diff --git a/AGENTS.md b/AGENTS.md index f02940b5ae..47893c81de 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -73,6 +73,10 @@ packages/ Harness packages, grouped by role at packages///. bash/ abstract bash executor seam (ctx.bash) — interface only bash-local/ local-subprocess BashExecutor implementation tool-bash/ model-facing bash/bash_output/bash_kill tool schemas + todo/ todo/planning capability family + tool-todo/ model-facing todo_write tool: writes the whole task list to + the session log (todo/write), rendered as a stdio checklist / + ACP plan session-persistence/ persistence capability family session-persistence/ durable persistence seam + write coordinator session-persistence-jsonl/ JSONL-sidecar backend @@ -172,6 +176,16 @@ pnpm run demo:acp # run examples/acp-agent — the coding agent as an ACP # drive it from Zed or another ACP client) ``` +### Run the CI gates locally BEFORE marking a PR ready + +CI is the backstop, not the first place a gate runs. Before you open a non-draft PR or move one from draft to ready, run the same gates CI runs, on your own tree, and confirm they pass — do not lean on CI (or a Codex pass) to discover a red gate you could have caught locally. The CI-equivalent local run is: + +```sh +pnpm run typecheck && pnpm run lint && pnpm run test:coverage && pnpm run test:snapshot && pnpm run doc-sync && pnpm run hygiene && pnpm run build +``` + +**`pnpm run test:coverage`, NOT `pnpm run test`, is the gating test command.** `pnpm run test` runs `vitest run` with no coverage; CI's node job runs `test:coverage`, which enforces a **per-file 100%** threshold on `packages/*/*/src`. A suite that is green under `test` can still fail CI on an uncovered line — and that uncovered line is often *dead code* the 100% gate is correctly flagging for deletion (see [§ Defensive patterns](#defensive-patterns-hard-won) "Line coverage is not behavior coverage"), not a missing test to bolt on. `hygiene` (knip + publint + workspace constraints + NodeNext types) and `test:snapshot` (keyless ACP replay) are likewise CI gates that `test` alone does not cover. When you rely on a Codex convergence pass for sign-off, check WHICH commands it ran: a pass that ran `test` but not `test:coverage`/`hygiene`/`doc-sync` has not exercised those gates. + ## Secrets / .env Real-API e2e tests (`pnpm run test:e2e`) read `DEEPSEEK_API_KEY` (and optionally `DEEPSEEK_BASE_URL`) from the environment, or from a gitignored `.env` at the repo root loaded via Node's native `process.loadEnvFile()`: diff --git a/docs/architecture.md b/docs/architecture.md index f5e5a52dce..436978823f 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -147,6 +147,7 @@ forever: session('assistant/message' {content, usage?}) log records what tool dispatch uses each tool-call (sequential, abort-checked between calls): session('tool/call'); ctx.tools.execute() ⟵ waterfall tools/execute + tool execution may append tool-owned session events, e.g. `todo/write` session('tool/result') drain steering → session('steering/message'); emit agent/steering emit agent/step-end @@ -197,7 +198,7 @@ Every MVP feature (including the TODO-marked ones), with the mechanism that impl | System prompt configurability | `ctx.systemPrompt.section()` with ordering | | AGENTS.md (root) | a section provider reading the file | | AGENTS.md (subdir, on-touch) + file-change notices | `agent.inject()` from a watcher / tool-result listener | -| Built-in tools (Read/Write/Edit/Bash/…) | `ctx.tools.register()`; schemas flow into the assembly automatically. **Bash: implemented** — `dsh-bash` (seam) + `dsh-bash-local` (subprocesses) + `dsh-tool-bash` (`bash`/`bash_output`/`bash_kill`, incl. background tasks) | +| Built-in tools (Read/Write/Edit/Bash/…) | `ctx.tools.register()`; schemas flow into the assembly automatically. **Bash: implemented** — `dsh-bash` (seam) + `dsh-bash-local` (subprocesses) + `dsh-tool-bash` (`bash`/`bash_output`/`bash_kill`, incl. background tasks). **`todo_write`: implemented** — `dsh-tool-todo` writes the whole task list to the session log (`todo/write`), rendered as a stdio checklist / ACP `plan` | | ToolSearch / progressive disclosure | wrap `agent/request`, filter `req.tools` | | Tool sandbox (landlock / sandbox-exec) | wrap `tools/execute`, or implement a sandboxing `BashExecutor` (the dsh-bash seam) | | Permission system / AskUserQuestion | wrap `tools/execute` (veto or ask); register an ask tool | diff --git a/docs/cookbook/adding-a-package.md b/docs/cookbook/adding-a-package.md index 3c9cdb07d5..ef5f48d624 100644 --- a/docs/cookbook/adding-a-package.md +++ b/docs/cookbook/adding-a-package.md @@ -16,7 +16,7 @@ packages/// README.md # service API, events, extension points, design notes ``` -Choose an existing group when one matches the package's role (`core`, `llm`, `bash`, `session-persistence`, `ui`, `util`, or `support`). A new group is allowed, but it is a pure container: no `package.json`, no source files, and packages still sit exactly one level below it. +Choose an existing group when one matches the package's role (`core`, `llm`, `bash`, `compact`, `subagent`, `todo`, `session-persistence`, `ui`, `util`, or `support`). A new group is allowed, but it is a pure container: no `package.json`, no source files, and packages still sit exactly one level below it. package.json invariants (enforced by `pnpm run constraints` / `scripts/check-workspace-constraints.ts`): `private: true`, `version: 0.0.1`, `type: module`, `main: "lib/index.js"`, `types: "lib/types/index.d.ts"`, `exports["."].types: "./lib/types/index.d.ts"`, `exports["."].default: "./lib/index.js"`, `cordis` in BOTH peerDependencies and devDependencies (same range). Mirror every dsh peer dependency in devDependencies. `schemastery` goes in `dependencies` (it is a runtime validator), matching agent-loop. The `files` list is precise: `lib/index.js`, `lib/types/**/*.d.ts`, `lib/types/**/*.d.ts.map`, and `src`; do not publish `lib/types` JS or JS-map intermediates or stale root declaration files. CLI app packages with a package `bin` include `lib/bin.js` immediately after `lib/index.js` in `files`. diff --git a/docs/cordis-catalog/events-and-services.md b/docs/cordis-catalog/events-and-services.md index 3823cf8144..a2bb8a4229 100644 --- a/docs/cordis-catalog/events-and-services.md +++ b/docs/cordis-catalog/events-and-services.md @@ -11,7 +11,7 @@ The **harness tier** below (the `@deepseek-ai/dsh-*` packages) is the vocabulary ## Events -Dispatch modes: **emit** (fire-and-forget), **waterfall** (each listener gets `next()` and may transform or veto — see [waterfall semantics](../architecture.md#cordis-waterfall-semantics-important)), **parallel** (awaited fan-out, no veto), **serial** (awaited, in registration order, no veto). The harness declares 25 events across 6 scopes. +Dispatch modes: **emit** (fire-and-forget), **waterfall** (each listener gets `next()` and may transform or veto — see [waterfall semantics](../architecture.md#cordis-waterfall-semantics-important)), **parallel** (awaited fan-out, no veto), **serial** (awaited, in registration order, no veto). ### `agent/*` @@ -315,7 +315,7 @@ Source: [`packages/core/tools/src/index.ts:43`](../../packages/core/tools/src/in ## Services -The 10 `ctx.` services the harness provides. An abstract seam (e.g. `ctx.bash`) is implemented by a separate package; the interface is what consumers code against. +The `ctx.` services the harness provides. An abstract seam (e.g. `ctx.bash`) is implemented by a separate package; the interface is what consumers code against. ### `ctx.agentLoop` — `AgentLoop` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 0b9c8452e3..34cf410944 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -214,7 +214,7 @@ type SessionEvent = { }[T] ``` -The eleven event variants (`turn/start`, `turn/end`, `step/start`, `step/end`, `user/message`, `context/message`, `assistant/chunk`, `assistant/message`, `tool/call`, `tool/result`, `steering/message`), the `deriveMessages()` projection rules, the `TurnTrigger`/`TurnEndReason` reasons, and the turn-enclosure invariant are on **[session.md](session.md)**. How the log is made durable — the `SessionPersistence` seam, JSONL/SQLite backends, the `session/flush` checkpoint, crash recovery, and `SessionHeader` — is on **[persistence.md](persistence.md)**. +The twelve event variants (`turn/start`, `turn/end`, `step/start`, `step/end`, `user/message`, `context/message`, `assistant/chunk`, `assistant/message`, `tool/call`, `tool/result`, `steering/message`, `todo/write`), the `deriveMessages()` projection rules, the `TurnTrigger`/`TurnEndReason` reasons, and the turn-enclosure invariant are on **[session.md](session.md)**. How the log is made durable — the `SessionPersistence` seam, JSONL/SQLite backends, the `session/flush` checkpoint, crash recovery, and `SessionHeader` — is on **[persistence.md](persistence.md)**. ## The agent handle diff --git a/docs/core-data-structures/session.md b/docs/core-data-structures/session.md index 890a3a0dee..1a0e209e41 100644 --- a/docs/core-data-structures/session.md +++ b/docs/core-data-structures/session.md @@ -35,6 +35,31 @@ interface SessionEventMap { 'tool/result': { turn: number; step: number; callId: CallId; content: ContentBlock[]; isError: boolean; error?: { name: string; code: string } } /** Steering content injected between steps of a running turn. */ 'steering/message': { turn: number; content: ContentBlock[]; source: MessageSource } + /** + * The agent's whole todo list, carried as a full snapshot and replaced + * wholesale on each write — the current list is the most recent `todo/write` + * (last-write-wins on replay, no fold). Appended by an owning agent via + * `session.append('todo/write', { todos })`. + * + * NOT a {@link SurfaceEventType}: it produces no LLM message and never reaches + * `deriveMessages()`, so it carries no `surfaceOp` and stays off the surface — + * it is durable, replayable UI state, distinct from the conversation history. + * It is a `SessionEventMap` member riding the existing `session/event` emit, + * not a first-class Cordis `interface Events` notification, so it has no + * cordis-catalog row. + */ + 'todo/write': { todos: TodoItem[] } +} +``` + +### `TodoItem` — one todo-list entry + +The unit of the `todo/write` event's whole-list snapshot. Deliberately minimal — a `content` line and a three-state `status` (no id, priority, or `activeForm`): the list is replaced wholesale on every write, so entries need no stable identity, and the status triple is exactly the ACP `PlanEntryStatus`, so a UI bridge can map a todo list onto an ACP `plan` 1:1 (synthesizing the priority ACP additionally requires). See the [todo_write RFC](../rfc/implemented/feature/2026-06-29-todo-write-tool.md). + +```ts type-equiv +export interface TodoItem { + content: string + status: 'pending' | 'in_progress' | 'completed' } ``` diff --git a/docs/module-graph.md b/docs/module-graph.md index 137538a0f9..2267dd327d 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -58,6 +58,9 @@ graph TD tool-bash --> bash tool-bash --> llm tool-bash --> tools + tool-todo --> agent + tool-todo --> session + tool-todo --> tools agent-core --> agent agent-core --> agent-loop agent-core --> invariants @@ -120,6 +123,7 @@ graph TD | `agent-loop` | `agent`, `llm`, `session`, `session-persistence`, `system-prompt`, `tools` | | `subagent` | `agent`, `llm`, `tools` | | `tool-bash` | `agent`, `bash`, `llm`, `tools` | +| `tool-todo` | `agent`, `session`, `tools` | | `agent-core` | `agent`, `agent-loop`, `invariants`, `llm`, `session`, `system-prompt`, `tool-bash`, `tools` | | `subagent-acp` | `agent`, `llm`, `subagent` | | `subagent-inprocess` | `agent`, `llm`, `session`, `subagent` | diff --git a/docs/rfc/README.md b/docs/rfc/README.md index 07d3418bcb..348a7fcdaf 100644 --- a/docs/rfc/README.md +++ b/docs/rfc/README.md @@ -85,6 +85,7 @@ Do NOT write one for a mechanical or local choice (a variable name, a one-file r | [Compaction as a capability seam (abstract contract + basic backend)](implemented/feature/2026-06-18-compaction-capability-seam.md) | 2026-06-18 | | [Subagent capability seam](implemented/feature/2026-06-21-subagent-capability-seam.md) | 2026-06-21 | | [ACP subagent backend (out-of-process delegation)](implemented/feature/2026-06-22-acp-subagent-backend.md) | 2026-06-22 | +| [The `todo_write` tool — model task list as event-sourced session state](implemented/feature/2026-06-29-todo-write-tool.md) | 2026-06-29 | ### Simplification diff --git a/docs/rfc/implemented/feature/2026-06-29-todo-write-tool.md b/docs/rfc/implemented/feature/2026-06-29-todo-write-tool.md new file mode 100644 index 0000000000..a2287918f9 --- /dev/null +++ b/docs/rfc/implemented/feature/2026-06-29-todo-write-tool.md @@ -0,0 +1,58 @@ +# RFC: The `todo_write` tool — model task list as event-sourced session state + +Status: implemented + +## Problem + +The harness gives the model bash and subagent tools but no way to record a structured task list. A todo list serves two co-equal purposes: it steers the model to plan multi-step work and keep the active task unambiguous (at most one active, exactly one while work remains), and it gives the human a live progress checklist. The ACP protocol has a native `plan` sessionUpdate that editors (Zed) already render, but the bridge never emitted one. Every reference coding agent surveyed (claude-code, opencode, codex, oh-my-pi, pi) ships some form of this; the harness had nothing. + +## Decision + +Add a model-facing `todo_write(todos: [{ content, status }])` tool whose whole-list state lives on the event-sourced session log as a new `todo/write` `SessionEventMap` variant. Both the stdio UI and the ACP bridge render off the existing `session/event` — the ACP bridge maps the list to a `plan` sessionUpdate. + +### Whole-list replace, three-state status + +The model sends the ENTIRE list every call; the new list replaces the old (last-write-wins on replay). This is the shape claude-code V1, opencode, and codex `update_plan` all use, and the shape the model is most trained on — no per-item ids, no delta protocol. `status` is exactly `pending | in_progress | completed`: the same triple as codex `update_plan` and, crucially, **identical to the ACP `PlanEntryStatus`**, so the bridge maps it 1:1 with no lossy translation. + +### State on the session log, not a service + +The list is appended as a `todo/write` event carrying the full `{ todos }` snapshot. The harness is event-sourced — the LLM history, tool calls, and turn structure all live on the log — so the todo list lives there too. This buys durability, replay, and `session/load` reconstruction for free: a reopened session re-derives the current list (the last `todo/write`) and the ACP bridge re-emits the `plan` on load, with no separate persistence backend, no in-memory service to rehydrate, and no extra wiring. An in-memory `ctx.todos` service would have had to reinvent all of that. + +### NOT a surface event + +`todo/write` is deliberately excluded from `SurfaceEventType`. The surface is the projection that produces the LLM message history (`deriveMessages()`); a todo write produces no conversation message. So it carries no `surfaceOp`, never joins the surface linked list, and never reaches `deriveMessages()` — it is durable, replayable *UI* state that travels alongside the conversation without being part of it. (The dev-mode invariants still require it to sit inside an open turn, which it always does: it is appended mid-step during a tool call.) + +### Priority synthesized only at the ACP boundary + +ACP's `PlanEntry` requires `content` + `priority` + `status`, but a `TodoItem` has no priority — the model never reasons about it. Rather than burden the schema with a field the model must always supply, the bridge synthesizes a constant `priority: 'medium'` on every entry when it builds the `plan`. Priority is an ACP wire requirement, not a harness concept, so it lives at exactly the boundary that needs it. + +### Dropped vs claude-code V1: `activeForm`, id, priority + +claude-code V1's item is `{ content, status, activeForm }`; later (V2) it grew ids, dependencies, and ownership — but only to support agent *swarms* (disk-backed, lock-guarded, per-item mutation). This tool keeps the item at the minimum: `{ content, status }`. No `activeForm` (the present-continuous label) — the UI shows `content`; no id — whole-list replace needs no stable identity; no priority — see above. Each dropped field is one less thing the model must produce on every call. + +### Single owner — no swarm machinery (YAGNI) + +The list belongs to the ONE agent session that called the tool (`exec.agent.session`); a non-agent caller is rejected. There is deliberately no shared/multi-owner scope, no capability seam (interface/impl/consumer), no scope resolver, and no delta protocol. The harness does have subagents, and a shared cross-agent list is conceivable — but building that now means designing for a form the product does not yet have. The whole-list-replace + single-owner shape is what claude-code V1, opencode, and codex all ship; if a shared list is ever needed, the on-log representation would change to per-item deltas (so concurrent writers can't clobber each other) and a scope resolver would choose the target log. That is a future RFC, not speculative scaffolding today. + +### Validation: the cheap middle + +The schema enforces type/required/enum. Beyond that, `execute` rejects empty or duplicate `content` and more than one `in_progress` task. claude-code leaves single-in-progress to the prompt; oh-my-pi enforces it in code. We take the middle: enforce the cheap invariants that make a plan *coherent* (no blank tasks, no dupes, at most one active), but leave ordering and the discipline of keeping the list current to the model via the tool description. A rejected write returns an `isError` result so the model self-corrects. + +## Why no cordis-catalog entry / no `@mode` + +`todo/write` is a member of `SessionEventMap`, not a first-class cordis `interface Events` event. The catalog generator (`scripts/gen-cordis-catalog.ts`) scans `interface Events` declarations; a `SessionEventMap` variant rides the existing `session/event` emit and produces no new catalog row. So it carries no `@mode` tag (which the generator requires only on `interface Events` members) — adding one would be meaningless. + +## Testing + +Four tiers, designed up front: +- **Unit** — the session event (append/snapshot-clone/last-write-wins/not-on-surface); the tool (schema shape, arg validation via the real `ctx.tools.execute`, value validation, the event append + replacement, no-agent rejection, `presentCall`, HMR-safety); the ACP `todosToPlan` mapping; the stdio render arm. +- **Real-Loader path** — the plugin run through `Loader.unwrapExports`, asserting the namespace export shape survives (it HAS `inject`, so a stray default would crash at load — postmortem/0001). +- **Full-loop integration** — a scripted mock model calls `todo_write` through the real agent loop; the `todo/write` event lands and a second call replaces it. +- **`session/load` replay** — a persisted `todo/write` re-emits the `plan` update when a fresh ACP bridge loads the session. +- **With-key e2e + snapshot** — a real prompt induces a `todo_write`; the snapshot golden gains the `plan` notification and the log event. + +## Alternatives rejected + +- **In-memory `ctx.todos` service** — would reinvent durability, replay, and `session/load` reconstruction the log gives for free. +- **Per-item delta protocol** — only needed for a shared multi-owner list, which is out of scope; whole-list replace is simpler and matches the references. +- **Tool in `core/`** — `todo_write` is an extension tool registering on `ctx.tools`, not part of the spine; it lives in its own `packages/todo/` group like other tool families. diff --git a/examples/AGENTS.md b/examples/AGENTS.md index 2c2b2a44f1..c5a797f5df 100644 --- a/examples/AGENTS.md +++ b/examples/AGENTS.md @@ -20,7 +20,7 @@ A keyless smoke that spawns the example from a temp cwd must set `TSX_TSCONFIG_P | Example | Keyless smoke | With-key smoke | |---|---|---| | `echo-agent` | `tests/echo.e2e.ts` — boots the real `cordis.yml`, drives the echo tool round-trip and the direct canned reply | **N/A — keyless by nature** (the `mock-echo` model has no real provider) | -| `coding-agent` | `tests/keyless-smoke.e2e.ts` — boots the full real tree (dummy key, no prompt → no model call), asserts banner + clean exit | `tests/{full-loop,coding-task,resume,compaction}.e2e.ts` — real model + real bash, world-verified | +| `coding-agent` | `tests/keyless-smoke.e2e.ts` — boots the full real tree (dummy key, no prompt → no model call), asserts banner + clean exit | `tests/{full-loop,coding-task,resume,compaction,todo-write}.e2e.ts` — real model + real bash + real todo_write, world-verified | | `acp-agent` | `pnpm run test:snapshot` — boots the real ACP subprocess and replays a recorded session keyless; `tests/acp.e2e.ts` also asserts stdout purity without a key | `tests/acp.e2e.ts` — real ACP prompt, verifies a file the agent wrote | See [the root AGENTS.md](../AGENTS.md) for repo-wide conventions and [docs/architecture.md](../docs/architecture.md) for the design. diff --git a/examples/README.md b/examples/README.md index 3fd9259e36..367ec84214 100644 --- a/examples/README.md +++ b/examples/README.md @@ -15,7 +15,7 @@ Run with: `pnpm run demo:echo`. When prompted, type "echo " to trigge ## coding-agent -The real thing: DeepSeek V4 + the bash tool suite on the same `@deepseek-ai/dsh-stdio-agent` app. Where echo-agent proves the skeleton with mocks, this is a usable coding assistant. +The real thing: DeepSeek V4 + the bash tool suite, `subagent` delegation, and the `todo_write` task tracker on the same `@deepseek-ai/dsh-stdio-agent` app. Where echo-agent proves the skeleton with mocks, this is a usable coding assistant. Run with: `pnpm run demo:coding` (needs `DEEPSEEK_API_KEY` in the environment or a gitignored repo-root `.env`). See [coding-agent/README.md](coding-agent/README.md) for details. diff --git a/examples/acp-agent/cordis.snapshot.yml b/examples/acp-agent/cordis.snapshot.yml index 5f36a11efa..90c8dd2daf 100644 --- a/examples/acp-agent/cordis.snapshot.yml +++ b/examples/acp-agent/cordis.snapshot.yml @@ -16,7 +16,9 @@ - id: llm-replay name: '@deepseek-ai/dsh-llm-replay' -# Local bash executor (the agent's only tool, via agent-core's tool-bash schema). +# Local bash executor for agent-core's tool-bash schema. +# FIXME(config-comments): keep this executor note from implying bash is the +# whole tool set; subagent and todo_write are loaded below. - id: bash name: '@deepseek-ai/dsh-bash-local' config: @@ -42,6 +44,12 @@ a fresh child agent (it works in its own context and returns only its final result) — give it a complete, standalone instruction. + For multi-step work, use the todo_write tool to track a task list: + send the WHOLE list each call (it replaces the previous one), keep at + most one task in_progress (exactly one while work remains), and mark a + task completed as soon as it is done. Skip it for trivial single-step + tasks. + # The subagent seam + both in-process backends + two model-facing tools — # identical to cordis.yml's wiring (only the LLM backend differs above): spawn # and fork are each reachable via a dsh-tool-subagent bound to it with a distinct @@ -70,3 +78,8 @@ config: provider: fork