nconst result = await tools.read({ file_path: \\\"nested/task.txt\\\" });\\nreturn result;\\n\", \"description\": \"Read nested/task.txt\"}"}}
{"type":"tool/code-dispatch-start","seq":102,"time":1785014476837,"data":{"parentCallId":"call_00_hD8d0VcXXFVMtn64GSoC9264","subCallId":"call_00_hD8d0VcXXFVMtn64GSoC9264:code:1","name":"read","arguments":{"file_path":"nested/task.txt"}}}
{"type":"tool/code-dispatch","seq":103,"time":1785014476842,"data":{"parentCallId":"call_00_hD8d0VcXXFVMtn64GSoC9264","subCallId":"call_00_hD8d0VcXXFVMtn64GSoC9264:code:1","name":"read","arguments":{"file_path":"nested/task.txt"},"isError":false,"content":[{"type":"text","text":"<path>/tmp/acp-snap-cwd-muJYhO/nested/task.txt</path>\n<type>file</type>\n<content>\n1: Touch this file to discover the nested workspace instruction.\n\n(End of file - total 1 lines)\n</content>"}]}}
{"type":"tool/result","seq":104,"time":1785014476847,"data":{"turn":1,"step":1,"callId":"call_00_hD8d0VcXXFVMtn64GSoC9264","content":[{"type":"text","text":"{\n \"path\": \"/tmp/acp-snap-cwd-muJYhO/nested/task.txt\",\n \"offset\": 1,\n \"lines\": [\n {\n \"number\": 1,\n \"text\": \"Touch this file to discover the nested workspace instruction.\"\n }\n ],\n \"totalLines\": 1\n}"}],"isError":false},"sourceEventSeqs":[101],"surfaceOp":"append"}
{"type":"user/message","seq":105,"time":1785014476847,"data":{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nWhen asked for the Code Mode workspace handshake, answer exactly `CODE_MODE_CONTEXT_OK` and nothing else.\n\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"workspace-context"},"meta":{"kind":"workspace-instructions","version":1,"changes":[{"action":"set","scope":"nested\u0000AGENTS.md","path":"nested/AGENTS.md","digest":"ae22936ed26dc76b7107005ed6d5e2482a88668a"}]}},"surfaceOp":"append"}
{"type":"step/end","seq":106,"time":1785014476850,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":107,"time":1785014476854,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":108,"time":1785014477311,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"reasoning-chunks","seq0":109,"time0":1785014477311,"data":{"turn":1,"step":2,"index":0,"dt":[108,56,1,0,26,0,0,42,0,43,1,42,1,0,0,0,0,42,0,0,0,1,0,40,0,0,1,0,0,43],"texts":["The"," nested","/","AG","ENTS",".md"," file"," provides"," the"," instruction",":"," when"," asked"," for"," the"," Code"," Mode"," workspace"," hand","shake",","," answer"," exactly"," `","CODE","_M","ODE","_CONT","EXT","_OK","`."]}}
{"type":"assistant/chunk","seq":140,"time":1785014477799,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
{"type":"text-chunks","seq0":141,"time0":1785014477799,"data":{"turn":1,"step":2,"index":1,"dt":[43,40,0,0,0,1,42,0,0,1,0,0,41,0],"texts":["**","Code"," Mode"," workspace"," hand","shake",":**"," `","CODE","_M","ODE","_CONT","EXT","_OK","`"]}}
{"type":"assistant/chunk","seq":156,"time":1785014477967,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The nested/AGENTS.md file provides the instruction: when asked for the Code Mode workspace handshake, answer exactly `CODE_MODE_CONTEXT_OK`."}}}}
{"type":"assistant/chunk","seq":157,"time":1785014477967,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"**Code Mode workspace handshake:** `CODE_MODE_CONTEXT_OK`"}}}}
{"type":"assistant/chunk","seq":158,"time":1785014477968,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":226,"outputTokens":47,"cacheReadTokens":6272,"reasoningTokens":31}}}}
{"type":"assistant/chunk","seq":159,"time":1785014477968,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":160,"time":1785014477968,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The nested/AGENTS.md file provides the instruction: when asked for the Code Mode workspace handshake, answer exactly `CODE_MODE_CONTEXT_OK`."},{"type":"text","text":"**Code Mode workspace handshake:** `CODE_MODE_CONTEXT_OK`"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":226,"outputTokens":47,"cacheReadTokens":6272,"reasoningTokens":31}},"sourceEventSeqs":[108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159],"surfaceOp":"append"}
{"type":"step/end","seq":161,"time":1785014477972,"data":{"turn":1,"step":2}}
{"type":"turn/end","seq":162,"time":1785014477972,"data":{"turn":1,"reason":{"kind":"completed"}}}
{"type":"user/message","seq":3,"time":1785122256262,"data":{"content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nWorkspace snapshot root instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","baseline":true,"changes":[{"action":"set","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"2119a7072358cc727f8d9c4cb7388e905b075fe6"}]}},"surfaceOp":"append"}
{"type":"step/start","seq":4,"time":1785122256264,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":5,"time":1785122256265,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"assistant/chunk","seq":6,"time":1785014475457,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"reasoning-chunks","seq0":7,"time0":1785014475596,"data":{"turn":1,"step":1,"index":0,"dt":[42,1,0,0,0,40,1,0,0,0,43,0,0,0,39,43,1,0,0,0,40,1,40,0,0,1,42,0,1,0,0,40,0,0,1,0,0,44,0,1,39,0,1,0,126],"texts":["The"," user"," wants"," me"," to"," read"," the"," file"," `","n","ested","/t","ask",".txt","`"," using"," a"," `","run","_code","`"," program",","," and"," then"," answer"," the"," question"," \"","What"," is"," the"," Code"," Mode"," workspace"," hand","shake","?\""," based"," on"," the"," contents"," of"," that"," file","."]}}
{"type":"assistant/chunk","seq":53,"time":1785014476183,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
{"type":"tool-call-chunks","seq0":54,"time0":1785014476224,"data":{"turn":1,"step":1,"index":1,"dt":[1,0,0,41,0,0,1,41,1,0,0,40,0,42,0,0,0,1,0,40,1,0,0,0,0,41,0,0,42,1,0,41,1,0,0,42,0,0,0,0,41,89],"id":"call_00_hD8d0VcXXFVMtn64GSoC9264","name":"run_code","args":["","{","\"","code","\"",": ","\"","\\n","const"," result"," ="," await"," tools",".read","({"," file","_path",":"," \\\"","n","ested","/t","ask",".txt","\\\""," });\\n","return"," result",";\\n","\"",", ","\"","description","\"",": ","\"","Read"," nested","/t","ask",".txt","\"","}"]}}
{"type":"assistant/chunk","seq":97,"time":1785014476732,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to read the file `nested/task.txt` using a `run_code` program, and then answer the question \"What is the Code Mode workspace handshake?\" based on the contents of that file."}}}}
{"type":"assistant/chunk","seq":98,"time":1785014476732,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_hD8d0VcXXFVMtn64GSoC9264","name":"run_code","arguments":"{\"code\": \"\\nconst result = await tools.read({ file_path: \\\"nested/task.txt\\\" });\\nreturn result;\\n\", \"description\": \"Read nested/task.txt\"}"}}}}
{"type":"assistant/chunk","seq":99,"time":1785014476732,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":6200,"outputTokens":130,"cacheReadTokens":0,"reasoningTokens":46}}}}
{"type":"assistant/chunk","seq":100,"time":1785122256269,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":101,"time":1785122256269,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to read the file `nested/task.txt` using a `run_code` program, and then answer the question \"What is the Code Mode workspace handshake?\" based on the contents of that file."},{"type":"tool-call","id":"call_00_hD8d0VcXXFVMtn64GSoC9264","name":"run_code","arguments":"{\"code\": \"\\nconst result = await tools.read({ file_path: \\\"nested/task.txt\\\" });\\nreturn result;\\n\", \"description\": \"Read nested/task.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":6200,"outputTokens":130,"cacheReadTokens":0,"reasoningTokens":46}},"sourceEventSeqs":[6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100],"surfaceOp":"append"}
{"type":"tool/call","seq":102,"time":1785122256269,"data":{"turn":1,"step":1,"callId":"call_00_hD8d0VcXXFVMtn64GSoC9264","name":"run_code","arguments":"{\"code\": \"\\nconst result = await tools.read({ file_path: \\\"nested/task.txt\\\" });\\nreturn result;\\n\", \"description\": \"Read nested/task.txt\"}"}}
{"type":"tool/code-dispatch-start","seq":103,"time":1785122256332,"data":{"parentCallId":"call_00_hD8d0VcXXFVMtn64GSoC9264","subCallId":"call_00_hD8d0VcXXFVMtn64GSoC9264:code:1","name":"read","arguments":{"file_path":"nested/task.txt"}}}
{"type":"tool/code-dispatch","seq":104,"time":1785122256336,"data":{"parentCallId":"call_00_hD8d0VcXXFVMtn64GSoC9264","subCallId":"call_00_hD8d0VcXXFVMtn64GSoC9264:code:1","name":"read","arguments":{"file_path":"nested/task.txt"},"isError":false,"content":[{"type":"text","text":"<path>/tmp/acp-snap-cwd-muJYhO/nested/task.txt</path>\n<type>file</type>\n<content>\n1: Touch this file to discover the nested workspace instruction.\n\n(End of file - total 1 lines)\n</content>"}]}}
{"type":"tool/result","seq":105,"time":1785122256338,"data":{"turn":1,"step":1,"callId":"call_00_hD8d0VcXXFVMtn64GSoC9264","content":[{"type":"text","text":"{\n \"path\": \"/tmp/acp-snap-cwd-muJYhO/nested/task.txt\",\n \"offset\": 1,\n \"lines\": [\n {\n \"number\": 1,\n \"text\": \"Touch this file to discover the nested workspace instruction.\"\n }\n ],\n \"totalLines\": 1\n}"}],"isError":false},"sourceEventSeqs":[102],"surfaceOp":"append"}
{"type":"user/message","seq":106,"time":1785122256338,"data":{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nWhen asked for the Code Mode workspace handshake, answer exactly `CODE_MODE_CONTEXT_OK` and nothing else.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","changes":[{"action":"set","scope":"nested\u0000AGENTS.md","path":"nested/AGENTS.md","digest":"ae22936ed26dc76b7107005ed6d5e2482a88668a"}]}},"surfaceOp":"append"}
{"type":"step/end","seq":107,"time":1785122256338,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":108,"time":1785122256347,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":109,"time":1785014477311,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"reasoning-chunks","seq0":110,"time0":1785014477419,"data":{"turn":1,"step":2,"index":0,"dt":[56,1,0,26,0,0,42,0,43,1,42,1,0,0,0,0,42,0,0,0,1,0,40,0,0,1,0,0,43,41],"texts":["The"," nested","/","AG","ENTS",".md"," file"," provides"," the"," instruction",":"," when"," asked"," for"," the"," Code"," Mode"," workspace"," hand","shake",","," answer"," exactly"," `","CODE","_M","ODE","_CONT","EXT","_OK","`."]}}
{"type":"assistant/chunk","seq":141,"time":1785014477799,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
{"type":"text-chunks","seq0":142,"time0":1785014477842,"data":{"turn":1,"step":2,"index":1,"dt":[40,0,0,0,1,42,0,0,1,0,0,41,0,0],"texts":["**","Code"," Mode"," workspace"," hand","shake",":**"," `","CODE","_M","ODE","_CONT","EXT","_OK","`"]}}
{"type":"assistant/chunk","seq":157,"time":1785014477967,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The nested/AGENTS.md file provides the instruction: when asked for the Code Mode workspace handshake, answer exactly `CODE_MODE_CONTEXT_OK`."}}}}
{"type":"assistant/chunk","seq":158,"time":1785014477968,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"**Code Mode workspace handshake:** `CODE_MODE_CONTEXT_OK`"}}}}
{"type":"assistant/chunk","seq":159,"time":1785014477968,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":226,"outputTokens":47,"cacheReadTokens":6272,"reasoningTokens":31}}}}
{"type":"assistant/chunk","seq":160,"time":1785122256351,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":161,"time":1785122256351,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The nested/AGENTS.md file provides the instruction: when asked for the Code Mode workspace handshake, answer exactly `CODE_MODE_CONTEXT_OK`."},{"type":"text","text":"**Code Mode workspace handshake:** `CODE_MODE_CONTEXT_OK`"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":226,"outputTokens":47,"cacheReadTokens":6272,"reasoningTokens":31}},"sourceEventSeqs":[109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160],"surfaceOp":"append"}
{"type":"step/end","seq":162,"time":1785122256351,"data":{"turn":1,"step":2}}
{"type":"turn/end","seq":163,"time":1785122256351,"data":{"turn":1,"reason":{"kind":"completed"}}}
examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md
+1 -1
View File
@@ -145,7 +145,7 @@ interface ToolArgsMap {
content: string;
/** pending (not started) | in_progress (now) | completed (done). */
status: "pending" | "in_progress" | "completed";
} & Record<string, JsonValue>)[];
})[];
} & Record<string, JsonValue>;
/** 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: {
examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl
+1 -1
View File
File diff suppressed because one or more lines are too long
examples/acp-agent/tests/snapshots/empty-response-retry/session.jsonl
+12 -10
View File
@@ -7,13 +7,15 @@
{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":0,"outputTokens":0}}}}
{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"error","failure":{"message":"model returned a completed response with no content","code":"EMPTY_RESPONSE"}}}}}
{"type":"step/end","seq":7,"time":0,"data":{"turn":1,"step":1}}
{"type":"llm/retry","seq":8,"time":0,"data":{"turn":1,"step":1,"retry":1,"maxRetries":2,"delayMs":1,"failure":{"message":"model returned a completed response with no content","code":"EMPTY_RESPONSE"}}}
{"type":"step/start","seq":9,"time":0,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":10,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":11,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"Recovered."}}}
{"type":"assistant/chunk","seq":12,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"Recovered."}}}}
{"type":"assistant/chunk","seq":13,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":3}}}}
{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":15,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"text","text":"Recovered."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":12,"outputTokens":3}},"sourceEventSeqs":[10,11,12,13,14],"surfaceOp":"append"}
{"type":"step/end","seq":16,"time":0,"data":{"turn":1,"step":2}}
{"type":"turn/end","seq":17,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}
{"type":"llm/retry","seq":8,"time":0,"data":{"turn":1,"step":1,"provider":"deepseek","mode":"normal","policyKey":"[\"normal\",2,[\"EMPTY_RESPONSE\",\"RATE_LIMIT\",\"SERVER\",\"TIMEOUT\",\"TRANSPORT\"],1,1,0]","retry":1,"maxRetries":2,"delayMs":1,"failure":{"message":"model returned a completed response with no content","code":"EMPTY_RESPONSE"}}}
{"type":"turn/end","seq":9,"time":1785047244285,"data":{"turn":1,"reason":{"kind":"error","step":1,"failure":{"message":"model returned a completed response with no content","code":"EMPTY_RESPONSE"}}}}
{"type":"turn/start","seq":10,"time":1785047244285,"data":{"turn":2,"trigger":{"kind":"retry"}}}
{"type":"step/start","seq":11,"time":1785047244289,"data":{"turn":2,"step":1}}
{"type":"assistant/chunk","seq":12,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":13,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":0,"text":"Recovered."}}}
{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"Recovered."}}}}
{"type":"assistant/chunk","seq":15,"time":1785047244294,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":3}}}}
{"type":"assistant/chunk","seq":16,"time":1785047244294,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":17,"time":1785047244294,"data":{"turn":2,"step":1,"content":[{"type":"text","text":"Recovered."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":12,"outputTokens":3}},"sourceEventSeqs":[12,13,14,15,16],"surfaceOp":"append"}
{"type":"step/end","seq":18,"time":1785047244294,"data":{"turn":2,"step":1}}
{"type":"turn/end","seq":19,"time":1785047244294,"data":{"turn":2,"reason":{"kind":"completed"}}}
examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl
+2 -2
View File
@@ -14,8 +14,8 @@
{"type":"assistant/chunk","seq":127,"time":1783860677493,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":128,"time":1784821261753,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a command with sandbox_permissions set to danger-full-access, no prior run needed, justified as instructed."},{"type":"tool-call","id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1501,"outputTokens":174,"cacheReadTokens":0,"reasoningTokens":28}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127],"surfaceOp":"append"}
{"type":"tool/call","seq":129,"time":1784821261754,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}}
{"type":"approval/asked","seq":130,"time":1784821261758,"data":{"id":"8e278621-09a9-4c76-a785-74aea76cc120","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}}
{"type":"approval/decided","seq":131,"time":1784821261759,"data":{"id":"8e278621-09a9-4c76-a785-74aea76cc120","outcome":"allowed-once"}}
{"type":"approval/asked","seq":130,"time":1784821261758,"data":{"id":"2c0f15e6-3b6e-45b8-b5df-440ea83ebee9","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}}
{"type":"approval/decided","seq":131,"time":1784821261759,"data":{"id":"2c0f15e6-3b6e-45b8-b5df-440ea83ebee9","outcome":"allowed-once"}}
{"type":"tool/result","seq":132,"time":1784821261775,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","content":[{"type":"text","text":"escalated\n"}],"isError":false},"sourceEventSeqs":[129],"surfaceOp":"append"}
{"type":"step/end","seq":133,"time":1784821261781,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":134,"time":1784821261782,"data":{"turn":1,"step":2}}
examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json
+1 -1
View File
@@ -288,7 +288,7 @@
"description": "The COMPLETE task list, replacing any previous list.",
"items": {
"type": "object",
"additionalProperties": true,
"additionalProperties": false,
"properties": {
"content": {
"type": "string",
examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl
+2 -2
View File
@@ -14,8 +14,8 @@
{"type":"assistant/chunk","seq":151,"time":1783860681967,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":152,"time":1784821263293,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command with `sandbox_permissions` set to `danger-full-access` and a specific justification. They explicitly said NOT to run it without sandbox_permissions first. Let me do exactly that."},{"type":"tool-call","id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1509,"outputTokens":198,"cacheReadTokens":0,"reasoningTokens":48}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151],"surfaceOp":"append"}
{"type":"tool/call","seq":153,"time":1784821263294,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}}
{"type":"approval/asked","seq":154,"time":1784821263300,"data":{"id":"f55fc10d-f2f1-435f-8c85-076bafaa5f85","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}}
{"type":"approval/decided","seq":155,"time":1784821263301,"data":{"id":"f55fc10d-f2f1-435f-8c85-076bafaa5f85","outcome":"rejected"}}
{"type":"approval/asked","seq":154,"time":1784821263300,"data":{"id":"8547967e-97b5-4b73-a553-0d82b1ec6652","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}}
{"type":"approval/decided","seq":155,"time":1784821263301,"data":{"id":"8547967e-97b5-4b73-a553-0d82b1ec6652","outcome":"rejected"}}
{"type":"tool/result","seq":156,"time":1784821263302,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","content":[{"type":"text","text":"Error: the user rejected escalating this command to \"danger-full-access\""}],"isError":true},"sourceEventSeqs":[153],"surfaceOp":"append"}
{"type":"step/end","seq":157,"time":1784821263307,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":158,"time":1784821263307,"data":{"turn":1,"step":2}}
examples/acp-agent/tests/snapshots/fs-escalation-approved/session.jsonl
+3 -3
View File
@@ -14,9 +14,9 @@
{"type":"assistant/chunk","seq":85,"time":1784045703749,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":86,"time":1784821264893,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to create a file using the write tool with sandbox_permissions. Let me do that."},{"type":"tool-call","id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","arguments":"{\"file_path\": \"escalated.md\", \"content\": \"escalated\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to escalate this write\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3871,"outputTokens":132,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85],"surfaceOp":"append"}