toolName: subagent_fork + +# The model-facing todo_write tool — identical to cordis.yml's wiring, so a +# replayed todo_write tool call resolves to a real tool during snapshot replay. +- id: tool-todo + name: '@deepseek-ai/dsh-tool-todo' diff --git a/examples/acp-agent/cordis.yml b/examples/acp-agent/cordis.yml index a00d0e6036..96071ab564 100644 --- a/examples/acp-agent/cordis.yml +++ b/examples/acp-agent/cordis.yml @@ -23,7 +23,9 @@ - deepseek-v4-flash - deepseek-v4-pro -# Local bash executor (the agent's only tool, via agent-core's tool-bash schema). +# Local bash executor for agent-core's tool-bash schema. +# FIXME(config-comments): keep this executor note from implying bash is the +# whole tool set; subagent and todo_write are loaded below. - id: bash name: '@deepseek-ai/dsh-bash-local' config: @@ -51,6 +53,12 @@ a fresh child agent (it works in its own context and returns only its final result) — give it a complete, standalone instruction. + For multi-step work, use the todo_write tool to track a task list: + send the WHOLE list each call (it replaces the previous one), keep at + most one task in_progress (exactly one while work remains), and mark a + task completed as soon as it is done. Skip it for trivial single-step + tasks. + # The subagent seam + both in-process backends + two model-facing tools, as leaf # entries after the app (which provides ctx.agents/ctx.tools). spawn (a fresh # child) and fork (a child seeded with the parent's completed-turn prefix) are @@ -81,3 +89,8 @@ config: provider: fork toolName: subagent_fork + +# The model-facing todo_write tool: whole-list task tracking written to the +# session log (todo/write), surfaced to the ACP client as a `plan` update. +- id: tool-todo + name: '@deepseek-ai/dsh-tool-todo' diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index 42e9107c04..94f18e64d3 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -52,6 +52,7 @@ const SCENARIOS: Scenario[] = [ { name: 'reject-extra-dirs', hasModelTurn: false, recorded: false }, { name: 'text-turn', hasModelTurn: true, recorded: true }, { name: 'tool-call-turn', hasModelTurn: true, recorded: true }, + { name: 'todo-plan', hasModelTurn: true, recorded: true }, { name: 'workspace-edit', hasModelTurn: true, recorded: true }, { name: 'multi-turn', hasModelTurn: true, recorded: true }, { name: 'error-finish', hasModelTurn: true, recorded: false }, diff --git a/examples/acp-agent/tests/snapshots/todo-plan/input.json b/examples/acp-agent/tests/snapshots/todo-plan/input.json new file mode 100644 index 0000000000..6cc82bdcae --- /dev/null +++ b/examples/acp-agent/tests/snapshots/todo-plan/input.json @@ -0,0 +1,7 @@ +{ + "steps": [ + { "op": "initialize" }, + { "op": "newSession" }, + { "op": "prompt", "text": "Use the todo_write tool to record a plan with exactly three todos: \"read the code\" (in_progress), \"write the fix\" (pending), \"run the tests\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop." } + ] +} diff --git a/examples/acp-agent/tests/snapshots/todo-plan/session.jsonl b/examples/acp-agent/tests/snapshots/todo-plan/session.jsonl new file mode 100644 index 0000000000..6fc52b6a4b --- /dev/null +++ b/examples/acp-agent/tests/snapshots/todo-plan/session.jsonl @@ -0,0 +1,124 @@ +{"type":"session","version":0,"id":"259ed557-03cf-4f50-9592-fc7fdbece7f3","createdAt":1782701599718,"cwd":"/tmp/acp-snap-cwd-4xZzZ9"} +{"type":"turn/start","seq":0,"time":1782701599722,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1782701599722,"data":{"content":[{"type":"text","text":"Use the todo_write tool to record a plan with exactly three todos: \"read the code\" (in_progress), \"write the fix\" (pending), \"run the tests\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1782701599722,"data":{"turn":1,"step":1}} +{"type":"assistant/chunk","seq":3,"time":1782701600164,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":4,"time":1782701600164,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":5,"time":1782701600271,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":6,"time":1782701600298,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":7,"time":1782701600299,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":8,"time":1782701600299,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":9,"time":1782701600299,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" use"}}} +{"type":"assistant/chunk","seq":10,"time":1782701600299,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" todo"}}} +{"type":"assistant/chunk","seq":11,"time":1782701600325,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_write"}}} +{"type":"assistant/chunk","seq":12,"time":1782701600326,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":13,"time":1782701600326,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" record"}}} +{"type":"assistant/chunk","seq":14,"time":1782701600354,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":15,"time":1782701600354,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" plan"}}} +{"type":"assistant/chunk","seq":16,"time":1782701600355,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":17,"time":1782701600355,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":18,"time":1782701600355,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" three"}}} +{"type":"assistant/chunk","seq":19,"time":1782701600383,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" todos"}}} +{"type":"assistant/chunk","seq":20,"time":1782701600383,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":21,"time":1782701600409,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" then"}}} +{"type":"assistant/chunk","seq":22,"time":1782701600438,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":23,"time":1782701600438,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":24,"time":1782701600438,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" D"}}} +{"type":"assistant/chunk","seq":25,"time":1782701600465,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":26,"time":1782701600466,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":27,"time":1782701600568,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":28,"time":1782701600568,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":29,"time":1782701600568,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":30,"time":1782701600568,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":31,"time":1782701600576,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"t"}}} +{"type":"assistant/chunk","seq":32,"time":1782701600577,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"odos"}}} +{"type":"assistant/chunk","seq":33,"time":1782701600577,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":34,"time":1782701600577,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":35,"time":1782701600604,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"["}}} +{"type":"assistant/chunk","seq":36,"time":1782701600605,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"{\""}}} +{"type":"assistant/chunk","seq":37,"time":1782701600605,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"content"}}} +{"type":"assistant/chunk","seq":38,"time":1782701600605,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"\":"}}} +{"type":"assistant/chunk","seq":39,"time":1782701600605,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":40,"time":1782701600631,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"read"}}} +{"type":"assistant/chunk","seq":41,"time":1782701600631,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":" the"}}} +{"type":"assistant/chunk","seq":42,"time":1782701600632,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":" code"}}} +{"type":"assistant/chunk","seq":43,"time":1782701600632,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"\","}}} +{"type":"assistant/chunk","seq":44,"time":1782701600632,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":45,"time":1782701600632,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"status"}}} +{"type":"assistant/chunk","seq":46,"time":1782701600659,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"\":"}}} +{"type":"assistant/chunk","seq":47,"time":1782701600660,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":48,"time":1782701600660,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"in"}}} +{"type":"assistant/chunk","seq":49,"time":1782701600660,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"_pro"}}} +{"type":"assistant/chunk","seq":50,"time":1782701600660,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"gress"}}} +{"type":"assistant/chunk","seq":51,"time":1782701600660,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"\"},"}}} +{"type":"assistant/chunk","seq":52,"time":1782701600686,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":" {\""}}} +{"type":"assistant/chunk","seq":53,"time":1782701600687,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"content"}}} +{"type":"assistant/chunk","seq":54,"time":1782701600687,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"\":"}}} +{"type":"assistant/chunk","seq":55,"time":1782701600687,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":56,"time":1782701600687,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"write"}}} +{"type":"assistant/chunk","seq":57,"time":1782701600687,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":" the"}}} +{"type":"assistant/chunk","seq":58,"time":1782701600715,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":" fix"}}} +{"type":"assistant/chunk","seq":59,"time":1782701600715,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"\","}}} +{"type":"assistant/chunk","seq":60,"time":1782701600715,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":61,"time":1782701600715,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"status"}}} +{"type":"assistant/chunk","seq":62,"time":1782701600716,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"\":"}}} +{"type":"assistant/chunk","seq":63,"time":1782701600716,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":64,"time":1782701600744,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"pending"}}} +{"type":"assistant/chunk","seq":65,"time":1782701600744,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"\"},"}}} +{"type":"assistant/chunk","seq":66,"time":1782701600744,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":" {\""}}} +{"type":"assistant/chunk","seq":67,"time":1782701600744,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"content"}}} +{"type":"assistant/chunk","seq":68,"time":1782701600744,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"\":"}}} +{"type":"assistant/chunk","seq":69,"time":1782701600744,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":70,"time":1782701600770,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"run"}}} +{"type":"assistant/chunk","seq":71,"time":1782701600770,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":" the"}}} +{"type":"assistant/chunk","seq":72,"time":1782701600770,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":" tests"}}} +{"type":"assistant/chunk","seq":73,"time":1782701600770,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"\","}}} +{"type":"assistant/chunk","seq":74,"time":1782701600770,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":75,"time":1782701600771,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"status"}}} +{"type":"assistant/chunk","seq":76,"time":1782701600798,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"\":"}}} +{"type":"assistant/chunk","seq":77,"time":1782701600799,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":78,"time":1782701600799,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"pending"}}} +{"type":"assistant/chunk","seq":79,"time":1782701600799,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":80,"time":1782701600799,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"}]"}}} +{"type":"assistant/chunk","seq":81,"time":1782701600826,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":82,"time":1782701600884,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use todo_write to record a plan with exactly three todos, then reply with DONE."