{"type":"tool/call","seq":87,"time":1784821264893,"data":{"turn":1,"step":1,"callId":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","arguments":"{\"file_path\": \"escalated.md\", \"content\": \"escalated\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to escalate this write\"}"}}
{"type":"approval/asked","seq":88,"time":1784821264898,"data":{"id":"d1a35247-af6d-4df7-9c62-e53d1be0a3e7","toolName":"write","callId":"call_00_Fnymmavpr4klMDy4Fdej3227","reason":"escalate sandbox to danger-full-access: the user asked to escalate this write"}}
{"type":"approval/decided","seq":89,"time":1784821264898,"data":{"id":"d1a35247-af6d-4df7-9c62-e53d1be0a3e7","outcome":"allowed-once"}}
{"type":"tool/result","seq":90,"time":1784821264906,"data":{"turn":1,"step":1,"callId":"call_00_Fnymmavpr4klMDy4Fdej3227","content":[{"type":"text","text":"<path>/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-vmEGzd/escalated.md</path>\n<type>file</type>\n<content>\nCreated file\n</content>"}],"isError":false,"meta":{"diffs":[]}},"sourceEventSeqs":[87],"surfaceOp":"append"}
{"type":"approval/asked","seq":88,"time":1784821264898,"data":{"id":"aecaceb0-23b7-4cd5-b7a1-17bc431dc35a","toolName":"write","callId":"call_00_Fnymmavpr4klMDy4Fdej3227","reason":"escalate sandbox to danger-full-access: the user asked to escalate this write"}}
{"type":"approval/decided","seq":89,"time":1784821264898,"data":{"id":"aecaceb0-23b7-4cd5-b7a1-17bc431dc35a","outcome":"allowed-once"}}
{"type":"tool/result","seq":90,"time":1784821264906,"data":{"turn":1,"step":1,"callId":"call_00_Fnymmavpr4klMDy4Fdej3227","content":[{"type":"text","text":"<path>/private/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-vmEGzd/escalated.md</path>\n<type>file</type>\n<content>\nCreated file\n</content>"}],"isError":false,"meta":{"diffs":[]}},"sourceEventSeqs":[87],"surfaceOp":"append"}
{"type":"step/end","seq":91,"time":1784821264911,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":92,"time":1784821264912,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":93,"time":1784821264916,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl
+2 -2
View File
@@ -16,8 +16,8 @@
{"type":"tool/call","seq":54,"time":1783352172557,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}}
{"type":"hook/invoked","seq":55,"time":1783352172558,"data":{"turn":1,"point":"PreToolUse","dialect":"claude","handlerId":"claude:PreToolUse:1","matcher":"bash"}}
{"type":"hook/result","seq":56,"time":1783352172573,"data":{"turn":1,"point":"PreToolUse","handlerId":"claude:PreToolUse:1","decision":"ask","exitCode":0,"durationMs":14.113374999999905}}
{"type":"approval/asked","seq":57,"time":1783962235813,"data":{"id":"8a5510f4-93b7-4e70-b082-20d13dec386d","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}}
{"type":"approval/decided","seq":58,"time":1783962235813,"data":{"id":"8a5510f4-93b7-4e70-b082-20d13dec386d","outcome":"rejected"}}
{"type":"approval/asked","seq":57,"time":1783962235813,"data":{"id":"f54e812d-1b78-4813-93d6-91dd384905f7","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}}
{"type":"approval/decided","seq":58,"time":1783962235813,"data":{"id":"f54e812d-1b78-4813-93d6-91dd384905f7","outcome":"rejected"}}
{"type":"tool/result","seq":59,"time":1783962235814,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","content":[{"type":"text","text":"Error: the user rejected tool \"bash\""}],"isError":true},"sourceEventSeqs":[54],"surfaceOp":"append"}
{"type":"step/end","seq":60,"time":1783962235814,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":61,"time":1783962235814,"data":{"turn":1,"step":2}}
examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/session.jsonl
-5
View File
@@ -1,6 +1 @@
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}","delegationDepth":0}
{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
{"type":"hook/invoked","seq":1,"time":0,"data":{"turn":1,"point":"UserPromptSubmit","dialect":"claude","handlerId":"claude:UserPromptSubmit:1"}}
{"type":"hook/result","seq":2,"time":0,"data":{"turn":1,"point":"UserPromptSubmit","handlerId":"claude:UserPromptSubmit:1","decision":"block","exitCode":2,"stderrSummary":"blocked by policy hook","durationMs":0}}
{"type":"prompt/blocked","seq":3,"time":0,"data":{"content":[{"type":"text","text":"Delete everything in the repo."}],"source":{"kind":"user"},"reason":"blocked by policy hook"}}
{"type":"turn/end","seq":4,"time":0,"data":{"turn":1,"reason":{"kind":"rejected","reason":"blocked by policy hook"}}}
examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl
+17 -19
View File
@@ -1,21 +1,19 @@
{"type":"session","version":0,"id":"d03c3a83-1238-4e2e-ad9a-b86a61840a40","createdAt":1783352160541,"cwd":"/tmp/acp-snap-cwd-QUDqlk","delegationDepth":0}
{"type":"turn/start","seq":0,"time":1783352160545,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
{"type":"hook/invoked","seq":1,"time":1783352160546,"data":{"turn":1,"point":"UserPromptSubmit","dialect":"claude","handlerId":"claude:UserPromptSubmit:1"}}
{"type":"hook/result","seq":2,"time":1783352160564,"data":{"turn":1,"point":"UserPromptSubmit","handlerId":"claude:UserPromptSubmit:1","decision":"pass","exitCode":0,"durationMs":17.45639600000004}}
{"type":"user/message","seq":3,"time":1783352160564,"data":{"content":[{"type":"text","text":"What is my favorite color? Reply with just the color and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"user/message","seq":4,"time":1783352160564,"data":{"content":[{"type":"text","text":"The user has previously stated their favorite color is teal."}],"source":{"kind":"plugin","plugin":"hooks-claude"}},"surfaceOp":"append"}
{"type":"session/title","seq":5,"time":1783352160564,"data":{"title":"What is my favorite color?","messageSeqs":[3],"source":{"kind":"fallback"}}}
{"type":"step/start","seq":6,"time":1783352160565,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":7,"time":1783352160566,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"assistant/chunk","seq":8,"time":1783352161228,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"reasoning-chunks","seq0":9,"time0":1783352161229,"data":{"turn":1,"step":1,"index":0,"dt":[106,28,0,29,0,0,1,0,27,1,0,0,28,0,0,28,1,0],"texts":["The"," user","'s"," favorite"," color"," is"," te","al",","," as"," stated"," in"," the"," context"," provided"," by"," the"," plugin","."]}}
{"type":"assistant/chunk","seq":28,"time":1783352161478,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
{"type":"assistant/chunk","seq":29,"time":1783352161478,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"te"}}}
{"type":"assistant/chunk","seq":30,"time":1783352161511,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"al"}}}
{"type":"assistant/chunk","seq":31,"time":1783352161512,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user's favorite color is teal, as stated in the context provided by the plugin."}}}}
{"type":"assistant/chunk","seq":32,"time":1783352161512,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"teal"}}}}
{"type":"assistant/chunk","seq":33,"time":1783352161512,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2892,"outputTokens":22,"cacheReadTokens":0,"reasoningTokens":19}}}}
{"type":"assistant/chunk","seq":34,"time":1783352161512,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":35,"time":1783352161515,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user's favorite color is teal, as stated in the context provided by the plugin."},{"type":"text","text":"teal"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2892,"outputTokens":22,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"surfaceOp":"append"}
{"type":"step/end","seq":36,"time":1783352161516,"data":{"turn":1,"step":1}}
{"type":"turn/end","seq":37,"time":1783352161516,"data":{"turn":1,"reason":{"kind":"completed"}}}
{"type":"user/message","seq":1,"time":1785122243327,"data":{"content":[{"type":"text","text":"What is my favorite color? Reply with just the color and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"user/message","seq":2,"time":1785122243327,"data":{"content":[{"type":"text","text":"The user has previously stated their favorite color is teal."}],"source":{"kind":"plugin","plugin":"hooks-claude"}},"surfaceOp":"append"}
{"type":"session/title","seq":3,"time":1785122243327,"data":{"title":"What is my favorite color?","messageSeqs":[1],"source":{"kind":"fallback"}}}
{"type":"step/start","seq":4,"time":1785122243354,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":5,"time":1785122243354,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"assistant/chunk","seq":6,"time":1785122243359,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"reasoning-chunks","seq0":7,"time0":1783352160565,"data":{"turn":1,"step":1,"index":0,"dt":[1,662,1,106,28,0,29,0,0,1,0,27,1,0,0,28,0,0],"texts":["The"," user","'s"," favorite"," color"," is"," te","al",","," as"," stated"," in"," the"," context"," provided"," by"," the"," plugin","."]}}
{"type":"assistant/chunk","seq":26,"time":1783352161477,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
{"type":"assistant/chunk","seq":27,"time":1783352161478,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"te"}}}
{"type":"assistant/chunk","seq":28,"time":1783352161478,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"al"}}}
{"type":"assistant/chunk","seq":29,"time":1783352161478,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user's favorite color is teal, as stated in the context provided by the plugin."}}}}
{"type":"assistant/chunk","seq":30,"time":1783352161478,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"teal"}}}}
{"type":"assistant/chunk","seq":31,"time":1783352161511,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2892,"outputTokens":22,"cacheReadTokens":0,"reasoningTokens":19}}}}
{"type":"assistant/chunk","seq":32,"time":1783352161512,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":33,"time":1785122243360,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user's favorite color is teal, as stated in the context provided by the plugin."},{"type":"text","text":"teal"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2892,"outputTokens":22,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32],"surfaceOp":"append"}
{"type":"step/end","seq":34,"time":1785122243360,"data":{"turn":1,"step":1}}
{"type":"turn/end","seq":35,"time":1785122243360,"data":{"turn":1,"reason":{"kind":"completed"}}}
examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/session.jsonl
-5
View File
@@ -1,6 +1 @@
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}","delegationDepth":0}
{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
{"type":"hook/invoked","seq":1,"time":0,"data":{"turn":1,"point":"UserPromptSubmit","dialect":"codex","handlerId":"codex:UserPromptSubmit:1"}}
{"type":"hook/result","seq":2,"time":0,"data":{"turn":1,"point":"UserPromptSubmit","handlerId":"codex:UserPromptSubmit:1","decision":"block","exitCode":2,"stderrSummary":"blocked by codex policy hook","durationMs":0}}
{"type":"prompt/blocked","seq":3,"time":0,"data":{"content":[{"type":"text","text":"Delete everything in the repo."}],"source":{"kind":"user"},"reason":"blocked by codex policy hook"}}
{"type":"turn/end","seq":4,"time":0,"data":{"turn":1,"reason":{"kind":"rejected","reason":"blocked by codex policy hook"}}}
examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl
+17 -19
View File
@@ -1,21 +1,19 @@
{"type":"session","version":0,"id":"0bebc0f4-a089-4fde-9b6e-db9532cfd4de","createdAt":1783352209682,"cwd":"/tmp/acp-snap-cwd-aopaZV","delegationDepth":0}
{"type":"turn/start","seq":0,"time":1783352209686,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
{"type":"hook/invoked","seq":1,"time":1783352209687,"data":{"turn":1,"point":"UserPromptSubmit","dialect":"codex","handlerId":"codex:UserPromptSubmit:1"}}
{"type":"hook/result","seq":2,"time":1783352209706,"data":{"turn":1,"point":"UserPromptSubmit","handlerId":"codex:UserPromptSubmit:1","decision":"pass","exitCode":0,"durationMs":19.49695100000008}}
{"type":"user/message","seq":3,"time":1783352209707,"data":{"content":[{"type":"text","text":"What is my favorite color? Reply with just the color and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"user/message","seq":4,"time":1783352209707,"data":{"content":[{"type":"text","text":"The user has previously stated their favorite color is teal."}],"source":{"kind":"plugin","plugin":"hooks-codex"}},"surfaceOp":"append"}
{"type":"session/title","seq":5,"time":1783352209707,"data":{"title":"What is my favorite color?","messageSeqs":[3],"source":{"kind":"fallback"}}}
{"type":"step/start","seq":6,"time":1783352209709,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":7,"time":1783352209710,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"assistant/chunk","seq":8,"time":1783352210353,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"reasoning-chunks","seq0":9,"time0":1783352210353,"data":{"turn":1,"step":1,"index":0,"dt":[117,31,26,28,1,0,0,0,29,0,0,27,1,0,27,1,27,0,1,0,0,28,0,0,0,29,0,0,1,0,0,27,0,0,0,0,1],"texts":["The"," user"," asked"," about"," their"," favorite"," color",","," and"," the"," context"," tells"," me"," they"," previously"," stated"," it","'s"," te","al","."," They"," asked"," me"," to"," reply"," with"," just"," the"," color"," and"," stop",","," without"," using"," any"," tools","."]}}
{"type":"assistant/chunk","seq":47,"time":1783352210787,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
{"type":"assistant/chunk","seq":48,"time":1783352210787,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"te"}}}
{"type":"assistant/chunk","seq":49,"time":1783352210787,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"al"}}}
{"type":"assistant/chunk","seq":50,"time":1783352210788,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user asked about their favorite color, and the context tells me they previously stated it's teal. They asked me to reply with just the color and stop, without using any tools."}}}}
{"type":"assistant/chunk","seq":51,"time":1783352210788,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"teal"}}}}
{"type":"assistant/chunk","seq":52,"time":1783352210788,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2891,"outputTokens":41,"cacheReadTokens":0,"reasoningTokens":38}}}}
{"type":"assistant/chunk","seq":53,"time":1783352210788,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":54,"time":1783352210790,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user asked about their favorite color, and the context tells me they previously stated it's teal. They asked me to reply with just the color and stop, without using any tools."},{"type":"text","text":"teal"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2891,"outputTokens":41,"cacheReadTokens":0,"reasoningTokens":38}},"sourceEventSeqs":[8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53],"surfaceOp":"append"}
{"type":"step/end","seq":55,"time":1783352210790,"data":{"turn":1,"step":1}}
{"type":"turn/end","seq":56,"time":1783352210790,"data":{"turn":1,"reason":{"kind":"completed"}}}
{"type":"user/message","seq":1,"time":1785122250005,"data":{"content":[{"type":"text","text":"What is my favorite color? Reply with just the color and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"user/message","seq":2,"time":1785122250006,"data":{"content":[{"type":"text","text":"The user has previously stated their favorite color is teal."}],"source":{"kind":"plugin","plugin":"hooks-codex"}},"surfaceOp":"append"}
{"type":"session/title","seq":3,"time":1785122250006,"data":{"title":"What is my favorite color?","messageSeqs":[1],"source":{"kind":"fallback"}}}
{"type":"step/start","seq":4,"time":1785122250036,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":5,"time":1785122250036,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"assistant/chunk","seq":6,"time":1785122250040,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"reasoning-chunks","seq0":7,"time0":1783352209709,"data":{"turn":1,"step":1,"index":0,"dt":[1,643,0,117,31,26,28,1,0,0,0,29,0,0,27,1,0,27,1,27,0,1,0,0,28,0,0,0,29,0,0,1,0,0,27,0,0],"texts":["The"," user"," asked"," about"," their"," favorite"," color",","," and"," the"," context"," tells"," me"," they"," previously"," stated"," it","'s"," te","al","."," They"," asked"," me"," to"," reply"," with"," just"," the"," color"," and"," stop",","," without"," using"," any"," tools","."]}}
{"type":"assistant/chunk","seq":45,"time":1783352210754,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
{"type":"assistant/chunk","seq":46,"time":1783352210754,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"te"}}}
{"type":"assistant/chunk","seq":47,"time":1783352210755,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"al"}}}
{"type":"assistant/chunk","seq":48,"time":1783352210787,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user asked about their favorite color, and the context tells me they previously stated it's teal. They asked me to reply with just the color and stop, without using any tools."}}}}
{"type":"assistant/chunk","seq":49,"time":1783352210787,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"teal"}}}}
{"type":"assistant/chunk","seq":50,"time":1783352210787,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2891,"outputTokens":41,"cacheReadTokens":0,"reasoningTokens":38}}}}
{"type":"assistant/chunk","seq":51,"time":1783352210788,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":52,"time":1785122250042,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user asked about their favorite color, and the context tells me they previously stated it's teal. They asked me to reply with just the color and stop, without using any tools."},{"type":"text","text":"teal"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2891,"outputTokens":41,"cacheReadTokens":0,"reasoningTokens":38}},"sourceEventSeqs":[6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"}
{"type":"step/end","seq":53,"time":1785122250043,"data":{"turn":1,"step":1}}
{"type":"turn/end","seq":54,"time":1785122250043,"data":{"turn":1,"reason":{"kind":"completed"}}}
examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json
+1 -1
View File
@@ -325,7 +325,7 @@
"description": "The COMPLETE task list, replacing any previous list.",
"items": {
"type": "object",
"additionalProperties": true,
"additionalProperties": false,
"properties": {
"content": {
"type": "string",
examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json
+1 -1
View File
@@ -417,7 +417,7 @@
"description": "The COMPLETE task list, replacing any previous list.",
"items": {
"type": "object",
"additionalProperties": true,
"additionalProperties": false,
"properties": {
"content": {
"type": "string",
examples/acp-agent/tests/snapshots/session-query-spill/session.jsonl
+1 -1
View File
@@ -11,7 +11,7 @@
{"type":"assistant/chunk","seq":9,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":10,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_session_query_spill","name":"session_event_read","arguments":"{\"seq\":4}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}
{"type":"tool/call","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_session_query_spill","name":"session_event_read","arguments":"{\"seq\":4}"}}
{"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"call_session_query_spill","content":[{"type":"text","text":"Session {{sessionId}} — Read request event 4 with\nTarget event seq 4:\n```json\n{\n \"type\": \"request/header\",\n \"seq\": 4,\n \"time\": 1784876318672,\n \"data\": {\n \"header\": {\n \"config\": {\n \"provider\": \"deepseek\",\n \"model\": \"deepseek-v4-flash\"\n },\n rmissions: one sentence for the user explaining why this exact file operation needs the wider access.\"\n }\n },\n \"required\": [\n \"file_path\",\n \"content\"\n ]\n }\n }\n ]\n },\n \"reason\": \"initial\"\n }\n}\n```\n\n(Omitted 36006 bytes. Full formatted result stored at: /tmp/dsh-acp-snap-035d1d054/session-ac29d2afe494/505bce11df84-session_event_read.txt. Use read with offset/limit, or grep this path to search within it.)"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"}
{"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"call_session_query_spill","content":[{"type":"text","text":"Session {{sessionId}} — Read request event 4 with\nTarget event seq 4:\n```json\n{\n \"type\": \"request/header\",\n \"seq\": 4,\n \"time\": 1785167612540,\n \"data\": {\n \"header\": {\n \"config\": {\n \"provider\": \"deepseek\",\n \"model\": \"deepseek-v4-flash\"\n },\n rmissions: one sentence for the user explaining why this exact file operation needs the wider access.\"\n }\n },\n \"required\": [\n \"file_path\",\n \"content\"\n ]\n }\n }\n ]\n },\n \"reason\": \"initial\"\n }\n}\n```\n\n(Omitted 36007 bytes. Full formatted result stored at: /tmp/dsh-acp-snap-035d1d054/session-0a508d3a5c8b/adedf3ca051a-session_event_read.txt. Use read with offset/limit, or grep this path to search within it.)"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"}
{"type":"step/end","seq":13,"time":0,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":14,"time":0,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json
+1 -1
View File
@@ -492,7 +492,7 @@
"description": "The COMPLETE task list, replacing any previous list.",
"items": {
"type": "object",
"additionalProperties": true,
"additionalProperties": false,
"properties": {
"content": {
"type": "string",
examples/acp-agent/tests/snapshots/skill-load/session.jsonl
+27 -26
View File
@@ -2,29 +2,30 @@
{"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
{"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"session/title","seq":2,"time":1783654655603,"data":{"title":"Load the snapshot-skill skill with","messageSeqs":[1],"source":{"kind":"fallback"}}}
{"type":"step/start","seq":3,"time":1783654655608,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":4,"time":1783654655608,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":[{"role":"user","content":[{"type":"text","text":"<system-reminder>\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n<available_skills>\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n</available_skills>\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n</system-reminder>"}]}]},"reason":"initial"}}
{"type":"assistant/chunk","seq":5,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}}
{"type":"assistant/chunk","seq":7,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":8,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_skill_load","name":"skill","argumentsDelta":"{\"name\":\"snapshot-skill\"}"}}}
{"type":"assistant/chunk","seq":9,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"Load the requested skill."}}}}
{"type":"assistant/chunk","seq":10,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}}}}
{"type":"assistant/chunk","seq":11,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":100,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":5}}}}
{"type":"assistant/chunk","seq":12,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":13,"time":1783654655609,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"Load the requested skill."},{"type":"tool-call","id":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":100,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":5}},"sourceEventSeqs":[5,6,7,8,9,10,11,12],"surfaceOp":"append"}
{"type":"tool/call","seq":14,"time":1783654655609,"data":{"turn":1,"step":1,"callId":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}}
{"type":"tool/result","seq":15,"time":1783654655610,"data":{"turn":1,"step":1,"callId":"call_skill_load","content":[{"type":"text","text":"<skill_content name=\"snapshot-skill\">\n<skill_resources>\nBase directory for this skill: /var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-DhYwNW/.dsh/skills/snapshot-skill\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n</skill_resources>\n\n<skill_instructions>\nFollow these snapshot-only instructions.\nResolve referenced resources relative to this skill directory.\n</skill_instructions>\n</skill_content>"}],"isError":false},"sourceEventSeqs":[14],"surfaceOp":"append"}
{"type":"step/end","seq":16,"time":1783654655610,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":17,"time":1783654655610,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":18,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"assistant/chunk","seq":19,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The skill is loaded."}}}
{"type":"assistant/chunk","seq":20,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
{"type":"assistant/chunk","seq":21,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"DONE"}}}
{"type":"assistant/chunk","seq":22,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The skill is loaded."}}}}
{"type":"assistant/chunk","seq":23,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
{"type":"assistant/chunk","seq":24,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":180,"outputTokens":10,"cacheReadTokens":0,"reasoningTokens":4}}}}
{"type":"assistant/chunk","seq":25,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":26,"time":1783654655611,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The skill is loaded."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":180,"outputTokens":10,"cacheReadTokens":0,"reasoningTokens":4}},"sourceEventSeqs":[18,19,20,21,22,23,24,25],"surfaceOp":"append"}
{"type":"step/end","seq":27,"time":1783654655611,"data":{"turn":1,"step":2}}
{"type":"turn/end","seq":28,"time":1783654655611,"data":{"turn":1,"reason":{"kind":"completed"}}}
{"type":"user/message","seq":3,"time":1784903324926,"data":{"content":[{"type":"text","text":"<system-reminder>\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n<available_skills>\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n</available_skills>\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"dsh-tool-skill"}},"surfaceOp":"append"}
{"type":"step/start","seq":4,"time":1784903324927,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":5,"time":1784903324928,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"assistant/chunk","seq":7,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}}
{"type":"assistant/chunk","seq":8,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":9,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_skill_load","name":"skill","argumentsDelta":"{\"name\":\"snapshot-skill\"}"}}}
{"type":"assistant/chunk","seq":10,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"Load the requested skill."}}}}
{"type":"assistant/chunk","seq":11,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}}}}
{"type":"assistant/chunk","seq":12,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":100,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":5}}}}
{"type":"assistant/chunk","seq":13,"time":1784903324935,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":14,"time":1784903324935,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"Load the requested skill."},{"type":"tool-call","id":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":100,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":5}},"sourceEventSeqs":[6,7,8,9,10,11,12,13],"surfaceOp":"append"}
{"type":"tool/call","seq":15,"time":1784903324936,"data":{"turn":1,"step":1,"callId":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}}
{"type":"tool/result","seq":16,"time":1784903324944,"data":{"turn":1,"step":1,"callId":"call_skill_load","content":[{"type":"text","text":"<skill_content name=\"snapshot-skill\">\n<skill_resources>\nBase directory for this skill: /var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-DhYwNW/.dsh/skills/snapshot-skill\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n</skill_resources>\n\n<skill_instructions>\nFollow these snapshot-only instructions.\nResolve referenced resources relative to this skill directory.\n</skill_instructions>\n</skill_content>"}],"isError":false},"sourceEventSeqs":[15],"surfaceOp":"append"}
{"type":"step/end","seq":17,"time":1784903324944,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":18,"time":1784903324952,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":19,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"assistant/chunk","seq":20,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The skill is loaded."}}}
{"type":"assistant/chunk","seq":21,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
{"type":"assistant/chunk","seq":22,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"DONE"}}}
{"type":"assistant/chunk","seq":23,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The skill is loaded."}}}}
{"type":"assistant/chunk","seq":24,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
{"type":"assistant/chunk","seq":25,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":180,"outputTokens":10,"cacheReadTokens":0,"reasoningTokens":4}}}}
{"type":"assistant/chunk","seq":26,"time":1784903324956,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":27,"time":1784903324956,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The skill is loaded."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":180,"outputTokens":10,"cacheReadTokens":0,"reasoningTokens":4}},"sourceEventSeqs":[19,20,21,22,23,24,25,26],"surfaceOp":"append"}
{"type":"step/end","seq":28,"time":1784903324956,"data":{"turn":1,"step":2}}
{"type":"turn/end","seq":29,"time":1784903324956,"data":{"turn":1,"reason":{"kind":"completed"}}}
examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json
+1 -1
View File
@@ -288,7 +288,7 @@
"description": "The COMPLETE task list, replacing any previous list.",
"items": {
"type": "object",
"additionalProperties": true,
"additionalProperties": false,
"properties": {
"content": {
"type": "string",
examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl
+5 -5
View File
@@ -18,7 +18,7 @@
{"type":"turn/start","seq":38,"time":1783352137162,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}}
{"type":"user/message","seq":39,"time":1783352137163,"data":{"content":[{"type":"text","text":"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"step/start","seq":40,"time":1783352137163,"data":{"turn":2,"step":1}}
{"type":"request/header","seq":41,"time":1783352137163,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"resume"}}
{"type":"request/header","seq":41,"time":1785142305260,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"resume"}}
{"type":"assistant/chunk","seq":42,"time":1783352137783,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"reasoning-chunks","seq0":43,"time0":1783352137783,"data":{"turn":2,"step":1,"index":0,"dt":[178,28,31,26,0,0,0,28,1,0,0,0,0,28,0,0,0,0,28,28,1,0,0,28,0,0,29,0,0,28,1,28,1],"texts":["The"," user"," asked"," me"," to"," remember"," the"," project"," cod","ew","ord"," \"","M","ARM","AL","ADE","\""," and"," now"," they","'re"," asking"," what"," it"," is","."," I"," should"," just"," reply"," with"," that"," word","."]}}
{"type":"assistant/chunk","seq":77,"time":1783352138275,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
@@ -26,7 +26,7 @@
{"type":"assistant/chunk","seq":82,"time":1783352138307,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user asked me to remember the project codeword \"MARMALADE\" and now they're asking what it is. I should just reply with that word."}}}}
{"type":"assistant/chunk","seq":83,"time":1783352138307,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"MARMALADE"}}}}
{"type":"assistant/chunk","seq":84,"time":1783352138307,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":97,"outputTokens":39,"cacheReadTokens":2816,"reasoningTokens":34}}}}
{"type":"assistant/chunk","seq":85,"time":1783352138307,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":86,"time":1783352138308,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user asked me to remember the project codeword \"MARMALADE\" and now they're asking what it is. I should just reply with that word."},{"type":"text","text":"MARMALADE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":97,"outputTokens":39,"cacheReadTokens":2816,"reasoningTokens":34}},"sourceEventSeqs":[42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85],"surfaceOp":"append"}
{"type":"step/end","seq":87,"time":1783352138308,"data":{"turn":2,"step":1}}
{"type":"turn/end","seq":88,"time":1783352138308,"data":{"turn":2,"reason":{"kind":"completed"}}}
{"type":"assistant/chunk","seq":85,"time":1785142305270,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":86,"time":1785142305270,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user asked me to remember the project codeword \"MARMALADE\" and now they're asking what it is. I should just reply with that word."},{"type":"text","text":"MARMALADE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":97,"outputTokens":39,"cacheReadTokens":2816,"reasoningTokens":34}},"sourceEventSeqs":[42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85],"surfaceOp":"append"}
{"type":"step/end","seq":87,"time":1785142305270,"data":{"turn":2,"step":1}}
{"type":"turn/end","seq":88,"time":1785142305270,"data":{"turn":2,"reason":{"kind":"completed"}}}
examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl
+5 -5
View File
@@ -18,7 +18,7 @@
{"type":"turn/start","seq":32,"time":1783352147508,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}}
{"type":"user/message","seq":33,"time":1783352147509,"data":{"content":[{"type":"text","text":"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"step/start","seq":34,"time":1783352147509,"data":{"turn":2,"step":1}}
{"type":"request/header","seq":35,"time":1783352147509,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"resume"}}
{"type":"request/header","seq":35,"time":1785142306299,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"resume"}}
{"type":"assistant/chunk","seq":36,"time":1783352147925,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"reasoning-chunks","seq0":37,"time0":1783352147925,"data":{"turn":2,"step":1,"index":0,"dt":[94,29,1,0,27,0,1,0,0,0,29,0,0,0,35,0,0,0,0,26,29,31,0,30,0,0,27,1,27,0],"texts":["The"," user"," is"," asking"," me"," to"," recall"," the"," project"," cod","ew","ord"," that"," was"," mentioned"," earlier"," in"," the"," conversation","."," I"," was"," told"," to"," remember"," it",":"," SA","FF","RON","."]}}
{"type":"assistant/chunk","seq":68,"time":1783352148313,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
@@ -26,7 +26,7 @@
{"type":"assistant/chunk","seq":72,"time":1783352148345,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user is asking me to recall the project codeword that was mentioned earlier in the conversation. I was told to remember it: SAFFRON."}}}}
{"type":"assistant/chunk","seq":73,"time":1783352148345,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"SAFFRON"}}}}
{"type":"assistant/chunk","seq":74,"time":1783352148345,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":95,"outputTokens":35,"cacheReadTokens":2816,"reasoningTokens":31}}}}
{"type":"assistant/chunk","seq":75,"time":1783352148345,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":76,"time":1783352148345,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user is asking me to recall the project codeword that was mentioned earlier in the conversation. I was told to remember it: SAFFRON."},{"type":"text","text":"SAFFRON"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":95,"outputTokens":35,"cacheReadTokens":2816,"reasoningTokens":31}},"sourceEventSeqs":[36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75],"surfaceOp":"append"}
{"type":"step/end","seq":77,"time":1783352148345,"data":{"turn":2,"step":1}}
{"type":"turn/end","seq":78,"time":1783352148345,"data":{"turn":2,"reason":{"kind":"completed"}}}
{"type":"assistant/chunk","seq":75,"time":1785142306309,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":76,"time":1785142306309,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user is asking me to recall the project codeword that was mentioned earlier in the conversation. I was told to remember it: SAFFRON."},{"type":"text","text":"SAFFRON"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":95,"outputTokens":35,"cacheReadTokens":2816,"reasoningTokens":31}},"sourceEventSeqs":[36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75],"surfaceOp":"append"}
{"type":"step/end","seq":77,"time":1785142306309,"data":{"turn":2,"step":1}}
{"type":"turn/end","seq":78,"time":1785142306309,"data":{"turn":2,"reason":{"kind":"completed"}}}
examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json
+1 -1
View File
@@ -288,7 +288,7 @@
"description": "The COMPLETE task list, replacing any previous list.",
"items": {
"type": "object",
"additionalProperties": true,
"additionalProperties": false,
"properties": {
"content": {
"type": "string",
examples/acp-agent/tests/snapshots/web-fetch/input.json
+7
View File
@@ -0,0 +1,7 @@
{
"steps": [
{ "op": "initialize" },
{ "op": "newSession" },
{ "op": "prompt", "text": "Use the web_fetch tool exactly once to fetch http://127.0.0.1:43117/menu.html, then reply with exactly DONE. Do not describe the content." }
]
}
examples/acp-agent/tests/snapshots/web-fetch/session.jsonl
+31
View File
@@ -0,0 +1,31 @@
{"type":"session","version":0,"id":"c12fa9af-1042-4a92-9ba4-4a968ff23495","createdAt":1785078727712,"cwd":"/tmp/acp-snap-cwd-hqkZWE","delegationDepth":0}
{"type":"turn/start","seq":0,"time":1785078727718,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
{"type":"user/message","seq":1,"time":1785078727719,"data":{"content":[{"type":"text","text":"Use the web_fetch tool exactly once to fetch http://127.0.0.1:43117/menu.html, then reply with exactly DONE. Do not describe the content."}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"session/title","seq":2,"time":1785078727721,"data":{"title":"Use the web_fetch tool exactly","messageSeqs":[1],"source":{"kind":"fallback"}}}
{"type":"step/start","seq":3,"time":1785078727730,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":4,"time":1785078727731,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-pro"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"assistant/chunk","seq":5,"time":1785078728804,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"reasoning-chunks","seq0":6,"time0":1785078728805,"data":{"turn":1,"step":1,"index":0,"dt":[138,46,0,0,1,0,0,48,0,1,0,46,1,0,0,0,0,46,1,0,0,0,0,49,0,1,0,0,0,47,0,0,0,0,1,45,1,0,0,45,1,0,0],"texts":["The"," user"," wants"," me"," to"," use"," the"," web","_f","etch"," tool"," exactly"," once"," to"," fetch"," http","://","127",".","0",".","0",".","1",":","431","17","/m","enu",".html",","," then"," reply"," with"," exactly"," \"","D","ONE","\"."," Let"," me"," do"," that","."]}}
{"type":"assistant/chunk","seq":50,"time":1785078729463,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
{"type":"tool-call-chunks","seq0":51,"time0":1785078729464,"data":{"turn":1,"step":1,"index":1,"dt":[47,0,0,0,0,46,0,0,1,46,0,0,0,0,1,46,1,0,0,0,0,45,1],"id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","args":["","{","\"","url","\"",": ","\"","http","://","127",".","0",".","0",".","1",":","431","17","/m","enu",".html","\"","}"]}}
{"type":"assistant/chunk","seq":75,"time":1785078729803,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use the web_fetch tool exactly once to fetch http://127.0.0.1:43117/menu.html, then reply with exactly \"DONE\". Let me do that."}}}}
{"type":"assistant/chunk","seq":76,"time":1785078729803,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","arguments":"{\"url\": \"http://127.0.0.1:43117/menu.html\"}"}}}}
{"type":"assistant/chunk","seq":77,"time":1785078729803,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":5405,"outputTokens":103,"cacheReadTokens":0,"reasoningTokens":44}}}}
{"type":"assistant/chunk","seq":78,"time":1785078729804,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":79,"time":1785078729807,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the web_fetch tool exactly once to fetch http://127.0.0.1:43117/menu.html, then reply with exactly \"DONE\". Let me do that."},{"type":"tool-call","id":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","arguments":"{\"url\": \"http://127.0.0.1:43117/menu.html\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-pro"},"usage":{"inputTokens":5405,"outputTokens":103,"cacheReadTokens":0,"reasoningTokens":44}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78],"surfaceOp":"append"}
{"type":"tool/call","seq":80,"time":1785078729809,"data":{"turn":1,"step":1,"callId":"call_00_sxjOyfDYN07koiE7jiIa5326","name":"web_fetch","arguments":"{\"url\": \"http://127.0.0.1:43117/menu.html\"}"}}