}}}} +{"type":"assistant/chunk","seq":83,"time":1782701600884,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}}}} +{"type":"assistant/chunk","seq":84,"time":1782701600884,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1706,"outputTokens":113,"cacheReadTokens":0,"reasoningTokens":23}}}} +{"type":"assistant/chunk","seq":85,"time":1782701600885,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":86,"time":1782701600886,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use todo_write to record a plan with exactly three todos, then reply with DONE."},{"type":"tool-call","id":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}],"usage":{"inputTokens":1706,"outputTokens":113,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85],"surfaceOp":"append"} +{"type":"tool/call","seq":87,"time":1782701600887,"data":{"turn":1,"step":1,"callId":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}} +{"type":"todo/write","seq":88,"time":1782701600887,"data":{"todos":[{"content":"read the code","status":"in_progress"},{"content":"write the fix","status":"pending"},{"content":"run the tests","status":"pending"}]}} +{"type":"tool/result","seq":89,"time":1782701600887,"data":{"turn":1,"step":1,"callId":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","content":[{"type":"text","text":"Updated todo list: 2 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[87],"surfaceOp":"append"} +{"type":"step/end","seq":90,"time":1782701600888,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":91,"time":1782701600888,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":92,"time":1782701601276,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":93,"time":1782701601276,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":94,"time":1782701601382,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" todo"}}} +{"type":"assistant/chunk","seq":95,"time":1782701601410,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" list"}}} +{"type":"assistant/chunk","seq":96,"time":1782701601437,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" was"}}} +{"type":"assistant/chunk","seq":97,"time":1782701601438,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" set"}}} +{"type":"assistant/chunk","seq":98,"time":1782701601438,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" successfully"}}} +{"type":"assistant/chunk","seq":99,"time":1782701601466,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":100,"time":1782701601467,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Now"}}} +{"type":"assistant/chunk","seq":101,"time":1782701601467,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":102,"time":1782701601467,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" just"}}} +{"type":"assistant/chunk","seq":103,"time":1782701601494,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" need"}}} +{"type":"assistant/chunk","seq":104,"time":1782701601494,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":105,"time":1782701601495,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":106,"time":1782701601495,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":107,"time":1782701601520,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":108,"time":1782701601521,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" single"}}} +{"type":"assistant/chunk","seq":109,"time":1782701601521,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} +{"type":"assistant/chunk","seq":110,"time":1782701601521,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" D"}}} +{"type":"assistant/chunk","seq":111,"time":1782701601550,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":112,"time":1782701601550,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":113,"time":1782701601550,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":114,"time":1782701601551,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}} +{"type":"assistant/chunk","seq":115,"time":1782701601551,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} +{"type":"assistant/chunk","seq":116,"time":1782701601551,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The todo list was set successfully. Now I just need to reply with the single word DONE."}}}} +{"type":"assistant/chunk","seq":117,"time":1782701601551,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} +{"type":"assistant/chunk","seq":118,"time":1782701601551,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":174,"outputTokens":23,"cacheReadTokens":1664,"reasoningTokens":20}}}} +{"type":"assistant/chunk","seq":119,"time":1782701601551,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":120,"time":1782701601551,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The todo list was set successfully. Now I just need to reply with the single word DONE."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":174,"outputTokens":23,"cacheReadTokens":1664,"reasoningTokens":20}},"sourceEventSeqs":[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],"surfaceOp":"append"} +{"type":"step/end","seq":121,"time":1782701601552,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":122,"time":1782701601552,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl new file mode 100644 index 0000000000..052b86fca0 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl @@ -0,0 +1,51 @@ +{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" use"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" todo"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_write"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" record"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" plan"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" exactly"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" three"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" todos"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" then"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" D"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","title":"Update todo list","kind":"other","status":"in_progress","rawInput":[{"content":"read the code","status":"in_progress"},{"content":"write the fix","status":"pending"},{"content":"run the tests","status":"pending"}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"plan","entries":[{"content":"read the code","priority":"medium","status":"in_progress"},{"content":"write the fix","priority":"medium","status":"pending"},{"content":"run the tests","priority":"medium","status":"pending"}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_OK2ZF1DYrsKHQQtxfQlJ0810","status":"completed","content":[{"type":"content","content":{"type":"text","text":"Updated todo list: 2 pending, 1 in progress, 0 completed."}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" todo"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" list"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" was"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" set"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" successfully"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Now"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" just"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" need"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" single"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" word"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" D"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"D"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ONE"}}}} +{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} diff --git a/examples/coding-agent/README.md b/examples/coding-agent/README.md index 76fbb7a237..e62397348b 100644 --- a/examples/coding-agent/README.md +++ b/examples/coding-agent/README.md @@ -12,7 +12,7 @@ The first REAL agent wiring: DeepSeek V4 + the bash tool suite + stdio chat pnpm run demo:coding ``` -Type a coding task. The agent's only tools are `bash` (+ `bash_output` / `bash_kill` for background tasks): file reads, writes, searches, and test runs all happen through shell commands, each in a fresh `bash -c` (the system prompt tells the model to pass `workdir` instead of `cd`). Reasoning streams dimmed; tool calls/results render inline. +Type a coding task. The agent works through `bash` (+ `bash_output` / `bash_kill` for background tasks): file reads, writes, searches, and test runs all happen through shell commands, each in a fresh `bash -c` (the system prompt tells the model to pass `workdir` instead of `cd`). It can also delegate with `subagent`/`subagent_fork` and track multi-step work with `todo_write` (a whole-list task tracker rendered as a checklist). Reasoning streams dimmed; tool calls/results render inline. ``` > fix the failing test in /path/to/project diff --git a/examples/coding-agent/cordis.yml b/examples/coding-agent/cordis.yml index d239db3a7e..82253a0aef 100644 --- a/examples/coding-agent/cordis.yml +++ b/examples/coding-agent/cordis.yml @@ -28,7 +28,9 @@ - deepseek-v4-flash - deepseek-v4-pro -# Local bash executor (the model's only tool, via agent-core's tool-bash schema). +# Local bash executor for agent-core's tool-bash schema. +# FIXME(config-comments): keep this executor note from implying bash is the +# whole tool set; subagent and todo_write are loaded below. - id: bash name: '@deepseek-ai/dsh-bash-local' config: @@ -44,7 +46,7 @@ # under ./.sessions); unset starts a fresh session each run. resumeSessionId: !!js process.env.RESUME_SESSION_ID persistenceRoot: './.sessions' - welcome: 'coding-agent ready. Give it a coding task (its tools are bash and subagent).' + welcome: 'coding-agent ready. Give it a coding task (its tools are bash, subagent, and todo_write).' systemPrompt: | You are coding-agent, a CLI coding assistant. @@ -65,6 +67,12 @@ failures before moving on. Verify your work by running the code or tests. Keep answers brief and factual. + For multi-step work, use the todo_write tool to track a task list: + send the WHOLE list each call (it replaces the previous one), keep at + most one task in_progress (exactly one while work remains), and mark a + task completed as soon as it is done. Skip it for trivial single-step + tasks. + # Automatic context compaction: when the derived history approaches the model's # context window, summarize an older range into a checkpoint so a long-running # or tool-heavy session keeps fitting. A leaf entry (needs ctx.llm + the @@ -106,3 +114,8 @@ config: provider: fork toolName: subagent_fork + +# The model-facing todo_write tool: whole-list task tracking written to the +# session log (todo/write), rendered as a stdio checklist / ACP plan. +- id: tool-todo + name: '@deepseek-ai/dsh-tool-todo' diff --git a/examples/coding-agent/tests/harness.ts b/examples/coding-agent/tests/harness.ts index 207652f69b..7ce24913cf 100644 --- a/examples/coding-agent/tests/harness.ts +++ b/examples/coding-agent/tests/harness.ts @@ -8,6 +8,7 @@ import AgentRegistry from '@deepseek-ai/dsh-agent' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-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' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' @@ -15,14 +16,21 @@ import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic' /** * Shared harness for the coding-agent e2e suites: the full plugin stack - * with the real DeepSeek adapter and the real bash tool. Lives outside the - * *.e2e.ts pattern so importing it never re-registers another file's tests. + * with the real DeepSeek adapter and the real bash + todo_write tools. Lives + * outside the *.e2e.ts pattern so importing it never re-registers another + * file's tests. */ -export const SYSTEM_PROMPT = 'You are a coding agent. Your only tool is bash; ' - + 'do file operations with cat/grep/heredocs, check [exit code: N] markers, ' +export const SYSTEM_PROMPT = 'You are a coding agent. Use bash for file operations ' + + 'with cat/grep/heredocs; check [exit code: N] markers, ' + 'and report results briefly.' +/** System prompt for the todo_write e2e: nudges the model to plan with the tool. */ +export const TODO_SYSTEM_PROMPT = 'You are a coding agent. For multi-step work, ' + + 'use the todo_write tool to track a task list: send the WHOLE list each call, ' + + 'keep at most one task in_progress (exactly one while work remains), and mark ' + + 'a task completed as soon as it is done.' + /** Options for {@link codingHarness}. */ export interface CodingHarnessOptions { /** Durable JSONL persistence root (the resume suite needs it; others stay file-free). */ @@ -46,6 +54,7 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 }) await ctx.plugin(ToolBash) + await ctx.plugin(ToolTodo) // Compaction is opt-in: only the compaction e2e loads it, with a lowered // contextWindow/retainTokens so a short real session crosses the threshold. if (options.compact !