{"type":"tool/result","seq":81,"time":1785078729843,"data":{"turn":1,"step":1,"callId":"call_00_sxjOyfDYN07koiE7jiIa5326","content":[{"type":"text","text":"Fetched http://127.0.0.1:43117/menu.html (HTTP 200)\n\nMenu\n\n# Café menu\n\nPrices include **service & _tax_** — updated daily.\n\n- Espresso\n- Flat white\n\n| Drink | Price |\n| --- | --- |\n| Espresso | €2 |\n| Flat white | €3 |\n\nSee [today’s specials](https://fixture.invalid/specials)."}],"isError":false},"sourceEventSeqs":[80],"surfaceOp":"append"}
{"type":"step/end","seq":82,"time":1785078729847,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":83,"time":1785078729848,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":84,"time":1785078730611,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"reasoning-chunks","seq0":85,"time0":1785078730612,"data":{"turn":1,"step":2,"index":0,"dt":[158,54,1,0,0,36,1,47,47,46,1,0,0,47,0,0,0,0,1,46,43,1,0,0,48,0,46,0,0,0],"texts":["The"," user"," asked"," me"," to"," fetch"," the"," URL",","," then"," reply"," with"," exactly"," \"","D","ONE","\"."," I","'ve"," fetched"," it","."," Now"," I"," just"," reply"," with"," \"","D","ONE","\"."]}}
{"type":"assistant/chunk","seq":116,"time":1785078731235,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
{"type":"assistant/chunk","seq":117,"time":1785078731236,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}}
{"type":"assistant/chunk","seq":118,"time":1785078731282,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}}
{"type":"assistant/chunk","seq":119,"time":1785078731282,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user asked me to fetch the URL, then reply with exactly \"DONE\". I've fetched it. Now I just reply with \"DONE\"."}}}}
{"type":"assistant/chunk","seq":120,"time":1785078731282,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
{"type":"assistant/chunk","seq":121,"time":1785078731282,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":239,"outputTokens":34,"cacheReadTokens":5376,"reasoningTokens":31}}}}
{"type":"assistant/chunk","seq":122,"time":1785078731282,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":123,"time":1785078731283,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user asked me to fetch the URL, then reply with exactly \"DONE\". I've fetched it. Now I just reply with \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-pro"},"usage":{"inputTokens":239,"outputTokens":34,"cacheReadTokens":5376,"reasoningTokens":31}},"sourceEventSeqs":[84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122],"surfaceOp":"append"}
{"type":"step/end","seq":124,"time":1785078731286,"data":{"turn":1,"step":2}}
{"type":"turn/end","seq":125,"time":1785078731286,"data":{"turn":1,"reason":{"kind":"completed"}}}
examples/acp-agent/tests/snapshots/web-fetch/stdout.expected.jsonl
+4
View File
@@ -0,0 +1,4 @@
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"DONE"}}}}
{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}
examples/acp-agent/tests/snapshots/web-fetch/system-prompt.expected.md
+27
View File
@@ -0,0 +1,27 @@
You are an AI agent powered by the DeepSeek Harness SDK.
You are a coding assistant powered by the deepseek-v4-pro model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug.
Verify your work by running the code or tests. Keep answers brief and factual.
Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.
Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.
Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.
Check the [exit code: N] marker on every bash result; investigate failures before moving on.
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 the web_fetch tool to retrieve the content of a specific HTTP(S) URL (for example a result from web_search). It returns the page content decoded to text. Cite the URL as a markdown link when you use its content.
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`).
<!-- dsh-user-approval-policy:never -->
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.
Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.
examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json
+489
View File
@@ -0,0 +1,489 @@
{
"initial": [
{
"name": "bash",
"description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The bash command to execute."
},
"description": {
"type": "string",
"description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."
},
"timeoutMs": {
"type": "number",
"description": "Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."
},
"workdir": {
"type": "string",
"description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."
},
"run_in_background": {
"type": "boolean",
"description": "Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies."
},
"sandbox_permissions": {
"type": "string",
"description": "The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.",
"enum": [
"workspace-write",
"danger-full-access"
]
},
"justification": {
"type": "string",
"description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."
}
},
"required": [
"command",
"description"
]
}
},
{
"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 limit on automatic continuation rounds."
}
},
"required": [
"objective"
]
}
},
{
"name": "edit",
"description": "Edit an existing UTF-8 text file by replacing literal text.",
"parameters": {
"type": "object",
"properties": {
"file_path": {
"type": "string",
"description": "Path to edit, resolved by the filesystem backend."
},
"old_string": {
"type": "string",
"description": "Literal text to replace. Must match exactly."
},
"new_string": {
"type": "string",
"description": "Literal replacement text. Use an empty string to delete the match."
},
"replace_all": {
"type": "boolean",
"description": "Replace all matches. Defaults to false; when false, old_string must appear exactly once."
},
"sandbox_permissions": {
"type": "string",
"description": "The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.",
"enum": [
"workspace-write",
"danger-full-access"
]
},
"justification": {
"type": "string",
"description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."
}
},
"required": [
"file_path",
"old_string",
"new_string"
]
}
},
{
"name": "get_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": {}
}
},
{
"name": "ralph",
"description": "Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools.",
"parameters": {
"type": "object",
"properties": {
"objective": {
"type": "string",
"description": "The immutable completion objective for every fresh Ralph round."
},
"maxRounds": {
"type": "number",
"description": "Optional positive safe-integer round cap, bounded by the deployment ceiling."
}
},
"required": [
"objective"
]
}
},
{
"name": "read",
"description": "Read a UTF-8 text file and return line-numbered content.",
"parameters": {
"type": "object",
"properties": {
"file_path": {
"type": "string",
"description": "Path to read, resolved by the filesystem backend."
},
"offset": {
"type": "number",
"description": "1-based first line to return. Defaults to 1."
},
"limit": {
"type": "number",
"description": "Maximum number of lines to return. Defaults to 2000."
}
},
"required": [
"file_path"
]
}
},
{
"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.",
"parameters": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "The exact skill name from the available skills list."
}
},
"required": [
"name"
]
}
},
{
"name": "subagent",
"description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.",
"parameters": {
"type": "object",
"properties": {
"description": {
"type": "string",
"description": "A short (3-5 word) description of the delegated task, for display."
},
"prompt": {
"type": "string",
"description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."
},
"run_in_background": {
"type": "boolean",
"description": "Run as a background task and return its id; collect with task_output or stop with task_kill."
}
},
"required": [
"description",
"prompt"
]
}
},
{
"name": "subagent_fork",
"description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.",
"parameters": {
"type": "object",
"properties": {
"description": {
"type": "string",
"description": "A short (3-5 word) description of the delegated task, for display."
},
"prompt": {
"type": "string",
"description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."
},
"run_in_background": {
"type": "boolean",
"description": "Run as a background task and return its id; collect with task_output or stop with task_kill."
}
},
"required": [
"description",
"prompt"
]
}
},
{
"name": "task_kill",
"description": "Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.",
"parameters": {
"type": "object",
"properties": {
"task_id": {
"type": "string",
"description": "Task id returned by the tool that started the background work."
},
"reason": {
"type": "string",
"description": "Optional short reason, recorded in the log and forwarded to the task."
}
},
"required": [
"task_id"
]
}
},
{
"name": "task_list",
"description": "List your background tasks (running and finished) with their ids, kinds, and statuses.",
"parameters": {
"type": "object",
"properties": {}
}
},
{
"name": "task_output",
"description": "Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.",
"parameters": {
"type": "object",
"properties": {
"task_id": {
"type": "string",
"description": "Task id returned by the tool that started the background work."
},
"wait": {
"type": "boolean",
"description": "Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."
},
"timeout_ms": {
"type": "number",
"description": "Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."
}
},
"required": [
"task_id"
]
}
},
{
"name": "todo_write",
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
"parameters": {
"type": "object",
"properties": {
"todos": {
"type": "array",
"description": "The COMPLETE task list, replacing any previous list.",
"items": {
"type": "object",
"additionalProperties": false,
"properties": {
"content": {
"type": "string",
"description": "What the task is — a short imperative line."
},
"status": {
"type": "string",
"description": "pending (not started) | in_progress (now) | completed (done).",
"enum": [
"pending",
"in_progress",
"completed"
]
}
},
"required": [
"content",
"status"
]
}
}
},
"required": [
"todos"
]
}
},
{
"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 and must explain it in blocked_reason.",
"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."
},
"blocked_reason": {
"type": "string",
"description": "Concrete blocking condition; required only with action blocked."
}
},
"required": [
"goal_id",
"revision",
"action"
]
}
},
{
"name": "web_fetch",
"description": "Fetch the content of a specific HTTP(S) URL and return it decoded to text.",
"parameters": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The HTTP(S) URL to fetch."
}
},
"required": [
"url"
]
}
},
{
"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 <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — 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/oneOf — no 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<any[]>` — 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<any[]>` — 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.",
"parameters": {
"type": "object",
"properties": {
"script": {
"type": "string",
"description": "The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."
},
"meta": {
"type": "object",
"description": "The workflow identity block (plain JSON — never code).",
"additionalProperties": true,
"properties": {
"name": {
"type": "string",
"description": "Short kebab-case workflow name."
},
"description": {
"type": "string",
"description": "One-line description of what the workflow does."
},
"whenToUse": {
"type": "string",
"description": "Optional guidance on when this workflow applies."
},
"phases": {
"type": "array",
"description": "Optional phase declarations matched by phase() calls.",
"items": {
"type": "object",
"additionalProperties": true,
"properties": {
"title": {
"type": "string",
"description": "The phase title phase() calls match by exact string."
},
"detail": {
"type": "string",
"description": "Optional one-line description of the phase."
},
"provider": {
"type": "string",
"description": "Optional provider override this phase is expected to use."
},
"model": {
"type": "string",
"description": "Optional model override this phase is expected to use."
}
},
"required": [
"title"
]
}
}
},
"required": [
"name",
"description"
]
},
"args": {
"type": "object",
"description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).",
"additionalProperties": true
}
},
"required": [
"script",
"meta"
]
}
},
{
"name": "write",
"description": "Create or fully replace a UTF-8 text file.",
"parameters": {
"type": "object",
"properties": {
"file_path": {
"type": "string",
"description": "Path to write, resolved by the filesystem backend."
},
"content": {
"type": "string",
"description": "Full UTF-8 text content to write."
},
"sandbox_permissions": {
"type": "string",
"description": "The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.",
"enum": [
"workspace-write",
"danger-full-access"
]
},
"justification": {
"type": "string",
"description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."
}
},
"required": [
"file_path",
"content"
]
}
}
],
"changes": []
}
examples/acp-agent/tests/snapshots/workspace-context/session.jsonl
+22 -21
View File
@@ -2,24 +2,25 @@
{"type":"turn/start","seq":0,"time":1783778297065,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
{"type":"user/message","seq":1,"time":1783778297066,"data":{"content":[{"type":"text","text":"Read nested/task.txt with the read tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"session/title","seq":2,"time":1783778297066,"data":{"title":"Read nested/task.txt with the read","messageSeqs":[1],"source":{"kind":"fallback"}}}
{"type":"step/start","seq":3,"time":1783778297069,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":4,"time":1783778297070,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":[{"role":"user","content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nRoot snapshot instruction.\n\n</system-reminder>"}]}]},"reason":"initial"}}
{"type":"assistant/chunk","seq":5,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":6,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_workspace_read","name":"read","argumentsDelta":"{\"file_path\":\"nested/task.txt\"}"}}}
{"type":"assistant/chunk","seq":7,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}}}}
{"type":"assistant/chunk","seq":8,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"type":"assistant/chunk","seq":9,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":10,"time":1783778297070,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}
{"type":"tool/call","seq":11,"time":1783778297070,"data":{"turn":1,"step":1,"callId":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}}
{"type":"tool/result","seq":12,"time":1783778297072,"data":{"turn":1,"step":1,"callId":"call_workspace_read","content":[{"type":"text","text":"<path>{{cwd}}/nested/task.txt</path>\n<type>file</type>\n<content>\n1: snapshot task\n\n(End of file - total 1 lines)\n</content>"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"}
{"type":"user/message","seq":13,"time":1783778297072,"data":{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nNested snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"workspace-context"},"meta":{"kind":"workspace-instructions","version":1,"changes":[{"action":"set","scope":"nested\u0000AGENTS.md","path":"nested/AGENTS.md","digest":"c446df9a85c7e73a3055f394a4822a19ac9ead5a"}]}},"surfaceOp":"append"}
{"type":"step/end","seq":14,"time":1783778297072,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":15,"time":1783778297072,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":16,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":17,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"DONE"}}}
{"type":"assistant/chunk","seq":18,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}}
{"type":"assistant/chunk","seq":19,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":2}}}}
{"type":"assistant/chunk","seq":20,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":21,"time":1783778297073,"data":{"turn":1,"step":2,"content":[{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":2}},"sourceEventSeqs":[16,17,18,19,20],"surfaceOp":"append"}
{"type":"step/end","seq":22,"time":1783778297073,"data":{"turn":1,"step":2}}
{"type":"turn/end","seq":23,"time":1783778297073,"data":{"turn":1,"reason":{"kind":"completed"}}}
{"type":"user/message","seq":3,"time":1784903339799,"data":{"content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nRoot snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","baseline":true,"changes":[{"action":"set","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"2e18766c26603608f321508caae00ea8f4434d59"}]}},"surfaceOp":"append"}
{"type":"step/start","seq":4,"time":1784903339799,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":5,"time":1784903339800,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"assistant/chunk","seq":6,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":7,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_workspace_read","name":"read","argumentsDelta":"{\"file_path\":\"nested/task.txt\"}"}}}
{"type":"assistant/chunk","seq":8,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}}}}
{"type":"assistant/chunk","seq":9,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"type":"assistant/chunk","seq":10,"time":1784903339801,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":11,"time":1784903339801,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[6,7,8,9,10],"surfaceOp":"append"}
{"type":"tool/call","seq":12,"time":1784903339802,"data":{"turn":1,"step":1,"callId":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}}
{"type":"tool/result","seq":13,"time":1784903339813,"data":{"turn":1,"step":1,"callId":"call_workspace_read","content":[{"type":"text","text":"<path>{{cwd}}/nested/task.txt</path>\n<type>file</type>\n<content>\n1: snapshot task\n\n(End of file - total 1 lines)\n</content>"}],"isError":false},"sourceEventSeqs":[12],"surfaceOp":"append"}
{"type":"user/message","seq":14,"time":1784903339813,"data":{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nNested snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","changes":[{"action":"set","scope":"nested\u0000AGENTS.md","path":"nested/AGENTS.md","digest":"c446df9a85c7e73a3055f394a4822a19ac9ead5a"}]}},"surfaceOp":"append"}
{"type":"step/end","seq":15,"time":1784903339813,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":16,"time":1784903339820,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":17,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":18,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"DONE"}}}
{"type":"assistant/chunk","seq":19,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}}
{"type":"assistant/chunk","seq":20,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":2}}}}
{"type":"assistant/chunk","seq":21,"time":1784903339821,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":22,"time":1784903339821,"data":{"turn":1,"step":2,"content":[{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":2}},"sourceEventSeqs":[17,18,19,20,21],"surfaceOp":"append"}
{"type":"step/end","seq":23,"time":1784903339821,"data":{"turn":1,"step":2}}
{"type":"turn/end","seq":24,"time":1784903339822,"data":{"turn":1,"reason":{"kind":"completed"}}}
examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json
+1 -1
View File
@@ -288,7 +288,7 @@
"description": "The COMPLETE task list, replacing any previous list.",
"items": {
"type": "object",
"additionalProperties": true,
"additionalProperties": false,
"properties": {
"content": {
"type": "string",
examples/acp-agent/web-fetch-fixture-server.mjs
+55
View File
@@ -0,0 +1,55 @@
/**
* Deterministic loopback HTTP fixture for the web-fetch snapshot scenario: a
* small HTML page (headings, named entities, a GFM table, nested formatting)
* on a fixed port, so recording and keyless replay drive the REAL
* `dsh-web-fetch-local` transport and `dsh-tool-web` markdown rendering
* without external network. The port is fixed because the fetched URL is part
* of the recorded model transcript.
*/
import { createServer } from 'node:http'
/** Fixed loopback port the scenario prompt points `web_fetch` at. */
const PORT = 43117
const PAGE = `<!doctype html>
<html><head><title>Menu</title><style>.x{color:red}</style><script>ignored()</script></head>
<body>
<h1>Caf&eacute; menu</h1>
<p>Prices include <strong>service &amp; <em>tax</em></strong> &mdash; updated daily.</p>
<ul><li>Espresso</li><li>Flat white</li></ul>
<table><thead><tr><th>Drink</th><th>Price</th></tr></thead><tbody><tr><td>Espresso</td><td>&euro;2</td></tr><tr><td>Flat white</td><td>&euro;3</td></tr></tbody></table>
<p>See <a href="https://fixture.invalid/specials">today&rsquo;s specials</a>.</p>
</body></html>
`
/** Cordis plugin name. */
export const name = 'web-fetch-fixture-server'
/**
* Start the fixture server on 127.0.0.1 and register its shutdown.
* @param ctx - Cordis context; the effect disposes the server with the fiber.
*/
export async function apply(ctx) {
const server = createServer((req, res) => {
if (req.url === '/menu.html') {
res.writeHead(200, { 'content-type': 'text/html; charset=utf-8' })
res.end(PAGE)
return
}
res.writeHead(404, { 'content-type': 'text/plain; charset=utf-8' })
res.end('not found')
})
await new Promise((resolve, reject) => {
server.once('error', reject)
server.listen(PORT, '127.0.0.1', () => resolve(undefined))
})
// The fixture must never hold the process open past protocol shutdown.
server.unref()
ctx.effect(() => async () => {
await new Promise((resolve, reject) => {
server.close(error => error ? reject(error) : resolve(undefined))
// Stop accepting first so a connection cannot arrive after the forced close.
server.closeAllConnections()
})
}, 'web-fetch-fixture-server')
}
examples/acp-agent/web.cordis.snapshot.yml
+31
View File
@@ -0,0 +1,31 @@
# Keyless replay counterpart to web.cordis.yml: the web stack and loopback
# fixture server stay real (the tool call re-executes the actual HTTP fetch and
# markdown rendering); only the model adapter is replaced by replay.
- id: base
name: '@cordisjs/plugin-include'
config:
path: ./cordis.yml
patches:
- id: llm-deepseek
name: '@deepseek-ai/dsh-llm-deepseek'
disabled: true
- insert:
- id: web
name: '@deepseek-ai/dsh-web'
- id: web-fetch-local
name: '@deepseek-ai/dsh-web-fetch-local'
- id: web-fetch-fixture
name: './web-fetch-fixture-server.mjs'
- id: tool-web
name: '@deepseek-ai/dsh-tool-web'
config:
search: false
- id: llm-replay
name: '@deepseek-ai/dsh-llm-replay'
config:
providers:
- id: deepseek
name: DeepSeek
models:
- id: deepseek-v4-flash
- id: deepseek-v4-pro
examples/acp-agent/web.cordis.yml
+21
View File
@@ -0,0 +1,21 @@
# Web-fetch composition for the web-fetch snapshot scenario: the web seam, the
# real local HTTP fetch provider, the model-facing web tools (fetch only, so
# the pinned header carries exactly the surface under test), and the loopback
# fixture server the scenario prompt fetches — deterministic content, no
# external network, in recording and replay alike.
- id: base
name: '@cordisjs/plugin-include'
config:
path: ./cordis.yml
patches:
- insert:
- id: web
name: '@deepseek-ai/dsh-web'
- id: web-fetch-local
name: '@deepseek-ai/dsh-web-fetch-local'
- id: web-fetch-fixture
name: './web-fetch-fixture-server.mjs'
- id: tool-web
name: '@deepseek-ai/dsh-tool-web'
config:
search: false
examples/cordis-agent/README.i18n.yaml
+3 -3
View File
@@ -1,6 +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
README.md: 1309fe9b2935d3224f097ceb2e80501c8075a933
README.zh.md: 2e3e7d7206d0d676ae7d9c9b3a2c2f8be26aafe7
# pnpm run verify-translation-pairing --write examples/cordis-agent/README.md
README.md: 55970e932bc16d8361932daa9ea55af83ef73d33
README.zh.md: c2873b6de96a8b47ad8ea4fb2cf03a7501406300
examples/cordis-agent/README.md
+10 -8
View File
@@ -2,7 +2,7 @@
English | [中文](README.zh.md)
The self-referential harness demo: the DeepSeek V4 coding spine on the full-screen TUI plus [`@deepseek-ai/dsh-tool-cordis`](../../packages/cordis/tool-cordis/README.md), which hands the model three tools over the **live cordis runtime it is running inside** — inspect it, mount new plugins into it, and dispose them again. The `ctx.fs` and `ctx.web` services are mounted (provider-only, no model-facing file/web tools) so the plugins the agent writes have real capabilities to build on; Node built-ins are trapped in the sandbox and redirect to those services. The design (sandbox semantics, mount lifecycle, cross-mount composition, caveats) lives in [the toolset Agent Note](../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md).
The self-referential harness demo: the DeepSeek V4 coding spine on the full-screen TUI plus [`@deepseek-ai/dsh-tool-cordis`](../../packages/cordis/tool-cordis/README.md), which lets the model inspect the current DSH process, mount in-memory temporary Plugins, and unmount them. Temporary Plugins remain active across turns but disappear on unmount, toolset unload, or DSH restart; they create no files or configuration and may affect other sessions in the process. The `ctx.fs` and `ctx.web` services are provider-only capabilities available to those Plugins. The design lives in [the toolset Agent Note](../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md).
## Run it
@@ -10,26 +10,28 @@ The self-referential harness demo: the DeepSeek V4 coding spine on the full-scre
# repo root .env (gitignored) or exported env:
# DEEPSEEK_API_KEY=sk-…
# DEEPSEEK_BASE_URL=https://… # optional; defaults to the public API
pnpm run demo:cordis
pnpm run demo:cordis # TUI (default)
pnpm run demo:cordis web # browser UI at http://127.0.0.1:3081
pnpm run demo:cordis acp # ACP server
```
The intended demo is staged — verify the listener link first, then let the agent extend itself:
```
> Mount a plugin that listens to the 'agent/status' event and logs every status change, then run `echo hi` with bash.
> Mount a temporary Plugin that listens to the 'agent/status' event and logs every status change, then run `echo hi` with bash.
[tool call] cordis_mount({"code": "return { name: 'status-logger', apply(ctx) { ctx.on('agent/status', (agent, status) => console.log('status →', status)) } }"})
[tool result] mounted dyn-1 (plugin "status-logger", state: active)
[tool result] Temporary Plugin dyn-1 is running (plugin "status-logger"; available until unmounted or DSH restarts).
[tool call] bash({"command": "echo hi"})
[cordis:dyn-1] status → … ← the mounted listener firing, live
[cordis:dyn-1] status → … ← the temporary listener firing, live
> Now give yourself a reverse_text tool and use it on "harness".
[tool call] cordis_mount({"code": "return { name: 'reverse-text', inject: ['tools'], apply(ctx) { ctx.tools.register(harness.defineTool({ name: 'reverse_text', … })) } }"})
[tool call] reverse_text({"text": "harness"}) ← a tool the agent built for itself, one step earlier
> Unmount both.
> Unmount both temporary Plugins.
[tool call] cordis_unmount({"id": "dyn-1"})
```
Ask for `cordis_inspect` with `what: "api"` or `what: "events"` to see the generated service/event reference the agent writes plugin code against, and try two cooperating mounts (`ctx.provide` in one, `inject` in the other) to watch cordis park and revive the consumer.
Ask for `cordis_inspect` with `what: "api"` or `what: "events"` to see the generated service/event reference used to write Plugin code, and mount two cooperating temporary Plugins (`ctx.provide` in one, `inject` in the other) to watch Cordis park and revive the consumer.
## End-to-end tests
`tests/keyless-smoke.e2e.ts` boots the real `cordis.yml` through the Loader with a dummy key and asserts the banner, package-name resolution, and clean EOF exit. `tests/cordis-tools.e2e.ts` is the with-key smoke: a real model mounts a status listener and the test verifies its tagged console line, creates and uses a `reverse_text` tool, and composes two mounts through provide/inject. [`packages/cordis/tool-cordis`](../../packages/cordis/tool-cordis) carries the unit coverage under the per-file 100% gate.
`tests/keyless-smoke.e2e.ts` boots the real `cordis.yml` through the Loader with a dummy key and asserts the banner, package-name resolution, and clean EOF exit. `tests/cordis-tools.e2e.ts` is the with-key smoke: a real model mounts a temporary status listener and the test verifies its tagged console line, creates and uses a `reverse_text` tool, and composes two temporary Plugins through provide/inject. [`packages/cordis/tool-cordis`](../../packages/cordis/tool-cordis) carries the unit coverage under the per-file 100% gate.
examples/cordis-agent/README.zh.md
+10 -8
View File
@@ -2,7 +2,7 @@
[English](README.md) | 中文
自指 harness 演示：在全屏 TUI 上运行 DeepSeek V4 编码主干，并加载 [`@deepseek-ai/dsh-tool-cordis`](../../packages/cordis/tool-cordis/README.md)。后者通过 agent（智能体）所在的 **实时 cordis 运行时** 向模型提供三个工具：检查运行时、将新插件挂载到其中，以及再次释放它们。`ctx.fs` 和 `ctx.web` 服务也会挂载（仅作为提供方，不包含面向模型的文件／Web 工具），使 agent 编写的插件可以构建于真实能力之上；Node 内置模块在沙箱中被截获并重定向到这些服务。设计（沙箱语义、挂载生命周期、跨挂载组合、注意事项）详见[工具集 Agent Note](../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)。
自指 harness 演示：在全屏 TUI 上运行 DeepSeek V4 编码主干，并加载 [`@deepseek-ai/dsh-tool-cordis`](../../packages/cordis/tool-cordis/README.md)。后者让模型检查当前 DSH 进程、挂载仅存于内存的临时 Plugin，并再次卸载它们。临时 Plugin 可跨 turn 保持活跃，但会在卸载、工具集卸载或 DSH 重启后消失；它们不创建文件或配置，也可能影响同一进程中的其他 session。`ctx.fs` 和 `ctx.web` 是这些 Plugin 可用的 provider-only 能力。设计详见[工具集 Agent Note](../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)。
## 运行
@@ -10,26 +10,28 @@
# repo root .env (gitignored) or exported env:
# DEEPSEEK_API_KEY=sk-…
# DEEPSEEK_BASE_URL=https://… # optional; defaults to the public API
pnpm run demo:cordis
pnpm run demo:cordis # TUI (default)
pnpm run demo:cordis web # browser UI at http://127.0.0.1:3081
pnpm run demo:cordis acp # ACP server
```
预期演示分阶段进行：先验证监听器链接，再让 agent 扩展自身：
```
> Mount a plugin that listens to the 'agent/status' event and logs every status change, then run `echo hi` with bash.
> Mount a temporary Plugin that listens to the 'agent/status' event and logs every status change, then run `echo hi` with bash.
[tool call] cordis_mount({"code": "return { name: 'status-logger', apply(ctx) { ctx.on('agent/status', (agent, status) => console.log('status →', status)) } }"})
[tool result] mounted dyn-1 (plugin "status-logger", state: active)
[tool result] Temporary Plugin dyn-1 is running (plugin "status-logger"; available until unmounted or DSH restarts).
[tool call] bash({"command": "echo hi"})
[cordis:dyn-1] status → … ← the mounted listener firing, live
[cordis:dyn-1] status → … ← the temporary listener firing, live
> Now give yourself a reverse_text tool and use it on "harness".
[tool call] cordis_mount({"code": "return { name: 'reverse-text', inject: ['tools'], apply(ctx) { ctx.tools.register(harness.defineTool({ name: 'reverse_text', … })) } }"})
[tool call] reverse_text({"text": "harness"}) ← a tool the agent built for itself, one step earlier
> Unmount both.
> Unmount both temporary Plugins.
[tool call] cordis_unmount({"id": "dyn-1"})
```
请求 `cordis_inspect` 并使用 `what: "api"` 或 `what: "events"`，即可查看为 agent 生成、供其编写插件时参考的服务／事件资料。还可尝试两个协作挂载（一个中调用 `ctx.provide`，另一个中使用 `inject`），观察 cordis 如何暂停并恢复消费方。
请求 `cordis_inspect` 并使用 `what: "api"` 或 `what: "events"`，即可查看编写 Plugin 代码所用的生成服务／事件资料。还可挂载两个协作临时 Plugin（一个中调用 `ctx.provide`，另一个中使用 `inject`），观察 Cordis 如何暂停并恢复消费方。
## 端到端测试
`tests/keyless-smoke.e2e.ts` 使用虚拟密钥通过 Loader 启动真实 `cordis.yml`，并断言横幅、包名解析和 EOF 后干净退出。`tests/cordis-tools.e2e.ts` 是带密钥的冒烟测试：真实模型挂载状态监听器，测试验证其带标记的 console 行；然后创建并使用 `reverse_text` 工具，再通过 provide/inject 组合两个挂载。[`packages/cordis/tool-cordis`](../../packages/cordis/tool-cordis) 在每文件 100% 覆盖率门禁下承载单元覆盖。
`tests/keyless-smoke.e2e.ts` 使用虚拟密钥通过 Loader 启动真实 `cordis.yml`，并断言横幅、包名解析和 EOF 后干净退出。`tests/cordis-tools.e2e.ts` 是带密钥的冒烟测试：真实模型挂载一个临时状态 listener，测试验证其带标记的 console 行；然后创建并使用 `reverse_text` 工具，再通过 provide/inject 组合两个临时 Plugin。[`packages/cordis/tool-cordis`](../../packages/cordis/tool-cordis) 在每文件 100% 覆盖率门禁下承载单元覆盖。
examples/cordis-agent/composition.md
+4 -1
View File
@@ -3,7 +3,7 @@
# Cordis Agent App Composition
The self-referential demo puts @deepseek-ai/dsh-tool-cordis on the coding spine, letting the agent inspect its own runtime and mount/unmount plugins into it.
The self-referential demo puts @deepseek-ai/dsh-tool-cordis on the coding spine, letting the agent inspect its current-process runtime and mount or unmount in-memory temporary Plugins.
```mermaid
flowchart LR
@@ -12,6 +12,8 @@ flowchart LR
cfg --> plugin_cordis_hmr
plugin_cordis_llm_deepseek["llm-deepseek<br/>@deepseek-ai/dsh-llm-deepseek"]
cfg --> plugin_cordis_llm_deepseek
plugin_cordis_subprocess["subprocess<br/>@deepseek-ai/dsh-subprocess-local"]
cfg --> plugin_cordis_subprocess
plugin_cordis_bash["bash<br/>@deepseek-ai/dsh-bash-local"]
cfg --> plugin_cordis_bash
plugin_cordis_fs_local["fs-local<br/>@deepseek-ai/dsh-fs-local"]
@@ -39,6 +41,7 @@ flowchart LR
| --- | --- |
| `hmr` | `@cordisjs/plugin-hmr` |
| `llm-deepseek` | `@deepseek-ai/dsh-llm-deepseek` |
| `subprocess` | `@deepseek-ai/dsh-subprocess-local` |
| `bash` | `@deepseek-ai/dsh-bash-local` |
| `fs-local` | `@deepseek-ai/dsh-fs-local` |
| `web` | `@deepseek-ai/dsh-web` |
examples/cordis-agent/cordis.yml
+13 -7
View File
@@ -1,9 +1,9 @@
# Self-referential TUI demo: the coding spine plus tools to inspect the live
# service/plugin/tool/mount/API/event state, mount a model-written plugin under
# `cordis-dynamic`, and quiescently unmount it. The app bin loads the gitignored
# service/plugin/tool/temporary/API/event state, mount a model-written temporary
# Plugin, and quiescently unmount it. The app bin loads the gitignored
# root `.env` before reading the required DeepSeek key and optional base URL.
# Trust stance: the vm and context façade limit accidental global/framework
# access but are not a security boundary; mounted code can reach live capabilities
# access but are not a security boundary; temporary Plugin code reaches live capabilities
# such as `ctx.bash`. Grant this toolset like bash access. See
# ../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md.
@@ -25,6 +25,10 @@
# Local bash executor for agent-spine-demo's tool-bash schema — gives the agent an
# ordinary tool whose calls make the mounted listeners observably fire.
# Managed child-process groups for the bash executor (spawn/kill/output plumbing).
- id: subprocess
name: '@deepseek-ai/dsh-subprocess-local'
- id: bash
name: '@deepseek-ai/dsh-bash-local'
config:
@@ -60,7 +64,7 @@
persistenceRoot: './.sessions'
workspaceContext:
maxBytes: 65536
welcome: 'cordis-agent ready. Ask it to inspect its runtime, mount a listener, or invent a tool for itself.'
welcome: 'cordis-agent ready. Ask it to inspect its runtime, mount a temporary listener, or invent a temporary tool for itself.'
persona: |
You are cordis-agent, a self-referential harness demo powered by the
{{model}} model.