== undefined) await ctx.plugin(BasicCompactService, options.compact) diff --git a/examples/coding-agent/tests/todo-write.e2e.ts b/examples/coding-agent/tests/todo-write.e2e.ts new file mode 100644 index 0000000000..33cac531cf --- /dev/null +++ b/examples/coding-agent/tests/todo-write.e2e.ts @@ -0,0 +1,49 @@ +import { afterEach, describe, expect, it } from 'vitest' +import type { Context } from 'cordis' +import { AgentId } from '@deepseek-ai/dsh-agent' +import { codingHarness, TODO_SYSTEM_PROMPT, waitForIdle } from './harness.ts' + +/** + * A REAL model drives the REAL todo_write tool: verify the WORLD (the session + * log gains a todo/write event whose snapshot the model actually produced), not + * the agent's self-report. Key-gated (see vitest.e2e.config.ts). + */ + +let ctx: Context | undefined + +afterEach(async () => { + await ctx?.fiber.dispose() + ctx = undefined +}) + +describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a plan', () => { + it('appends a todo/write event with the model-produced task list', async () => { + ctx = await codingHarness(process.cwd()) + const agent = ctx.agentLoop.create(AgentId('e2e-todo'), { + model: 'deepseek-v4-flash', + systemPrompt: TODO_SYSTEM_PROMPT, + }) + + agent.send([{ 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.' }]) + await waitForIdle(ctx, agent) + + const events = [...agent.session.events] + + // The model actually called the tool. + const calls = events.filter(event => event.type === 'tool/call') + expect(calls.some(event => event.data.name === 'todo_write')).toBe(true) + + // And the tool wrote a todo/write event to the log — verify the WORLD. + const todoEvents = events.filter(event => event.type === 'todo/write') + expect(todoEvents.length).toBeGreaterThan(0) + + const todos = (todoEvents.at(-1)!).data.todos + expect(todos).toEqual([ + { content: 'inspect the failing test', status: 'in_progress' }, + { content: 'apply the fix', status: 'pending' }, + ]) + }, 120_000) +}) diff --git a/packages/README.md b/packages/README.md index b828fd5407..a4459d2881 100644 --- a/packages/README.md +++ b/packages/README.md @@ -13,6 +13,7 @@ Packages are grouped by modular role at `packages///`. The group dir | [`bash/`](bash/README.md) | Bash capability family: the executor seam, a local impl, and the model-facing tool | Product — stable surface | | [`compact/`](compact/README.md) | Compaction capability family: the abstract seam + a basic backend (tool deferred) | Product — stable surface | | [`subagent/`](subagent/README.md) | Subagent capability family: the provider-registry seam and the model-facing delegation tool | Product — stable surface | +| [`todo/`](todo/README.md) | Todo/planning family: the model-facing `todo_write` tool (whole-list task tracking on the session log) | Product — stable surface | | [`session-persistence/`](session-persistence/README.md) | Persistence capability family: the seam + JSONL/SQLite backends | Product — stable surface | | [`ui/`](ui/README.md) | Editor/client integration surfaces (the ACP bridge) | Product — stable surface | | [`support/`](support/README.md) | Dev/test/example infrastructure (invariants, stdio UI, replay adapter) | Support — lower compatibility expectations | @@ -47,6 +48,7 @@ dsh-subagent-spawn ← dsh-subagent, dsh-agent, dsh-session, dsh-llm (in-proces dsh-subagent-fork ← dsh-subagent-spawn, dsh-agent, dsh-session (in-process child seeded from parent log) dsh-subagent-acp ← dsh-subagent, dsh-agent, dsh-llm, @agentclientprotocol/sdk (out-of-process child over ACP) dsh-tool-subagent ← dsh-subagent, dsh-tools, dsh-agent (model-facing delegation tool) +dsh-tool-todo ← dsh-tools, dsh-agent, dsh-session (model-facing todo_write tool; whole list on the session log) dsh-agent-core ← timer, dsh-llm, dsh-session, dsh-system-prompt, dsh-tools, dsh-agent, dsh-invariants, dsh-tool-bash, dsh-agent-loop (the providerless spine, as one bundle plugin) dsh-stdio-agent ← dsh-agent-core, dsh-ui-stdio, dsh-session-persistence-jsonl, dsh-agent, dsh-session (stdio chat APP + bin) dsh-acp-agent ← dsh-agent-core, dsh-acp, dsh-session-persistence-jsonl (ACP server APP + bin) @@ -87,6 +89,7 @@ The rule: **extension** plugins depend on interfaces, never on the concrete loop | `subagent-acp/` | `subagent` | Out-of-process backend: a child agent in a spawned subprocess, driven over the Agent Client Protocol | (registers on `ctx.subagents`) | | `subagent-mock/` | `support` | Scripted `SubagentProvider` for testing the seam through the real load path | (registers on `ctx.subagents`) | | `tool-subagent/` | `subagent` | Model-facing `subagent` delegation tool over `ctx.subagents` | (registers on `ctx.tools`) | +| `tool-todo/` | `todo` | Model-facing `todo_write` tool; writes the whole task list to the session log (`todo/write`) | (registers on `ctx.tools`) | | `brand/` | `util` | Type-only `Branded` nominal-typing primitive (no runtime code, no harness deps) | (none — type-only) | Each package has its own `README.md` with purpose, service API, events, extension points, and deliberate non-goals (TODOs). diff --git a/packages/core/session/src/types.ts b/packages/core/session/src/types.ts index 2a32c7b3f0..6ed8c4391e 100644 --- a/packages/core/session/src/types.ts +++ b/packages/core/session/src/types.ts @@ -149,6 +149,24 @@ export interface TurnEndReasonMap { export type TurnEndReason = TurnEndReasonMap[keyof TurnEndReasonMap] +/** + * One entry in an agent's todo list — the unit of the `todo/write` + * {@link SessionEventMap} event's whole-list snapshot. + * + * Deliberately minimal: a human-readable `content` line and a three-state + * `status`. No id, priority, or `activeForm` — the list is replaced wholesale + * on every write (last-write-wins), so entries need no stable identity, and the + * status triple is exactly the ACP `PlanEntryStatus`, so a UI bridge can map a + * todo list onto an ACP `plan` 1:1 (synthesizing the priority ACP additionally + * requires). + */ +export interface TodoItem { + /** What this task is — a short imperative line shown in the UI. */ + content: string + /** Lifecycle state. `in_progress` marks the single task being worked now. */ + status: 'pending' | 'in_progress' | 'completed' +} + /** * The session event vocabulary — the append-only source of truth for an * agent's whole interaction history. The LLM message history is *derived* @@ -195,6 +213,20 @@ export interface SessionEventMap { 'tool/result': { turn: number; step: number; callId: CallId; content: ContentBlock[]; isError: boolean; error?: { name: string; code: string } } /** Steering content injected between steps of a running turn. */ 'steering/message': { turn: number; content: ContentBlock[]; source: MessageSource } + /** + * The agent's whole todo list, carried as a full snapshot and replaced + * wholesale on each write — the current list is the most recent `todo/write` + * (last-write-wins on replay, no fold). Appended by an owning agent via + * `session.append('todo/write', { todos })`. + * + * NOT a {@link SurfaceEventType}: it produces no LLM message and never reaches + * `deriveMessages()`, so it carries no `surfaceOp` and stays off the surface — + * it is durable, replayable UI state, distinct from the conversation history. + * It is a `SessionEventMap` member riding the existing `session/event` emit, + * not a first-class Cordis `interface Events` notification, so it has no + * cordis-catalog row. + */ + 'todo/write': { todos: TodoItem[] } } export type SessionEventType = keyof SessionEventMap diff --git a/packages/core/session/tests/session.spec.ts b/packages/core/session/tests/session.spec.ts index 6138a479f1..27f8b5d420 100644 --- a/packages/core/session/tests/session.spec.ts +++ b/packages/core/session/tests/session.spec.ts @@ -2,7 +2,7 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import { CallId } from '@deepseek-ai/dsh-llm' import SessionStore, { SESSION_FORMAT_VERSION, Session, SessionEvent, SessionId } from '@deepseek-ai/dsh-session' -import type { SessionEventType } from '@deepseek-ai/dsh-session' +import type { SessionEventType, TodoItem } from '@deepseek-ai/dsh-session' describe('Session', () => { it('derives message history from the event log', () => { @@ -365,3 +365,63 @@ describe('SessionStore', () => { expect(events).toHaveLength(1) }) }) + +describe('todo/write event', () => { + it('appends the whole-list snapshot and isolates the log from later mutation', () => { + const session = new Session(SessionId('t1')) + const todos: TodoItem[] = [ + { content: 'plan the work', status: 'in_progress' }, + { content: 'write the code', status: 'pending' }, + ] + session.append('todo/write', { todos }) + + const event = session.events.findLast(e => e.type === 'todo/write')! + expect(event.type).toBe('todo/write') + expect(event.data.todos).toEqual(todos) + + // The append snapshots its input: mutating the caller's array afterward must + // not change what the log holds (the durable-source-of-truth contract). + todos.push({ content: 'sneak in', status: 'pending' }) + todos[0]!.status = 'completed' + expect(event.data.todos).toEqual([ + { content: 'plan the work', status: 'in_progress' }, + { content: 'write the code', status: 'pending' }, + ]) + }) + + it('is last-write-wins: the current list is the most recent todo/write', () => { + const session = new Session(SessionId('t2')) + session.append('todo/write', { todos: [{ content: 'first', status: 'pending' }] }) + session.append('todo/write', { todos: [ + { content: 'first', status: 'completed' }, + { content: 'second', status: 'in_progress' }, + ] }) + + const current = session.events.findLast(e => e.type === 'todo/write')!.data.todos + expect(current).toEqual([ + { content: 'first', status: 'completed' }, + { content: 'second', status: 'in_progress' }, + ]) + }) + + it('is NOT a surface event: it produces no derived message and joins no surface node', () => { + const session = new Session(SessionId('t3')) + session.append('user/message', { content: [{ type: 'text', text: 'q' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) + const before = session.deriveMessages().length + session.append('todo/write', { todos: [{ content: 'a task', status: 'pending' }] }) + // The todo event must not add a message to the derived history… + expect(session.deriveMessages()).toHaveLength(before) + // …and