@@ -68,9 +72,11 @@
You run INSIDE a cordis plugin runtime, and your cordis_* tools operate
on that live runtime: cordis_inspect to look around (its `api` and
`events` sections document the service methods, type shapes, and events
your plugin code can use), cordis_mount to add a plugin (an event
listener, a brand-new tool for yourself, or a service other mounts
inject), cordis_unmount to clean one up. In mounted code, NEVER use Node
your Plugin code can use), cordis_mount to mount an in-memory temporary
Plugin (an event listener, a brand-new tool for yourself, or a service
another temporary Plugin injects), cordis_unmount to clean one up. These
Plugins remain across turns but disappear on unmount, toolset unload, or
DSH restart and may affect other sessions in this process. In Plugin code, NEVER use Node
built-ins (require/setTimeout/fetch) — use the runtime's cordis services
via inject: fs, web, bash, and timer (ctx.setTimeout). Prefer small
single-purpose plugins, prefer plain notification events over waterfall
examples/cordis-agent/tests/cordis-tools.e2e.ts
+19 -19
View File
@@ -37,16 +37,16 @@ function resultText(result: { content: { type: string; text?: string }[] }): str
}
describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modifies its own runtime', () => {
it('mounts a status listener whose tagged output actually fires, then unmounts it', async () => {
it('mounts a temporary status listener whose tagged output actually fires, then unmounts it', async () => {
ctx = await cordisHarness()
const log = vi.spyOn(console, 'log').mockImplementation(() => {})
const agent = ctx.agentLoop.create(SessionId('cordis-e2e-listener'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.followup([{
agent.followup({ content: [{
type: 'text',
text: 'Use cordis_mount to mount a plugin that listens to the \'agent/status\' '
+ 'cordis event and logs every change with console.log. Reply "mounted" once done.',
}])
text: 'Use cordis_mount to create a temporary Plugin that listens to the \'agent/status\' '
+ 'Cordis event and logs every change with console.log. Reply "running" once done.',
}], source: { kind: 'user' } })
await waitForIdle(ctx, agent)
// The WORLD check: the turn's own running→idle transition must have driven
@@ -54,32 +54,32 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
expect(taggedCalls(log).length).toBeGreaterThan(0)
const mid = await ctx.tools.execute({
signal: testToolSignal,
callId: CallId('verify-mounted'), name: 'cordis_inspect', arguments: { what: 'dynamic' },
callId: CallId('verify-mounted'), name: 'cordis_inspect', arguments: { what: 'temporary' },
})
expect(resultText(mid)).toContain('dyn-')
agent.followup([{ type: 'text', text: 'Now unmount the plugin you just mounted.' }])
agent.followup({ content: [{ type: 'text', text: 'Now unmount the temporary Plugin you just mounted.' }], source: { kind: 'user' } })
await waitForIdle(ctx, agent)
const after = await ctx.tools.execute({
signal: testToolSignal,
callId: CallId('verify-unmounted'), name: 'cordis_inspect', arguments: { what: 'dynamic' },
callId: CallId('verify-unmounted'), name: 'cordis_inspect', arguments: { what: 'temporary' },
})
expect(resultText(after)).toContain('(no dynamic plugins mounted)')
expect(resultText(after)).toContain('No temporary Plugins are running.')
}, 120_000)
it('builds itself a reverse_text tool and actually calls it', async () => {
ctx = await cordisHarness()
const agent = ctx.agentLoop.create(SessionId('cordis-e2e-selftool'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.followup([{
agent.followup({ content: [{
type: 'text',
text: 'Give yourself a new tool: use cordis_mount to mount a plugin with '
text: 'Give yourself a new tool: use cordis_mount to create a temporary Plugin with '
+ 'inject ["tools"] that calls harness.registerTool(ctx, harness.defineTool({...})) '
+ 'to register a tool named reverse_text with one required string parameter '
+ '"text", returning the text reversed. Then CALL reverse_text with the '
+ 'exact text "harness" and report its exact output.',
}])
}], source: { kind: 'user' } })
await waitForIdle(ctx, agent)
// World checks: the tool exists in the registry, was invoked as a real tool call, and its
@@ -115,19 +115,19 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
).toBe(true)
}, 120_000)
it('composes two mounts through provide/inject, and unmounting the provider parks the consumer', async () => {
it('composes two temporary Plugins through provide/inject, and unmounting the provider parks the consumer', async () => {
ctx = await cordisHarness()
const agent = ctx.agentLoop.create(SessionId('cordis-e2e-compose'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.followup([{
agent.followup({ content: [{
type: 'text',
text: 'Mount TWO separate plugins with cordis_mount. First a provider: apply calls '
text: 'Mount TWO separate temporary Plugins with cordis_mount. First a provider: apply calls '
+ 'ctx.provide(\'shouter\', { shout: (s) => s.toUpperCase() }). Second a consumer with '
+ 'inject ["shouter", "tools"] that registers (via harness.registerTool + harness.defineTool) '
+ 'a tool named shout_text with one required string parameter "text" whose execute returns '
+ 'ctx.shouter.shout(args.text) as a text content block. Then CALL shout_text with "quiet" '
+ 'and report the exact output.',
}])
}], source: { kind: 'user' } })
await waitForIdle(ctx, agent)
// World checks: the service is really in the store, the tool really ran.
@@ -144,16 +144,16 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
.flatMap(event => event.data.content.filter(block => block.type === 'text').map(block => block.text))
expect(shoutResults.some(text => text.includes('QUIET'))).toBe(true)
agent.followup([{ type: 'text', text: 'Now unmount ONLY the provider plugin (the one that provided shouter).' }])
agent.followup({ content: [{ type: 'text', text: 'Now unmount ONLY the provider temporary Plugin (the one that provided shouter).' }], source: { kind: 'user' } })
await waitForIdle(ctx, agent)
// The consumer must have been parked by cordis itself: service gone,
// dependent tool unregistered, dynamic table naming the missing service.
// dependent tool unregistered, temporary section naming the missing service.
expect(ctx.get('shouter')).toBeUndefined()
expect(ctx.tools.get('shout_text')).toBeUndefined()
const after = await ctx.tools.execute({
signal: testToolSignal,
callId: CallId('verify-parked'), name: 'cordis_inspect', arguments: { what: 'dynamic' },
callId: CallId('verify-parked'), name: 'cordis_inspect', arguments: { what: 'temporary' },
})
expect(resultText(after)).toContain('waiting for: shouter')
}, 120_000)
examples/cordis-agent/tests/harness.ts
+2 -2
View File
@@ -15,8 +15,8 @@ import * as ToolCordis from '@deepseek-ai/dsh-tool-cordis'
const PERSONA = 'You are cordis-agent, a self-referential harness demo. '
+ 'Your cordis_* tools operate on the live cordis runtime you run inside: '
+ 'cordis_inspect to look around, cordis_mount to add a plugin, cordis_unmount '
+ 'to clean one up. Follow the tool descriptions exactly and report results briefly.'
+ 'cordis_inspect to look around, cordis_mount to mount a temporary Plugin, cordis_unmount '
+ 'to unmount one. Follow the tool descriptions exactly and report results briefly.'
export async function cordisHarness(): Promise<Context> {
const ctx = new Context()
examples/headless-agent/composition.md
+3
View File
@@ -10,6 +10,8 @@ flowchart LR
cfg["examples/headless-agent<br/>cordis.yml"]
plugin_headless_llm_deepseek["llm-deepseek<br/>@deepseek-ai/dsh-llm-deepseek"]
cfg --> plugin_headless_llm_deepseek
plugin_headless_subprocess["subprocess<br/>@deepseek-ai/dsh-subprocess-local"]
cfg --> plugin_headless_subprocess
plugin_headless_bash["bash<br/>@deepseek-ai/dsh-bash-local"]
cfg --> plugin_headless_bash
plugin_headless_cli_agent["cli-agent<br/>@deepseek-ai/dsh-cli-demo"]
@@ -54,6 +56,7 @@ flowchart LR
| Plugin id | Package / module |
| --- | --- |
| `llm-deepseek` | `@deepseek-ai/dsh-llm-deepseek` |
| `subprocess` | `@deepseek-ai/dsh-subprocess-local` |
| `bash` | `@deepseek-ai/dsh-bash-local` |
| `cli-agent` | `@deepseek-ai/dsh-cli-demo` |
| `token-meter` | `@deepseek-ai/dsh-token-meter` |
examples/headless-agent/cordis.yml
+4
View File
@@ -19,6 +19,10 @@
- id: deepseek-v4-flash
contextWindow: 128000
# Managed child-process groups for the bash executor (spawn/kill/output plumbing).
- id: subprocess
name: '@deepseek-ai/dsh-subprocess-local'
- id: bash
name: '@deepseek-ai/dsh-bash-local'
config:
examples/headless-agent/goal.cordis.snapshot.yml
+8 -2
View File
@@ -1,12 +1,18 @@
# Replay counterpart to goal.cordis.yml; only the live model is replaced.
# Replay counterpart to goal.cordis.yml. It includes cordis.yml directly because
# a config patch cannot target an entry behind a nested include, then restates
# the goal overlay while replacing the live model with keyless replay.
- id: base
name: '@cordisjs/plugin-include'
config:
path: ./goal.cordis.yml
path: ./cordis.yml
patches:
- id: llm-deepseek
name: '@deepseek-ai/dsh-llm-deepseek'
disabled: true
- insert:
- id: goal
name: '@deepseek-ai/dsh-goal'
- id: tool-goal
name: '@deepseek-ai/dsh-tool-goal'
- id: llm-replay
name: '@deepseek-ai/dsh-llm-replay'
examples/headless-agent/retry.cordis.snapshot.yml
+12
View File
@@ -0,0 +1,12 @@
# Keyless provider-retry composition for the headless stream-json snapshot.
- id: base
name: '@cordisjs/plugin-include'
config:
path: ./cordis.yml
patches:
- id: llm-deepseek
name: '@deepseek-ai/dsh-llm-deepseek'
disabled: true
- insert:
- id: retry-snapshot-backend
name: './tests/fixtures/retry-snapshot-backend.mjs'
examples/headless-agent/semantic-checkpoint.cordis.snapshot.yml
+4
View File
@@ -17,6 +17,10 @@
file: !!js process.env.DSH_SNAPSHOT_FILE
overrideFile: !!js process.env.DSH_SNAPSHOT_OVERRIDE
# Managed child-process groups for the bash executor (spawn/kill/output plumbing).
- id: subprocess
name: '@deepseek-ai/dsh-subprocess-local'
- id: bash
name: '@deepseek-ai/dsh-bash-local'
config:
examples/headless-agent/tests/code-mode.e2e.ts
+14 -15
View File
@@ -13,6 +13,7 @@ import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
import LocalSubprocessService from '@deepseek-ai/dsh-subprocess-local'
import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
import { WorkerCodeRuntime } from '@deepseek-ai/dsh-code-runtime-worker'
@@ -55,6 +56,7 @@ async function codeModeHarness(cwd: string): Promise<Context> {
await harness.plugin(AgentRegistry)
await harness.plugin(AgentLoop, { agents: [] })
await harness.plugin(LlmDeepSeek)
await harness.plugin(LocalSubprocessService)
await harness.plugin(LocalBashExecutor, { cwd, timeoutMs: 30_000 })
await harness.plugin(ToolBash)
await harness.plugin(WorkerCodeRuntime, {})
@@ -114,6 +116,7 @@ async function backgroundCodeModeHarness(cwd: string): Promise<Context> {
const harness = await typedCodeModeHarness()
await harness.plugin(LocalTaskService)
await harness.plugin(ToolTasks, {})
await harness.plugin(LocalSubprocessService)
await harness.plugin(LocalBashExecutor, { cwd, timeoutMs: 30_000 })
await harness.plugin(ToolBash)
return harness
@@ -248,7 +251,7 @@ describe('Code Mode typed values: keyless real-worker contracts', () => {
expect(ctx.tasks.list()).toEqual([])
}, 15_000)
it('uses cordis_mount DTO ids directly for active and pending mounts, then confirms removal', async () => {
it('uses cordis_mount DTO ids directly for running and pending temporary Plugins, then confirms removal', async () => {
ctx = await typedCodeModeHarness()
await ctx.plugin(ToolCordis)
@@ -259,14 +262,14 @@ describe('Code Mode typed values: keyless real-worker contracts', () => {
const pending = await tools.cordis_mount({
code: "return { name: 'pending-code-mode-plugin', inject: ['missing-code-mode-service'], apply(ctx) {} }",
});
const before = await tools.cordis_inspect({ what: 'dynamic' });
const unmounted = await tools.cordis_unmount({ id: active.id });
const after = await tools.cordis_inspect({ what: 'dynamic' });
const before = await tools.cordis_inspect({ what: 'temporary' });
const stopped = await tools.cordis_unmount({ id: active.id });
const after = await tools.cordis_inspect({ what: 'temporary' });
await tools.cordis_unmount({ id: pending.id });
return {
active,
pending,
unmounted,
stopped,
beforeContainsId: before.includes(active.id),
afterContainsId: after.includes(active.id),
};
@@ -287,7 +290,7 @@ describe('Code Mode typed values: keyless real-worker contracts', () => {
provides: [],
waitingFor: ['missing-code-mode-service'],
},
unmounted: { id: 'dyn-1', pluginName: 'active-code-mode-plugin' },
stopped: { id: 'dyn-1', pluginName: 'active-code-mode-plugin' },
beforeContainsId: true,
afterContainsId: false,
})
@@ -311,12 +314,12 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p
ctx = await codeModeHarness(workdir)
const agent = ctx.agentLoop.create(SessionId('e2e-code-mode'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.followup([{
agent.followup({ content: [{
type: 'text',
text: 'Using one run_code program: run `echo alpha-7` with the bash tool, run `echo beta-9` with the bash tool, '
+ 'then write both outputs joined by a plus sign into combined.txt (bash heredoc or redirect), '
+ 'and return only the joined string.',
}])
}], source: { kind: 'user' } })
await waitForIdle(ctx, agent)
const events: SessionEvent[] = [...agent.session.events]
@@ -363,21 +366,17 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
})
handle.agent.followup([{
handle.agent.followup({ content: [{
type: 'text',
text: 'Use one run_code program to call tools.read on pkg/deep/task.txt. After it finishes, answer: Code Mode workspace handshake?',
}])
}], source: { kind: 'user' } })
await waitForIdle(ctx, handle.agent)
const events: SessionEvent[] = [...handle.agent.session.events]
const dispatch = events.find(event => event.type === 'tool/code-dispatch' && event.data.name === 'read')
const outerResult = events.find(event => event.type === 'tool/result')
const workspaceContext = events.find(event => event.type === 'user/message'
&& event.data.source.kind === 'plugin'
&& typeof event.data.meta === 'object'
&& event.data.meta !== null
&& !Array.isArray(event.data.meta)
&& event.data.meta.kind === 'workspace-instructions')
&& event.data.source.kind === 'workspace-instructions')
expect(dispatch).toBeDefined()
expect(outerResult).toBeDefined()
expect(workspaceContext).toBeDefined()
examples/headless-agent/tests/coding-task.e2e.ts
+2 -2
View File
@@ -56,12 +56,12 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('coding task: fix a failing test
ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT })
const agent = ctx.agentLoop.create(SessionId('e2e-task'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.followup([{
agent.followup({ content: [{
type: 'text',
text: 'In the current directory, `node add.test.js` fails because add.js has a bug. '
+ 'Fix add.js so the test passes, run `node add.test.js` to verify, and report the result. '
+ 'Do not modify add.test.js.',
}])
}], source: { kind: 'user' } })
await waitForIdle(ctx, agent)
// The agent claims success…
examples/headless-agent/tests/compaction.e2e.ts
+2 -2
View File
@@ -46,12 +46,12 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa
})
const agent = ctx.agentLoop.create(SessionId('e2e-compaction'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.followup([{
agent.followup({ content: [{
type: 'text',
text: 'Read file1.txt, file2.txt, file3.txt, and file4.txt one at a '
+ 'time using cat (a separate bash command for each). After reading all four, tell me how '
+ 'many files you read and the number mentioned in file1.txt.',
}])
}], source: { kind: 'user' } })
await waitForIdle(ctx, agent)
const events = [...agent.session.events]
examples/headless-agent/tests/fixtures/cli-mock-llm.ts
Vendored
+30 -1
View File
@@ -1,8 +1,33 @@
import type { Context } from 'cordis'
import { CallId, LlmAdapter, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm'
import {
CallId,
LlmAdapter,
ReasoningEffortId,
type GenerateOptions,
type LlmResolvedModelInfo,
type StreamChunk,
} from '@deepseek-ai/dsh-llm'
const HIGH = ReasoningEffortId('high')
const OFF = ReasoningEffortId('off')
/** Keyless headless-agent adapter: one real bash call followed by a final answer. */
class CliMockAdapter extends LlmAdapter {
override async resolveModel(provider: string, model: string): Promise<LlmResolvedModelInfo> {
return {
provider,
id: model,
name: model,
reasoning: {
efforts: [
{ id: OFF, name: 'Off' },
{ id: HIGH, name: 'High' },
],
defaultEffort: HIGH,
},
}
}
async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
const toolResult = options.messages.at(-1)?.content.find(block => block.type === 'tool-result')
if (toolResult === undefined) {
@@ -34,4 +59,8 @@ export const inject = ['llm']
/** Register the keyless `cli-mock` adapter. */
export function apply(ctx: Context): void {
ctx.llm.registerAdapter(['cli-mock'], new CliMockAdapter())
ctx.on('agent/request', async (_agent, _turn, step, _signal, next) => {
const config = await next()
return step === 2 ? { ...config, reasoningEffort: OFF } : config
})
}
examples/headless-agent/tests/fixtures/goal-domain/cordis.yml
Vendored
+4
View File
@@ -2,6 +2,10 @@
- id: cli-mock-llm
name: '../cli-mock-llm.ts'