must not appear on the surface linked list. + expect(session.surface.nodes.some(node => node.seq === session.seq - 1)).toBe(false) + }) + + it('round-trips through a seeded replay identically (durable, no surfaceOp needed)', () => { + const original = new Session(SessionId('t4')) + original.append('todo/write', { todos: [{ content: 'only', status: 'completed' }] }) + // Seeding a non-surface event with no surfaceOp must not throw. + const replayed = new Session(SessionId('t4-replay'), [...original.events]) + expect(replayed.events.findLast(e => e.type === 'todo/write')!.data.todos) + .toEqual([{ content: 'only', status: 'completed' }]) + expect(replayed.seq).toBe(original.seq) + }) +}) diff --git a/packages/support/ui-stdio/src/index.ts b/packages/support/ui-stdio/src/index.ts index 070e842094..edfa82285e 100644 --- a/packages/support/ui-stdio/src/index.ts +++ b/packages/support/ui-stdio/src/index.ts @@ -110,6 +110,13 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const { content } = event.data const text = content.filter(block => block.type === 'text').map(block => block.text).join('') output.write(`\n [tool result] ${text}\n `) + } else if (event.type === 'todo/write') { + if (inReasoning) output.write('\x1B[0m') + inReasoning = false + const glyph = (status: string): string => + status === 'completed' ? '[x]' : status === 'in_progress' ? '[~]' : '[ ]' + const lines = event.data.todos.map(todo => ` ${glyph(todo.status)} ${todo.content}`).join('\n') + output.write(`\n [todos]\n${lines}\n `) } }) diff --git a/packages/support/ui-stdio/tests/ui-stdio.spec.ts b/packages/support/ui-stdio/tests/ui-stdio.spec.ts index bd5e0f7f91..7bd1fd4868 100644 --- a/packages/support/ui-stdio/tests/ui-stdio.spec.ts +++ b/packages/support/ui-stdio/tests/ui-stdio.spec.ts @@ -151,6 +151,35 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('[tool result] file.txt') }) + it('renders a todo/write session event as a glyphed checklist', async () => { + const { ctx, out } = await setup() + const session = {} as Session + ctx.emit('session/event', session, { + type: 'todo/write', seq: 1, time: 0, + data: { todos: [ + { content: 'read the code', status: 'completed' }, + { content: 'write the fix', status: 'in_progress' }, + { content: 'run the tests', status: 'pending' }, + ] }, + } as SessionEvent) + const text = out.text() + expect(text).toContain('[todos]') + expect(text).toContain('[x] read the code') + expect(text).toContain('[~] write the fix') + expect(text).toContain('[ ] run the tests') + }) + + it('resets dim styling when a todo/write interrupts reasoning', async () => { + const { ctx, out } = await setup() + const agent = makeAgent('main') + ctx.emit('agent/stream-chunk', agent, 1, 0, { type: 'reasoning-delta', index: 0, text: 'r' }) + ctx.emit('session/event', {} as Session, { + type: 'todo/write', seq: 1, time: 0, + data: { todos: [{ content: 'a task', status: 'pending' }] }, + } as SessionEvent) + expect(out.text()).toContain('\x1B[2mr\x1B[0m') + }) + it('resets dim styling when a tool/call interrupts reasoning', async () => { const { ctx, out } = await setup() const agent = makeAgent('main') diff --git a/packages/todo/README.md b/packages/todo/README.md new file mode 100644 index 0000000000..df258fab0c --- /dev/null +++ b/packages/todo/README.md @@ -0,0 +1,9 @@ +# todo/ — todo / planning capability family + +The model-facing todo tool. A single **product** package — there is no interface/implementation seam here, because the list is single-owner session state (one agent session owns its own list), not a swappable capability. + +| Package | Role | ctx key | +|---|---|---| +| `tool-todo/` | Model-facing `todo_write` tool; writes the whole list to the session log (`todo/write`) | (registers on `ctx.tools`) | + +The list lives on the event-sourced session log (`SessionEventMap['todo/write']`, owned by [`dsh-session`](../core/session)); this package is the thin consumer that appends the snapshot. UIs render off `session/event`: the [stdio UI](../support/ui-stdio) prints the list, the [ACP bridge](../ui/acp) maps it to a `plan` sessionUpdate. diff --git a/packages/todo/tool-todo/README.md b/packages/todo/tool-todo/README.md new file mode 100644 index 0000000000..fc6dc94860 --- /dev/null +++ b/packages/todo/tool-todo/README.md @@ -0,0 +1,25 @@ +# @deepseek-ai/dsh-tool-todo + +The model-facing `todo_write` tool: the agent's whole task list, replaced wholesale on each call. + +## What it does + +Registers one tool, `todo_write(todos: [{ content, status }])`, on `ctx.tools`. The model sends the ENTIRE list every call — there are no partial updates or per-item edits. Each call appends a `todo/write` event (the full list snapshot) to the calling agent's session log via `agent.session.append('todo/write', { todos })`; the current list is the most recent such event (last-write-wins on replay). + +`status` is one of `pending`, `in_progress`, `completed` — exactly the ACP `PlanEntryStatus` triple. + +## Single owner + +The list belongs to the ONE agent session that called the tool. There is no subagent/shared/swarm scope: a non-agent caller (no `exec.agent`) has nowhere to write the list and is rejected. This is a deliberate scope limit — see the RFC. + +## Validation + +Beyond the schema's type/required/enum checks, `execute` rejects an empty or duplicate `content` and more than one `in_progress` task (a coherent plan has at most one task active). Ordering and the discipline of keeping the list current are left to the model via the tool description. + +## Rendering + +The tool writes only the session event; it does not render. UIs subscribe to `session/event` and render the `todo/write` data themselves: the [stdio UI](../../support/ui-stdio) prints a glyphed checklist, and the [ACP bridge](../../ui/acp) maps the list to a `plan` sessionUpdate (synthesizing the `priority` ACP requires). + +## Export shape + +A function/namespace plugin: it exports `name` / `inject` / `apply` and NO default. A stray `export default` would collapse the module via the Loader's `unwrapExports` and drop `inject` (see [docs/postmortem/0001](../../../docs/postmortem/0001-acp-default-export-drops-inject.md)). diff --git a/packages/todo/tool-todo/package.json b/packages/todo/tool-todo/package.json new file mode 100644 index 0000000000..f2d4344f99 --- /dev/null +++ b/packages/todo/tool-todo/package.json @@ -0,0 +1,39 @@ +{ + "name": "@deepseek-ai/dsh-tool-todo", + "description": "Model-facing todo_write tool over the DeepSeek Harness event-sourced session log", + "version": "0.0.1", + "private": true, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./src/*": "./src/*", + "./package.json": "./package.json" + }, + "files": [ + "lib/index.js", + "lib/types/**/*.d.ts", + "lib/types/**/*.d.ts.map", + "src" + ], + "license": "BSD-3-Clause", + "peerDependencies": { + "@deepseek-ai/dsh-agent": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", + "@deepseek-ai/dsh-tools": "^0.0.1", + "cordis": "^4.0.0-rc.6" + }, + "devDependencies": { + "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-loop": "workspace:^", + "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", + "@deepseek-ai/dsh-system-prompt": "workspace:^", + "@deepseek-ai/dsh-tools": "workspace:^", + "cordis": "^4.0.0-rc.6" + } +} diff --git a/packages/todo/tool-todo/src/index.ts b/packages/todo/tool-todo/src/index.ts new file mode 100644 index 0000000000..912e08f269 --- /dev/null +++ b/packages/todo/tool-todo/src/index.ts @@ -0,0 +1,123 @@ +/** + * The model-facing `todo_write` tool: the agent's whole task list, replaced + * wholesale on each call. Every call appends a `todo/write` event (the full + * list snapshot) to the calling agent's session log via + * `exec.agent.session.append('todo/write', { todos })`; the current list is the + * most recent such event (last-write-wins on replay). UIs render off + * `session/event`: the stdio UI prints the checklist, the ACP bridge maps it to + * a `plan` sessionUpdate. + * + * Single owner: the list belongs to the ONE agent session that called the tool. + * There is no subagent/shared/swarm scope — a non-agent caller (no + * `exec.agent`) has nowhere to write the list and is rejected. + * + * Plugin export shape: named exports, NO default. The cordis Loader's + * `unwrapExports` does `exports.default ?? exports`, so a stray default would + * collapse the module to the bare `apply` and drop `inject`, crashing at load + * (see docs/postmortem/0001). + * + * @module @deepseek-ai/dsh-tool-todo + */ + +import type { Context } from 'cordis' +import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import { defineTool } from '@deepseek-ai/dsh-tools' +import type { TodoItem } from '@deepseek-ai/dsh-session' + +export const name = 'tool-todo' +export const inject = ['tools'] + +/** The valid {@link TodoItem} statuses, as a runtime set for input narrowing. */ +const STATUSES = ['pending', 'in_progress', 'completed'] as const + +const 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).' + +/** + * Validate the value constraints the SchemaSpec can't express and build the + * canonical {@link TodoItem}[]. + * + * `defineTool` already validates type/required/enum before `execute` runs (a + * bad `status` is rejected by the registry's `validateArgs`, never reaching + * here), so `status` is guaranteed to be one of the three enum literals. But + * `InferArgs` maps an `enum` string prop to plain `string`, so the compiler sees + * `args.todos` as `{ content: string; status: string }[]`; the + * `status as TodoItem['status']` narrowing records that registry guarantee + * rather than re-checking it (an unreachable re-check would be dead code — see + * AGENTS.md "don't validate scenarios that can't happen"). What remains is the + * value rules the DSL has no vocabulary for: non-empty unique content (stored + * trimmed, so the persisted value matches the dedupe/length key), and at most + * one `in_progress` task. + */ +function toTodoList(raw: { content: string; status: string }[]): TodoItem[] { + const todos: TodoItem[] = [] + const seen = new Set() + let inProgress = 0 + for (const item of raw) { + const content = item.content.trim() + if (content.length === 0) { + throw new Error('invalid todo: `content` must be a non-empty string') + } + if (seen.has(content)) { + throw new Error(`invalid todos: duplicate content ${JSON.stringify(content)}`) + } + seen.add(content) + const status = item.status as TodoItem['status'] + if (status === 'in_progress') inProgress++ + todos.push({ content, status }) + } + if (inProgress > 1) { + throw new Error(`invalid todos: at most one task may be in_progress, got ${inProgress}`) + } + return todos +} + +/** Register the `todo_write` tool on `ctx.tools`. */ +export function apply(ctx: Context): void { + ctx.tools.register(defineTool({ + name: 'todo_write', + description: DESCRIPTION, + parameters: { + todos: { + type: 'array', + required: true, + description: 'The COMPLETE task list, replacing any previous list.', + items: { + type: 'object', + properties: { + content: { type: 'string', required: true, description: 'What the task is — a short imperative line.' }, + status: { + type: 'string', + required: true, + enum: [...STATUSES], + description: 'pending (not started) | in_progress (now) | completed (done).', + }, + }, + }, + }, + }, + execute(args, exec): Promise { + const todos = toTodoList(args.todos) + if (!exec.agent) { + // The list is per-agent-session state; a non-agent caller (no owning + // session) has nowhere to write it. Reject rather than silently no-op. + throw new Error('todo_write requires an owning agent session') + } + exec.agent.session.append('todo/write', { todos }) + const count = (status: TodoItem['status']): number => todos.filter(t => t.status === status).length + return Promise.resolve([{ + type: 'text', + text: `Updated todo list: ${count('pending')} pending, ${count('in_progress')} in progress, ${count('completed')} completed.`, + }]) + }, + presentCall: args => ({ title: 'Update todo list', kind: 'other', rawInput: args.todos }), + })) +} diff --git a/packages/todo/tool-todo/tests/integration.spec.ts b/packages/todo/tool-todo/tests/integration.spec.ts new file mode 100644 index 0000000000..739367a699 --- /dev/null +++ b/packages/todo/tool-todo/tests/integration.spec.ts @@ -0,0 +1,107 @@ +import { describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import LlmService from '@deepseek-ai/dsh-llm' +import SessionStore from '@deepseek-ai/dsh-session' +import type { SessionEvent } from '@deepseek-ai/dsh-session' +import SystemPrompt from '@deepseek-ai/dsh-system-prompt' +import ToolRegistry from '@deepseek-ai/dsh-tools' +import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' +import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' + +/** + * Full-loop integration: a scripted mock model drives the REAL todo_write tool + * through the agent loop, exercising the same seams a live model would — the + * tool/call + tool/result session events AND the todo/write event the tool + * appends. Only the model is mocked; the tool and the session log are real. + */ +async function harness(adapter: MockAdapter): Promise { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentLoop, { agents: [] }) + await ctx.plugin(ToolTodo) + ctx.llm.registerAdapter(['mock'], adapter) + return ctx +} + +function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { + return new Promise((resolve) => { + const dispose = ctx.on('agent/status', (subject, status) => { + if (subject === agent && status === 'idle') { + dispose() + resolve() + } + }) + }) +} + +function findEvent( + log: readonly SessionEvent[], + type: T, + position: 'first' | 'last' = 'first', +): Extract { + const found = position === 'first' + ? log.find(event => event.type === type) + : log.findLast(event => event.type === type) + if (!found) throw new Error(`no ${type} event in the session log`) + return found as Extract +} + +describe('todo_write tool through the agent loop', () => { + it('model calls todo_write: a tool/call, a non-error tool/result, and a todo/write snapshot land', async () => { + const adapter = new MockAdapter([ + toolCallResponse('call-1', 'todo_write', { + todos: [ + { content: 'read the code', status: 'in_progress' }, + { content: 'write the fix', status: 'pending' }, + ], + }, 'Planning the work.'), + textResponse('Plan recorded.'), + ]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId('it-todo'), { model: 'mock' }) + + agent.send([{ type: 'text', text: 'plan a two-step task' }]) + await waitForIdle(ctx, agent) + + const log = agent.session.events + expect(findEvent(log, 'tool/call').data.name).toBe('todo_write') + expect(findEvent(log, 'tool/result').data.isError).toBe(false) + + const todoEvent = findEvent(log, 'todo/write') + expect(todoEvent.data.todos).toEqual([ + { content: 'read the code', status: 'in_progress' }, + { content: 'write the fix', status: 'pending' }, + ]) + }) + + it('a second todo_write replaces the list (last-write-wins on the log)', async () => { + const adapter = new MockAdapter([ + toolCallResponse('call-1', 'todo_write', { todos: [{ content: 'step one', status: 'in_progress' }] }), + toolCallResponse('call-2', 'todo_write', { + todos: [ + { content: 'step one', status: 'completed' }, + { content: 'step two', status: 'in_progress' }, + ], + }), + textResponse('Done planning.'), + ]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId('it-todo-2'), { model: 'mock' }) + + agent.send([{ type: 'text', text: 'plan then update' }]) + await waitForIdle(ctx, agent) + + const todoEvents = agent.session.events.filter(e => e.type === 'todo/write') + expect(todoEvents).toHaveLength(2) + expect(findEvent(agent.session.events, 'todo/write', 'last').data.todos).toEqual([ + { content: 'step one', status: 'completed' }, + { content: 'step two', status: 'in_progress' }, + ]) + }) +}) diff --git a/packages/todo/tool-todo/tests/tool-todo.spec.ts b/packages/todo/tool-todo/tests/tool-todo.spec.ts new file mode 100644 index 0000000000..8b1c504840 --- /dev/null +++ b/packages/todo/tool-todo/tests/tool-todo.spec.ts @@ -0,0 +1,167 @@ +import { describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import Loader from '@cordisjs/plugin-loader' +import { CallId } from '@deepseek-ai/dsh-llm' +import SystemPrompt from '@deepseek-ai/dsh-system-prompt' +import ToolRegistry from '@deepseek-ai/dsh-tools' +import { Session, SessionId } from '@deepseek-ai/dsh-session' +import type { TodoItem } from '@deepseek-ai/dsh-session' +import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import * as tool from '../src/index.ts' + +/** + * Drives the REAL plugin body: mounts `dsh-tool-todo` on a real `ToolRegistry` + * and invokes the registered `todo_write` tool through `ctx.tools.execute`, + * with a fake parent Agent carrying a real `Session` — so the append the tool + * makes is observable on a genuine session log (only the agent wrapper is a + * stand-in; the session and the tool are the shipping code). + */ + +/** A parent Agent backed by a real Session — the tool reads `agent.session`. */ +function agentWithSession(id = 'parent-1'): Agent & { session: Session } { + const session = new Session(SessionId(id)) + return { id: AgentId(id), session } as unknown as Agent & { session: Session } +} + +async function setup(): Promise { + const ctx = new Context() + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(tool) + return ctx +} + +let callCounter = 0 +function callTodo(ctx: Context, args: unknown, over: { agent?: Agent | undefined } = {}) { + const agent = 'agent' in over ? over.agent : agentWithSession() + return ctx.tools.execute({ + callId: CallId(`call-${++callCounter}`), + name: 'todo_write', + arguments: args, + ...agent ? { agent } : {}, + }) +} + +function text(result: { content: { type: string; text?: string }[] }): string { + return result.content.filter(b => b.type === 'text').map(b => b.text).join('') +} + +describe('dsh-tool-todo', () => { + it('registers a `todo_write` tool whose schema is an array of {content,status}', async () => { + const ctx = await setup() + const schema = ctx.tools.schemas().find(s => s.name === 'todo_write') + expect(schema).toBeDefined() + const props = (schema!.parameters as { properties?: Record }).properties ?? {} + expect(Object.keys(props)).toEqual(['todos']) + const todos = props.todos as { type: string; items?: { properties?: Record } } + expect(todos.type).toBe('array') + const itemProps = todos.items?.properties ?? {} + expect(Object.keys(itemProps).sort()).toEqual(['content', 'status']) + expect(itemProps.status?.enum).toEqual(['pending', 'in_progress', 'completed']) + }) + + it('appends a todo/write event carrying the whole list to the calling session', async () => { + const ctx = await setup() + const agent = agentWithSession('writer') + const todos: TodoItem[] = [ + { content: 'plan', status: 'in_progress' }, + { content: 'build', status: 'pending' }, + ] + const result = await callTodo(ctx, { todos }, { agent }) + expect(result.isError).toBe(false) + expect(text(result)).toContain('1 pending, 1 in progress, 0 completed') + + const event = agent.session.events.findLast(e => e.type === 'todo/write')! + expect(event.data.todos).toEqual(todos) + }) + + it('stores the trimmed content (the dedupe/length key), not the raw input', async () => { + const ctx = await setup() + const agent = agentWithSession('trim') + const result = await callTodo(ctx, { todos: [{ content: ' plan the work ', status: 'pending' }] }, { agent }) + expect(result.isError).toBe(false) + + const event = agent.session.events.findLast(e => e.type === 'todo/write')! + expect(event.data.todos).toEqual([{ content: 'plan the work', status: 'pending' }]) + }) + + it('replaces the list on a second call (last-write-wins on the log)', async () => { + const ctx = await setup() + const agent = agentWithSession('writer-2') + await callTodo(ctx, { todos: [{ content: 'a', status: 'pending' }] }, { agent }) + await callTodo(ctx, { todos: [ + { content: 'a', status: 'completed' }, + { content: 'b', status: 'in_progress' }, + ] }, { agent }) + + const current = agent.session.events.findLast(e => e.type === 'todo/write')!.data.todos + expect(current).toEqual([ + { content: 'a', status: 'completed' }, + { content: 'b', status: 'in_progress' }, + ]) + }) + + it('rejects a malformed status before execute runs (registry arg-validation)', async () => { + const ctx = await setup() + const result = await callTodo(ctx, { todos: [{ content: 'x', status: 'doing' }] }) + expect(result.isError).toBe(true) + }) + + it('rejects a non-array todos argument', async () => { + const ctx = await setup() + const result = await callTodo(ctx, { todos: 'nope' }) + expect(result.isError).toBe(true) + }) + + it.each([ + { label: 'empty content', todos: [{ content: ' ', status: 'pending' }], fragment: 'non-empty' }, + { label: 'duplicate content', todos: [{ content: 'dup', status: 'pending' }, { content: 'dup', status: 'completed' }], fragment: 'duplicate' }, + { label: 'two in_progress', todos: [{ content: 'a', status: 'in_progress' }, { content: 'b', status: 'in_progress' }], fragment: 'in_progress' }, + ])('rejects $label as an isError result', async ({ todos, fragment }) => { + const ctx = await setup() + const result = await callTodo(ctx, { todos }) + expect(result.isError).toBe(true) + expect(text(result)).toContain(fragment) + }) + + it('rejects a non-agent caller (the list has no owning session)', async () => { + const ctx = await setup() + const result = await callTodo(ctx, { todos: [{ content: 'a', status: 'pending' }] }, { agent: undefined }) + expect(result.isError).toBe(true) + expect(text(result)).toContain('owning agent session') + }) + + it('presents the call with a stable title and the list as raw input', async () => { + const ctx = await setup() + const def = ctx.tools.get('todo_write')! + const todos = [{ content: 'a', status: 'pending' }] + expect(def.presentCall?.