# Managed child-process groups for the bash executor (spawn/kill/output plumbing).
- id: subprocess
name: '@deepseek-ai/dsh-subprocess-local'
- id: bash
name: '@deepseek-ai/dsh-bash-local'
examples/headless-agent/tests/fixtures/goal-domain/seed-goal.ts
Vendored
+1 -1
View File
@@ -7,7 +7,7 @@ export const name = 'seed-goal'
export const inject = ['goals']
export function apply(ctx: Context): void {
ctx.on('agent/pre-step', (agent) => {
ctx.on('agent/step', (agent) => {
if (ctx.goals.get(agent) !== undefined) return
ctx.goals.create(agent, {
objective: 'Prove the composed goal survives in the session log',
examples/headless-agent/tests/fixtures/retry-snapshot-backend.mjs
Vendored
+53
View File
@@ -0,0 +1,53 @@
/** Deterministic provider adapter for the headless retry-policy snapshot. */
import {
LlmAdapter,
LlmError,
resolveRetryPolicy,
} from '@deepseek-ai/dsh-llm'
class RetrySnapshotAdapter extends LlmAdapter {
requests = 0
firstMessages
policy = resolveRetryPolicy({
mode: 'normal',
maxRetries: 1,
retryableCodes: ['RATE_LIMIT'],
backoff: { initialDelayMs: 1, maxDelayMs: 1, jitterRatio: 0 },
}, 'retry-snapshot-backend.retryPolicy')
providerRetryPolicy() {
return this.policy
}
async * stream(options) {
const messages = JSON.stringify(options.messages)
this.requests++
if (this.requests === 1) {
this.firstMessages = messages
throw new LlmError('snapshot transient failure', 'RATE_LIMIT', { status: 429 })
}
if (this.requests === 2 && messages !== this.firstMessages) {
throw new Error('retry snapshot changed the model-visible messages')
}
const text = 'RETRY_OK'
yield { type: 'block-start', index: 0, blockType: 'text' }
yield { type: 'text-delta', index: 0, text }
yield { type: 'block-end', index: 0, block: { type: 'text', text } }
yield { type: 'usage', usage: { inputTokens: 4, outputTokens: 2 } }
yield { type: 'finish', reason: { kind: 'stop' } }
}
}
/** Cordis plugin name. */
export const name = 'retry-snapshot-backend'
/** Required LLM registry service. */
export const inject = ['llm']
/**
* Register the deterministic provider adapter.
* @param {import('cordis').Context} ctx - plugin context carrying the LLM service.
*/
export function apply(ctx) {
ctx.llm.registerAdapter(['deepseek'], new RetrySnapshotAdapter())
}
examples/headless-agent/tests/fixtures/telemetry-otel-driver.ts
Vendored
+43
View File
@@ -0,0 +1,43 @@
#!/usr/bin/env node
/**
* Test driver: start a mock OTLP/HTTP collector, boot the telemetry Loader
* composition against it, run one turn whose prompt carries a fixture
* credential, then persist everything the collector captured to
* `./otlp-captures.json` for the e2e's inspect step.
*/
import { writeFile } from 'node:fs/promises'
import { createServer } from 'node:http'
import { once } from 'node:events'
import { boot, resolveConfigPath } from '@deepseek-ai/dsh-app-boot'
import { runOneShot } from '@deepseek-ai/dsh-cli-demo/src/cli.ts'
const configPath = process.argv[2]
if (configPath === undefined) throw new Error('telemetry-otel driver requires a config path')
const captures: unknown[] = []
const server = createServer((request, response) => {
const chunks: Buffer[] = []
request.on('data', chunk => chunks.push(chunk as Buffer))
request.on('end', () => {
captures.push(JSON.parse(Buffer.concat(chunks).toString()))
response.writeHead(200, { 'content-type': 'application/json' }).end('{}')
})
})
server.listen(0, '127.0.0.1')
await once(server, 'listening')
const address = server.address()
if (address === null || typeof address === 'string') throw new Error('collector has no port')
process.env.DSH_TELEMETRY_E2E_URL = `http://127.0.0.1:${address.port}/v1/logs`
const ctx = await boot('telemetry-otel-e2e', resolveConfigPath(configPath, undefined))
try {
// The fixture credential rides the model-visible user message; the exported
// copy must scrub it while the canonical log keeps the original bytes.
await runOneShot(ctx, { task: 'prove telemetry with key sk-e2efixture1234567890' })
} finally {
await ctx.fiber.dispose()
}
await writeFile('./otlp-captures.json', JSON.stringify(captures))
server.close()
server.closeAllConnections()
examples/headless-agent/tests/fixtures/telemetry-otel.cordis.yml
Vendored
+28
View File
@@ -0,0 +1,28 @@
# Test-only composition: session-telemetry-otel through the real Loader/app
# path, exporting to the mock OTLP collector the driver starts (url via env).
# The redact-rule entry models a deployment mounting its own scrub rule on the
# telemetry/record waterfall — the seam itself ships no rules.
- id: cli-mock-llm
name: './cli-mock-llm.ts'
- id: telemetry-redact-rule
name: './telemetry-redact-rule.ts'
- id: bash
name: '@deepseek-ai/dsh-bash-local'
- id: telemetry-otel
name: '@deepseek-ai/dsh-session-telemetry-otel'
config:
exporter:
url: !!js process.env.DSH_TELEMETRY_E2E_URL
- id: cli-agent
name: '@deepseek-ai/dsh-cli-demo'
config:
provider: cli-mock
model: cli-mock
persona: 'Test the session-telemetry-otel plugin.'
persistenceRoot: './.sessions'
persistenceCompression: 'none'
workspaceContext: false
examples/headless-agent/tests/fixtures/telemetry-redact-rule.ts
Vendored
+29
View File
@@ -0,0 +1,29 @@
import type { Context } from 'cordis'
/**
* Deployment-style redaction rule for the telemetry e2e: scrubs the fixture
* credential from body strings, exactly as a real deployment would mount its
* own rules on the `telemetry/record` waterfall.
*/
const SECRET = /sk-e2efixture[0-9]+/g
const PLACEHOLDER = '[E2E-REDACTED]'
function scrub(value: unknown): unknown {
if (typeof value === 'string') return value.replace(SECRET, PLACEHOLDER)
if (Array.isArray(value)) return value.map(scrub)
if (value !== null && typeof value === 'object') {
return Object.fromEntries(Object.entries(value).map(([key, entry]) => [key, scrub(entry)]))
}
return value
}
export const name = 'telemetry-redact-rule'
/** Mount the fixture scrub rule onto the redact waterfall. */
export function apply(ctx: Context): void {
ctx.on('telemetry/record', (_record, next) => {
const record = next()
return { ...record, body: scrub(record.body) }
})
}
examples/headless-agent/tests/fixtures/time-context.cordis.yml
Vendored
+4
View File
@@ -2,6 +2,10 @@
- id: time-context-mock-llm
name: './time-context-mock-llm.ts'
# Managed child-process groups for the bash executor (spawn/kill/output plumbing).
- id: subprocess
name: '@deepseek-ai/dsh-subprocess-local'
- id: bash
name: '@deepseek-ai/dsh-bash-local'
examples/headless-agent/tests/full-loop.e2e.ts
+1 -1
View File
@@ -30,7 +30,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('full loop: real model + real bas
ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT })
const agent = ctx.agentLoop.create(SessionId('e2e-loop'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.followup([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }])
agent.followup({ content: [{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }], source: { kind: 'user' } })
await waitForIdle(ctx, agent)
const events = [...agent.session.events]
examples/headless-agent/tests/harness.ts
+2
View File
@@ -4,6 +4,7 @@ import type { Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit'
import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
import LocalSubprocessService from '@deepseek-ai/dsh-subprocess-local'
import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
import * as ToolTodo from '@deepseek-ai/dsh-tool-todo'
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
@@ -59,6 +60,7 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio
await ctx.plugin(LlmDeepSeek, options.modelContextWindow === undefined ? {} : {
models: [{ id: 'deepseek-v4-flash', contextWindow: options.modelContextWindow }],
})
await ctx.plugin(LocalSubprocessService)
await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 })
await ctx.plugin(ToolBash)
await ctx.plugin(ToolTodo)
examples/headless-agent/tests/headless.snapshot.ts
+94 -9
View File
@@ -24,10 +24,13 @@ const ptyStreamExpected = join(ptyScenarioDir, 'stream-json.expected.jsonl')
const ptyConfigPath = fileURLToPath(new URL('../pty.cordis.snapshot.yml', import.meta.url))
const goalScenarioDir = join(snapshotsDir, 'goal-tools')
const goalConfigPath = fileURLToPath(new URL('../goal.cordis.snapshot.yml', import.meta.url))
const retryScenarioDir = join(snapshotsDir, 'provider-retry')
const retryConfigPath = fileURLToPath(new URL('../retry.cordis.snapshot.yml', import.meta.url))
const ralphScenarioDir = join(snapshotsDir, 'ralph-loop')
const ralphConfigPath = fileURLToPath(new URL('../ralph.cordis.snapshot.yml', import.meta.url))
const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url))
const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
const reasoningConfigPath = fileURLToPath(new URL('./fixtures/cli.cordis.yml', import.meta.url))
const refreshing = process.env.DSH_SNAPSHOT === 'refresh'
interface JsonObject {
@@ -124,6 +127,86 @@ async function persistedLogs(cwd: string): Promise<PersistedLog[]> {
}
describe('headless stream-json snapshots', () => {
it('retries a transient provider failure through the one-shot app', async () => {
const prompt = await scenarioPrompt(retryScenarioDir, 'provider-retry')
const streamExpected = join(retryScenarioDir, 'stream-json.expected.jsonl')
let runCwd = ''
const result = await runLoaderSmoke({
label: 'provider retry headless stream-json snapshot',
tempDirPrefix: 'headless-snapshot-provider-retry-',
binScript,
configPath: retryConfigPath,
binArgs: ['--config', retryConfigPath, '--output-format', 'stream-json', prompt],
tsconfigPath,
env: {
DSH_SNAPSHOT: 'replay',
NODE_OPTIONS: [process.env.NODE_OPTIONS, '--disable-warning=ExperimentalWarning'].filter(Boolean).join(' '),
},
prepare: (cwd) => { runCwd = cwd },
inspect: async (cwd) => {
const logs = await persistedLogs(cwd)
expect(logs).toHaveLength(1)
const records = parseJsonl(logs[0]?.content ?? '')
const retries = records.filter(record => record.type === 'llm/retry')
expect(retries).toHaveLength(1)
expect(retries[0]?.data).toMatchObject({
provider: 'deepseek',
mode: 'normal',
policyKey: '["normal",1,["RATE_LIMIT"],1,1,0]',
retry: 1,
maxRetries: 1,
delayMs: 1,
failure: { message: 'snapshot transient failure', code: 'RATE_LIMIT', status: 429 },
})
},
})
expect(result.stderr).toBe('')
const normalized = normalizeHeadlessStream(result.stdout, runCwd)
if (refreshing) await writeFile(streamExpected, normalized)
expect(normalized).toBe(await readFile(streamExpected, 'utf8'))
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
it('logs the model default and a dynamic next-step reasoning effort', async () => {
const result = await runLoaderSmoke({
label: 'reasoning effort headless stream-json snapshot',
tempDirPrefix: 'headless-snapshot-reasoning-effort-',
binScript,
configPath: reasoningConfigPath,
binArgs: ['--config', reasoningConfigPath, '--output-format', 'stream-json', 'prove dynamic reasoning effort'],
tsconfigPath,
})
expect(result.stderr).toBe('')
const headers = parseJsonl(result.stdout)
.map(record => record.event)
.filter((event): event is JsonObject => (
event !== null
&& typeof event === 'object'
&& !Array.isArray(event)
&& 'type' in event
&& event.type === 'request/header'
))
.map((event) => {
const data = event.data as JsonObject
return (data.header as JsonObject).config
})
expect(headers).toMatchInlineSnapshot(`
[
{
"model": "cli-mock",
"provider": "cli-mock",
"reasoningEffort": "high",
},
{
"model": "cli-mock",
"provider": "cli-mock",
"reasoningEffort": "off",
},
]
`)
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
it('replays the advanced toolchain through the one-shot app', async () => {
const prompt = await scenarioPrompt(advancedScenarioDir, 'advanced-toolchain')
const fixtureFiles = [
@@ -160,6 +243,7 @@ describe('headless stream-json snapshots', () => {
const children = logs.filter(log => typeof log.header.parentSession === 'string')
.sort((left, right) => Number(left.header.createdAt) - Number(right.header.createdAt))
const actualSessions = [parent, ...children]
const actualContext = contextFromLogs(actualSessions.map(log => log.content))
if (refreshing) {
const harvested = actualSessions.map((log): HarvestedLog => ({
id: String(log.header.id),
@@ -176,12 +260,11 @@ describe('headless stream-json snapshots', () => {
if (existing === undefined || file === undefined) {
throw new Error(`headless snapshot has no fixture for persisted log ${index}`)
}
const stable = stabilizeRefreshLog(actual.content, existing, replacements)
const stable = stabilizeRefreshLog(actual.content, existing, replacements, actualContext)
await writeFile(file, stable)
return stable
}))
}
const actualContext = contextFromLogs(actualSessions.map(log => log.content))
const expectedContext = contextFromLogs(expectedSessions)
for (const [index, actual] of actualSessions.entries()) {
const expected = expectedSessions[index]
@@ -231,14 +314,16 @@ describe('headless stream-json snapshots', () => {
const goalChanges = records.filter((record) => {
if (record.type !== 'user/message') return false
const data = record.data as JsonObject | undefined
const meta = data?.meta as JsonObject | undefined
return meta?.kind === 'goal/change'
const source = data?.source as JsonObject | undefined
const change = source?.change as JsonObject | undefined
return source?.kind === 'goal' && change?.kind === 'goal/change'
})
expect(goalChanges).toHaveLength(1)
const data = goalChanges[0]?.data as JsonObject | undefined
const meta = data?.meta as JsonObject | undefined
const goal = meta?.goal as JsonObject | undefined
expect(meta?.operation).toBe('create')
const source = data?.source as JsonObject | undefined
const change = source?.change as JsonObject | undefined
const goal = change?.goal as JsonObject | undefined
expect(change?.operation).toBe('create')
expect(goal).toMatchObject({
objective: 'Finish the headless goal-tool snapshot proof',
phase: 'active',
@@ -354,6 +439,7 @@ describe('headless stream-json snapshots', () => {
expect(logs).toHaveLength(1)
const actual = logs[0]
if (actual === undefined) throw new Error('headless PTY snapshot did not persist its session')
const actualContext = contextFromLogs([actual.content])
if (refreshing) {
const harvested: HarvestedLog = {
id: String(actual.header.id),
@@ -361,10 +447,9 @@ describe('headless stream-json snapshots', () => {
content: actual.content,
}
const replacements = refreshFixtureReplacements([harvested], [expectedSession])
expectedSession = stabilizeRefreshLog(actual.content, expectedSession, replacements)
expectedSession = stabilizeRefreshLog(actual.content, expectedSession, replacements, actualContext)
await writeFile(ptySessionFixture, expectedSession)
}
const actualContext = contextFromLogs([actual.content])
const expectedContext = contextFromLogs([expectedSession])
expect(scrubRequestHeaders(normalizeSessionLog(actual.content, actualContext)))
.toBe(scrubRequestHeaders(normalizeSessionLog(expectedSession, expectedContext)))
examples/headless-agent/tests/resume.e2e.ts
+2 -2
View File
@@ -41,7 +41,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses
sessionId: SESSION_ID,
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
})).agent
first.followup([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }])
first.followup({ content: [{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }], source: { kind: 'user' } })
await waitForIdle(ctx, first)
await ctx.fiber.dispose()
ctx = undefined
@@ -58,7 +58,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses
// The prior user turn is in the rehydrated log before the model is asked.
expect(JSON.stringify(resumed.session.deriveMessages())).toContain(SECRET)
resumed.followup([{ type: 'text', text: 'What was the code I asked you to remember? Reply with just the code.' }])
resumed.followup({ content: [{ type: 'text', text: 'What was the code I asked you to remember? Reply with just the code.' }], source: { kind: 'user' } })
await waitForIdle(ctx, resumed)
// The model recalls it — only possible from the resumed history.
examples/headless-agent/tests/snapshots/advanced-toolchain/input.json
+1 -1
View File
@@ -2,6 +2,6 @@
"steps": [
{ "op": "initialize" },
{ "op": "newSession" },
{ "op": "prompt", "text": "Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_HEADLESS_OK." }
{ "op": "prompt", "text": "Run this advanced flow exactly once: try a no-op temporary Cordis Plugin named snapshot-marker; use run_code to inspect the live temporary Plugins through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; stop dyn-1; then reply with exactly ADVANCED_HEADLESS_OK." }
]
}
examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
+1 -1
View File
File diff suppressed because one or more lines are too long
examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
+1 -1
View File
File diff suppressed because one or more lines are too long
examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl
+11 -11
View File
File diff suppressed because one or more lines are too long
examples/headless-agent/tests/snapshots/advanced-toolchain/stream-json.expected.jsonl
+10 -10
View File
@@ -1,5 +1,5 @@
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_HEADLESS_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: try a no-op temporary Cordis Plugin named snapshot-marker; use run_code to inspect the live temporary Plugins through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; stop dyn-1; then reply with exactly ADVANCED_HEADLESS_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":2,"time":0,"data":{"title":"Run this advanced flow exactly","messageSeqs":[1],"source":{"kind":"fallback"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":4,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}}
@@ -10,19 +10,19 @@
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":9,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":10,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"advanced-mount","content":[{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"advanced-mount","content":[{"type":"text","text":"Temporary Plugin dyn-1 is running (plugin \"snapshot-marker\"; available until unmounted or DSH restarts)."}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":13,"time":0,"data":{"turn":1,"step":1}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":14,"time":0,"data":{"turn":1,"step":2}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-code","name":"run_code","argumentsDelta":"{\"code\": \"return await tools.cordis_inspect({ what: 'dynamic' })\", \"description\": \"Run the scripted inspection program\"}"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'dynamic' })\", \"description\": \"Run the scripted inspection program\"}"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-code","name":"run_code","argumentsDelta":"{\"code\": \"return await tools.cordis_inspect({ what: 'temporary' })\", \"description\": \"Run the scripted inspection program\"}"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'temporary' })\", \"description\": \"Run the scripted inspection program\"}"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'dynamic' })\", \"description\": \"Run the scripted inspection program\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'dynamic' })\", \"description\": \"Run the scripted inspection program\"}"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/code-dispatch-start","seq":22,"time":0,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"dynamic"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/code-dispatch","seq":23,"time":0,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"dynamic"},"isError":false,"content":[{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}]}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":24,"time":0,"data":{"turn":1,"step":2,"callId":"advanced-code","content":[{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}],"isError":false},"sourceEventSeqs":[21],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'temporary' })\", \"description\": \"Run the scripted inspection program\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'temporary' })\", \"description\": \"Run the scripted inspection program\"}"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/code-dispatch-start","seq":22,"time":0,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"temporary"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/code-dispatch","seq":23,"time":0,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"temporary"},"isError":false,"content":[{"type":"text","text":"## Temporary Plugins\n- Temporary Plugin dyn-1: snapshot-marker [running] — provides: none; waiting for: none; lifetime: until unmounted or DSH restarts"}]}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":24,"time":0,"data":{"turn":1,"step":2,"callId":"advanced-code","content":[{"type":"text","text":"## Temporary Plugins\n- Temporary Plugin dyn-1: snapshot-marker [running] — provides: none; waiting for: none; lifetime: until unmounted or DSH restarts"}],"isError":false},"sourceEventSeqs":[21],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":25,"time":0,"data":{"turn":1,"step":2}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":26,"time":0,"data":{"turn":1,"step":3}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":27,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
@@ -52,7 +52,7 @@
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":51,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":52,"time":0,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[47,48,49,50,51],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":53,"time":0,"data":{"turn":1,"step":5,"callId":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":54,"time":0,"data":{"turn":1,"step":5,"callId":"advanced-unmount","content":[{"type":"text","text":"unmounted dyn-1 (plugin \"snapshot-marker\")"}],"isError":false},"sourceEventSeqs":[53],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":54,"time":0,"data":{"turn":1,"step":5,"callId":"advanced-unmount","content":[{"type":"text","text":"Temporary Plugin dyn-1 was unmounted and removed."}],"isError":false},"sourceEventSeqs":[53],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":55,"time":0,"data":{"turn":1,"step":5}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":56,"time":0,"data":{"turn":1,"step":6}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":57,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}}
examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl
+1 -1
View File
@@ -21,7 +21,7 @@
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_create","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[21],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":23,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":7},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0},"meta":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the headless goal-tool snapshot proof","phase":"active","maxGoalRounds":7},"roundsStarted":0,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":23,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":7},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0,"change":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the headless goal-tool snapshot proof","phase":"active","maxGoalRounds":7},"roundsStarted":0,"createdAt":0,"updatedAt":0}}},"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":24,"time":0,"data":{"turn":1,"step":2}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":25,"time":0,"data":{"turn":1,"step":3}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
examples/headless-agent/tests/snapshots/provider-retry/input.json
+8
View File
@@ -0,0 +1,8 @@
{
"steps": [
{
"op": "prompt",
"text": "retry the transient provider failure"
}
]
}
examples/headless-agent/tests/snapshots/provider-retry/stream-json.expected.jsonl
+19
View File
@@ -0,0 +1,19 @@
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"retry the transient provider failure"}],"source":{"kind":"user"}},"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":2,"time":0,"data":{"title":"retry the transient provider failure","messageSeqs":[1],"source":{"kind":"fallback"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":4,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":5,"time":0,"data":{"turn":1,"step":1}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"llm/retry","seq":6,"time":0,"data":{"turn":1,"step":1,"provider":"deepseek","mode":"normal","policyKey":"[\"normal\",1,[\"RATE_LIMIT\"],1,1,0]","retry":1,"maxRetries":1,"delayMs":1,"failure":{"message":"snapshot transient failure","code":"RATE_LIMIT","status":429}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":7,"time":0,"data":{"turn":1,"reason":{"kind":"error","step":1,"failure":{"message":"snapshot transient failure","code":"RATE_LIMIT","status":429}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":8,"time":0,"data":{"turn":2,"trigger":{"kind":"retry"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":9,"time":0,"data":{"turn":2,"step":1}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":10,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":11,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":0,"text":"RETRY_OK"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":12,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"RETRY_OK"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":13,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":4,"outputTokens":2}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":15,"time":0,"data":{"turn":2,"step":1,"content":[{"type":"text","text":"RETRY_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":4,"outputTokens":2}},"sourceEventSeqs":[10,11,12,13,14],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":16,"time":0,"data":{"turn":2,"step":1}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":17,"time":0,"data":{"turn":2,"reason":{"kind":"completed"}}}}
{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":2,"result":"RETRY_OK","reason":{"kind":"completed"},"usage":{"inputTokens":4,"outputTokens":2}}
examples/headless-agent/tests/snapshots/pty-tools/session.jsonl
+1 -1
View File
File diff suppressed because one or more lines are too long
examples/headless-agent/tests/todo-write.e2e.ts
+2 -2
View File
@@ -28,10 +28,10 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a
ctx = await codingHarness(workdir, { persona: TODO_SYSTEM_PROMPT })
const agent = ctx.agentLoop.create(SessionId('e2e-todo'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.followup([{ type: 'text', text:
agent.followup({ content: [{ type: 'text', text:
'Use the todo_write tool to record a plan of exactly two steps: first '
+ '"inspect the failing test" (in_progress), then "apply the fix" (pending). '
+ 'Send both in one todo_write call, then reply with the single word DONE.' }])
+ 'Send both in one todo_write call, then reply with the single word DONE.' }], source: { kind: 'user' } })
await waitForIdle(ctx, agent)
const events = [...agent.session.events]
examples/jsonrpc-agent/cordis.snapshot.yml
+28
View File
@@ -0,0 +1,28 @@
# Keyless replay includes the live `cordis.yml`, disables the key-requiring
# DeepSeek adapter, and inserts `llm-replay` to serve recorded JSONL without a
# key or network; every other entry remains shared. The replay provider
# catalog claims the `deepseek` provider so the SDK server's `initialize`
# finds it owned and never mounts the real-adapter fallback. The SDK snapshot
# suite passes this path explicitly through `DSH_CORDIS_CONFIG` (the
# jsonrpc-demo bin performs no DSH_SNAPSHOT config swap of its own), and
# `llm-replay` reads `DSH_SNAPSHOT_FILE` / `DSH_SNAPSHOT_CHILD_FILES` from the
# harness. Stdout remains reserved for JSON-RPC frames.
- id: base
name: '@cordisjs/plugin-include'
config:
path: ./cordis.yml
patches:
# `name` asserts the target: a mismatch skips the patch and warns only
# when a logger exists.
- 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
examples/jsonrpc-agent/cordis.yml
+6
View File
@@ -17,6 +17,10 @@
thinking: enabled
reasoningEffort: max
# Managed child-process groups for the bash executor (spawn/kill/output plumbing).
- id: subprocess
name: '@deepseek-ai/dsh-subprocess-local'
- id: bash
name: '@deepseek-ai/dsh-bash-local'
config:
@@ -38,6 +42,8 @@
name: '@deepseek-ai/dsh-session-persistence-jsonl'
config:
root: !!js process.env.DSH_SESSION_ROOT ?? './.sessions'
# Snapshot runs read the raw JSONL back; production keeps zstd frames.
compression: !!js "process.env.DSH_SNAPSHOT === undefined ? 'zstd' : 'none'"
- id: session-checkpoints
name: '@deepseek-ai/dsh-session-checkpoint-policy'
examples/jsonrpc-agent/tests/fixtures/subagent/subagent-dsh-sdk/child-mock-llm.ts
Vendored
+32
View File
@@ -0,0 +1,32 @@
import type { Context } from 'cordis'
import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
import { LlmAdapter } from '@deepseek-ai/dsh-llm'
/**
* Scripted model for the CHILD runtime: answers every request with its own
* process cwd, so the driving e2e can prove the parent session's workspace
* reached the child process across the SDK wire. `options` carries the
* request; the reply depends only on process state.
*/
class CwdEchoAdapter extends LlmAdapter {
async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
void options
const reply = `child cwd: ${process.cwd()}`
yield { type: 'block-start', index: 0, blockType: 'text' }
yield { type: 'text-delta', index: 0, text: reply }
yield { type: 'block-end', index: 0, block: { type: 'text', text: reply } }
yield { type: 'usage', usage: { inputTokens: 3, outputTokens: reply.length } }
yield { type: 'finish', reason: { kind: 'stop' } }
}
}
export const name = 'child-mock-llm'
export const inject = ['llm']
/**
* Register the cwd-echo adapter under the `mock` provider.
* @param ctx - the plugin context supplying `ctx.llm`.
*/
export function apply(ctx: Context): void {
ctx.llm.registerAdapter(['mock'], new CwdEchoAdapter())
}
examples/jsonrpc-agent/tests/fixtures/subagent/subagent-dsh-sdk/child.cordis.yml
Vendored
+40
View File
@@ -0,0 +1,40 @@
# The CHILD runtime for the SDK subagent composition test: a complete
# stdio JSON-RPC harness whose scripted model echoes its process cwd. The
# parent's subagent-sdk backend spawns this composition per run; stdout is
# reserved for JSON-RPC frames.
- id: jsonrpc
name: '@deepseek-ai/dsh-jsonrpc'
- id: child-mock-llm
name: './child-mock-llm.ts'
- id: agent-core
name: '@deepseek-ai/dsh-agent-spine-demo'
config:
persona: 'Echo where you run.'
workspaceContext: false
skills:
enabled: false
toolBash:
enableRunInBackground: false
toolTasks: false
# The child persists its own session log beside the parent's (distinct root),
# so the driving e2e can inspect both transcripts after the run.
- id: sessions
name: '@deepseek-ai/dsh-session-persistence-jsonl'
config:
root: !!js process.env.DSH_SESSION_ROOT ?? './.child-sessions'
compression: none
- id: session-checkpoints
name: '@deepseek-ai/dsh-session-checkpoint-policy'
# bash-local executes through the subprocess seam.
- id: subprocess
name: '@deepseek-ai/dsh-subprocess-local'
- id: bash
name: '@deepseek-ai/dsh-bash-local'
config:
cwd: !!js process.env.DSH_CWD ?? process.cwd()
examples/jsonrpc-agent/tests/fixtures/subagent/subagent-dsh-sdk/cordis.yml
Vendored
+43
View File
@@ -0,0 +1,43 @@
# Test-only composition: the SDK subagent backend on the real Loader/app path.
# The scripted model delegates once; the child — a COMPLETE second harness
# runtime speaking stdio JSON-RPC — echoes its process cwd, so parent-session
# cwd inheritance is asserted keylessly end to end across the SDK wire.
# `cwd` is deliberately omitted — the inheritance branch under test. The child
# launch is machine-absolute, so the driving e2e supplies it via
# DSH_TEST_CHILD_COMMAND / DSH_TEST_CHILD_ARGS / DSH_TEST_CHILD_ENV (resolved
# through the shared example-launch resolver, per testing policy).
- id: mock-llm
name: './mock-delegating-llm.ts'
- id: subagent
name: '@deepseek-ai/dsh-subagent'
# providerName is omitted: the composition exercises the shipped default
# (`dsh-sdk`) through the real Loader.
- id: subagent-dsh-sdk
name: '@deepseek-ai/dsh-subagent-dsh-sdk'
config:
command: !!js process.env.DSH_TEST_CHILD_COMMAND
args: !!js JSON.parse(process.env.DSH_TEST_CHILD_ARGS ?? '[]')
provider: mock
model: mock-echo
env: !!js JSON.parse(process.env.DSH_TEST_CHILD_ENV ?? '{}')
- id: tool-subagent
name: '@deepseek-ai/dsh-tool-subagent'
config:
provider: dsh-sdk
toolName: subagent
# The SDK backend advertises no depthLimit: the child harness owns its own
# recursion budget, so the local numeric default cannot apply here.
maxDepth: 'provider-managed'
- id: cli-agent
name: '@deepseek-ai/dsh-cli-demo'
config:
provider: mock
model: mock-delegate
persona: 'Test SDK subagent cwd inheritance.'
persistenceRoot: './.sessions'
persistenceCompression: 'none'
workspaceContext: false
examples/jsonrpc-agent/tests/fixtures/subagent/subagent-dsh-sdk/driver.ts
Vendored
+15
View File
@@ -0,0 +1,15 @@
#!/usr/bin/env node
/** Test driver: one delegation turn through a headless Loader composition. */
import { boot, resolveConfigPath } from '@deepseek-ai/dsh-app-boot'
import { runOneShot } from '@deepseek-ai/dsh-cli-demo/src/cli.ts'
const configPath = process.argv[2]
if (configPath === undefined) throw new Error('sdk-subagent cwd driver requires a config path')
const ctx = await boot('sdk-subagent-cwd-e2e', resolveConfigPath(configPath, undefined))
try {
await runOneShot(ctx, { task: 'delegate' })
} finally {
await ctx.fiber.dispose()
}
examples/jsonrpc-agent/tests/fixtures/subagent/subagent-dsh-sdk/mock-delegating-llm.ts
Vendored
+48
View File
@@ -0,0 +1,48 @@
import type { Context } from 'cordis'
import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm'
/**
* Test adapter for the `mock-delegate` model: the first request calls the
* `subagent` tool once, and the follow-up streams the tool result text back
* verbatim — so the SDK child runtime's answer (the scripted child model's
* cwd echo) reaches the parent session log for the driving e2e to assert.
*/
class MockDelegatingAdapter extends LlmAdapter {
async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
const toolResultText = options.messages.at(-1)?.content
.filter(block => block.type === 'tool-result')
.flatMap(block => block.content)
.filter(block => block.type === 'text')
.map(block => block.text)
.join('') ?? ''
if (toolResultText.length === 0) {
const args = JSON.stringify({ description: 'cwd probe', prompt: 'report your workspace' })
yield { type: 'block-start', index: 0, blockType: 'tool-call' }
yield { type: 'tool-call-delta', index: 0, id: CallId('call-delegate'), name: 'subagent', argumentsDelta: args }
yield { type: 'block-end', index: 0, block: { type: 'tool-call', id: CallId('call-delegate'), name: 'subagent', arguments: args } }
yield { type: 'usage', usage: { inputTokens: 10, outputTokens: 5 } }
yield { type: 'finish', reason: { kind: 'tool-calls' } }
return
}
const reply = `child reported:\n${toolResultText}`
yield { type: 'block-start', index: 0, blockType: 'text' }
yield { type: 'text-delta', index: 0, text: reply }
yield { type: 'block-end', index: 0, block: { type: 'text', text: reply } }
yield { type: 'usage', usage: { inputTokens: 10, outputTokens: reply.length } }
yield { type: 'finish', reason: { kind: 'stop' } }
}
}
export const name = 'mock-llm'
export const inject = ['llm']
/**
* Register the delegating mock adapter under the `mock` provider.
* @param ctx - the plugin context supplying `ctx.llm`.
*/
export function apply(ctx: Context): void {
ctx.llm.registerAdapter(['mock'], new MockDelegatingAdapter())
}

Some files were not shown because too many files have changed in this diff Show More