({ todos })).toEqual({ title: 'Update todo list', kind: 'other', rawInput: todos }) + }) + + it('unregisters the tool when its contributing fiber is disposed (HMR-safety)', async () => { + const ctx = new Context() + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + const fiber = await ctx.plugin(tool) + expect(ctx.tools.schemas().some(s => s.name === 'todo_write')).toBe(true) + await fiber.dispose() + expect(ctx.tools.schemas().some(s => s.name === 'todo_write')).toBe(false) + }) + + it('has the namespace-plugin export shape (no stray default) so the Loader keeps name/inject/apply', () => { + // Postmortem 0001 guard: this plugin HAS `inject = ['tools']`, so a stray + // `export default apply` would collapse the module via `unwrapExports` + // (`exports.default ?? exports`), DROP `inject`, and crash at load with + // "cannot get property … without inject". Guard the shape directly. + expect('default' in tool).toBe(false) + expect(tool.name).toBe('tool-todo') + expect(tool.inject).toEqual(['tools']) + + const loader = Object.create(Loader.prototype) as Loader + const unwrapped = loader.unwrapExports(tool) as Record + expect(unwrapped).toBe(tool) + expect(unwrapped.name).toBe('tool-todo') + expect(unwrapped.inject).toEqual(['tools']) + expect(typeof unwrapped.apply).toBe('function') + }) +}) diff --git a/packages/todo/tool-todo/tsconfig.json b/packages/todo/tool-todo/tsconfig.json new file mode 100644 index 0000000000..adf2f25dec --- /dev/null +++ b/packages/todo/tool-todo/tsconfig.json @@ -0,0 +1,27 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": [ + "src" + ], + "references": [ + { + "path": "../../../vendor/cosmokit" + }, + { + "path": "../../../vendor/cordis" + }, + { + "path": "../../core/tools" + }, + { + "path": "../../core/agent" + }, + { + "path": "../../core/session" + } + ] +} diff --git a/packages/ui/acp/package.json b/packages/ui/acp/package.json index 6973dc5e20..52080be092 100644 --- a/packages/ui/acp/package.json +++ b/packages/ui/acp/package.json @@ -44,6 +44,7 @@ "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-tool-bash": "workspace:^", + "@deepseek-ai/dsh-tool-todo": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "cordis": "^4.0.0-rc.6" } diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index ec79e97443..754b1750be 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -53,6 +53,8 @@ import { type LoadSessionResponse, type NewSessionRequest, type NewSessionResponse, + type Plan, + type PlanEntry, type PromptRequest, type PromptResponse, type SessionNotification, @@ -64,7 +66,7 @@ import { CallId } from '@deepseek-ai/dsh-llm' import type { Agent, AgentStatus } from '@deepseek-ai/dsh-agent' import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' -import type { SessionEvent, TurnEndReason } from '@deepseek-ai/dsh-session' +import type { SessionEvent, TodoItem, TurnEndReason } from '@deepseek-ai/dsh-session' import type { ToolCallKind, ToolCallPresentation, ToolRegistry, ToolResultPresentation, ToolTerminal } from '@deepseek-ai/dsh-tools' // Side-effect type import: declaration-merges `ctx.sessionPersistence` onto // Context (the bridge injects it and reads `list()` for load cwd validation). @@ -873,6 +875,10 @@ export function streamSessionEventUpdate( }) return } + case 'todo/write': { + notify({ sessionId, update: { sessionUpdate: 'plan', ...todosToPlan(event.data.todos) } }) + return + } // turn/step boundaries, context/message, steering, // assistant/message — no direct ACP client update. default: @@ -880,6 +886,18 @@ export function streamSessionEventUpdate( } } +/** + * Map a harness todo list to an ACP `plan` body. ACP's `PlanEntry` requires + * `content` + `priority` + `status`, but a {@link TodoItem} carries no priority, + * so synthesize a constant `'medium'` on every entry; `status` maps 1:1 (the + * harness status triple IS `PlanEntryStatus`). The ACP client REPLACES its whole + * plan on each `plan` update, matching the harness's whole-list-replace + * semantics, so no per-entry diffing is needed. + */ +export function todosToPlan(todos: TodoItem[]): Plan { + return { entries: todos.map((todo): PlanEntry => ({ content: todo.content, priority: 'medium', status: todo.status })) } +} + /** * Per-connection terminal-rendering context threaded into * {@link streamSessionEventUpdate}: whether the client advertised the diff --git a/packages/ui/acp/tests/harness.ts b/packages/ui/acp/tests/harness.ts index 4f6b5ac17a..9077d106d0 100644 --- a/packages/ui/acp/tests/harness.ts +++ b/packages/ui/acp/tests/harness.ts @@ -20,6 +20,7 @@ import AgentLoop from '@deepseek-ai/dsh-agent-loop' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' +import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' import { ClientSideConnection, ndJsonStream, @@ -158,6 +159,12 @@ export async function makeBridgeHarness(options: { * implementation over a mock in tests"). */ withBash?: boolean + /** + * Plug the REAL `dsh-tool-todo` tool so a test can drive `todo_write` through + * the bridge and assert the resulting `plan` sessionUpdate — the shipping + * tool + the bridge's own todo/write→plan mapping, not a stand-in. + */ + withTodo?: boolean } = { storageDir: '' }): Promise { const adapter = new MockAdapter(options.script ?? []) @@ -173,6 +180,9 @@ export async function makeBridgeHarness(options: { await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) await ctx.plugin(ToolBash) } + if (options.withTodo) { + await ctx.plugin(ToolTodo) + } ctx.llm.registerAdapter(['mock'], adapter) // Two identity byte pipes cross-wired into the two ndJsonStreams: bytes the diff --git a/packages/ui/acp/tests/load.spec.ts b/packages/ui/acp/tests/load.spec.ts index a87fa49a9e..c07ef93274 100644 --- a/packages/ui/acp/tests/load.spec.ts +++ b/packages/ui/acp/tests/load.spec.ts @@ -94,6 +94,44 @@ describe('acp bridge — session/load replay', () => { expect(content[0]?.content.text).toBe('```console\nhello\n```') }) + it('replays a persisted todo/write as a plan sessionUpdate on load', async () => { + // A turn whose model called todo_write persists a todo/write event. A fresh + // bridge loading the session must re-emit the ACP `plan` update from the log + // (the load replay runs every event through streamSessionEventUpdate), so an + // editor reopening the session sees the current plan. + live = await makeBridgeHarness({ + storageDir, + withTodo: true, + script: [ + toolCallResponse('c1', 'todo_write', { + todos: [ + { content: 'first step', status: 'in_progress' }, + { content: 'second step', status: 'pending' }, + ], + }), + textResponse('planned'), + ], + }) + await live.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const { sessionId } = await live.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + await live.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'plan it' }] }) + await live.dispose() + live = undefined + + loader = await makeBridgeHarness({ storageDir, withTodo: true, script: [] }) + await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + await loader.client.loadSession({ sessionId, cwd: process.cwd(), mcpServers: [] }) + + const plan = loader.updates.find(u => u.sessionUpdate === 'plan') + expect(plan).toEqual({ + sessionUpdate: 'plan', + entries: [ + { content: 'first step', priority: 'medium', status: 'in_progress' }, + { content: 'second step', priority: 'medium', status: 'pending' }, + ], + }) + }) + it('replays a persisted bash call as a TERMINAL card when the loader advertises the capability', async () => { // The presentation is resolved at replay time, so a loader that advertised // _meta.terminal_output must reconstruct the terminal card (content + _meta) diff --git a/packages/ui/acp/tests/stream-update.spec.ts b/packages/ui/acp/tests/stream-update.spec.ts index 30cbd17c40..89d68fd1c0 100644 --- a/packages/ui/acp/tests/stream-update.spec.ts +++ b/packages/ui/acp/tests/stream-update.spec.ts @@ -3,7 +3,7 @@ import { CallId } from '@deepseek-ai/dsh-llm' import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import type { SessionNotification } from '@agentclientprotocol/sdk' import type { ToolDefinition, ToolRegistry } from '@deepseek-ai/dsh-tools' -import { streamSessionEventUpdate, agentOptions, ToolPresenter } from '../src/index.ts' +import { streamSessionEventUpdate, agentOptions, todosToPlan, ToolPresenter } from '../src/index.ts' /** Collect the updates a single event produces (no presenter → generic fallback). */ function updatesFor(event: SessionEvent): SessionNotification['update'][] { @@ -118,6 +118,43 @@ describe('streamSessionEventUpdate', () => { expect(updatesFor(evt('turn/end', { turn: 1, reason: { kind: 'completed' } }))).toEqual([]) expect(updatesFor(evt('step/start', { turn: 1, step: 1 }))).toEqual([]) }) + + it('maps todo/write to a plan sessionUpdate with priority synthesized as medium', () => { + expect(updatesFor(evt('todo/write', { + todos: [ + { content: 'plan the work', status: 'in_progress' }, + { content: 'write the code', status: 'pending' }, + { content: 'run the tests', status: 'completed' }, + ], + }))).toEqual([{ + sessionUpdate: 'plan', + entries: [ + { content: 'plan the work', priority: 'medium', status: 'in_progress' }, + { content: 'write the code', priority: 'medium', status: 'pending' }, + { content: 'run the tests', priority: 'medium', status: 'completed' }, + ], + }]) + }) + + it('maps an empty todo list to a plan with no entries', () => { + expect(updatesFor(evt('todo/write', { todos: [] }))).toEqual([{ sessionUpdate: 'plan', entries: [] }]) + }) +}) + +describe('todosToPlan', () => { + it('maps status 1:1 and stamps every entry priority medium', () => { + expect(todosToPlan([ + { content: 'a', status: 'pending' }, + { content: 'b', status: 'in_progress' }, + { content: 'c', status: 'completed' }, + ])).toEqual({ + entries: [ + { content: 'a', priority: 'medium', status: 'pending' }, + { content: 'b', priority: 'medium', status: 'in_progress' }, + { content: 'c', priority: 'medium', status: 'completed' }, + ], + }) + }) }) describe('ToolPresenter (tool-owned presentation via the tool registry)', () => { diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 15b61280cb..185ed72b33 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -624,6 +624,30 @@ importers: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/todo/tool-todo: + devDependencies: + '@deepseek-ai/dsh-agent': + specifier: workspace:^ + version: link:../../core/agent + '@deepseek-ai/dsh-agent-loop': + specifier: workspace:^ + version: link:../../core/agent-loop + '@deepseek-ai/dsh-llm': + specifier: workspace:^ + version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session + '@deepseek-ai/dsh-system-prompt': + specifier: workspace:^ + version: link:../../core/system-prompt + '@deepseek-ai/dsh-tools': + specifier: workspace:^ + version: link:../../core/tools + cordis: + specifier: ^4.0.0-rc.6 + version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/ui/acp: dependencies: '@agentclientprotocol/sdk': @@ -663,6 +687,9 @@ importers: '@deepseek-ai/dsh-tool-bash': specifier: workspace:^ version: link:../../bash/tool-bash + '@deepseek-ai/dsh-tool-todo': + specifier: workspace:^ + version: link:../../todo/tool-todo '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools diff --git a/scripts/gen-cordis-catalog.ts b/scripts/gen-cordis-catalog.ts index 5bf7a344ca..ea1c4b6661 100644 --- a/scripts/gen-cordis-catalog.ts +++ b/scripts/gen-cordis-catalog.ts @@ -394,7 +394,7 @@ function render(events: EventEntry[], services: ServiceEntry[]): string { '', '## Events', '', - `Dispatch modes: **emit** (fire-and-forget), **waterfall** (each listener gets \`next()\` and may transform or veto — see [waterfall semantics](../architecture.md#cordis-waterfall-semantics-important)), **parallel** (awaited fan-out, no veto), **serial** (awaited, in registration order, no veto). The harness declares ${events.length} events across ${new Set(events.map(e => e.scope)).size} scopes.`, + 'Dispatch modes: **emit** (fire-and-forget), **waterfall** (each listener gets `next()` and may transform or veto — see [waterfall semantics](../architecture.md#cordis-waterfall-semantics-important)), **parallel** (awaited fan-out, no veto), **serial** (awaited, in registration order, no veto).', '', ] const scopes = [...new Set(events.map(e => e.scope))].sort() @@ -407,7 +407,7 @@ function render(events: EventEntry[], services: ServiceEntry[]): string { lines.push( '## Services', '', - `The ${services.length} \`ctx.\` services the harness provides. An abstract seam (e.g. \`ctx.bash\`) is implemented by a separate package; the interface is what consumers code against.`, + 'The `ctx.` services the harness provides. An abstract seam (e.g. `ctx.bash`) is implemented by a separate package; the interface is what consumers code against.', '', ) for (const s of services) lines.push(...renderService(s)) diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index 4008a7cc20..c5e4c10b71 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -16,6 +16,7 @@ { "doc": "docs/core-data-structures/llm-streaming.md", "symbol": "ContentBlockMap", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/session.md", "symbol": "SessionEventMap", "source": "packages/core/session/src/types.ts" }, + { "doc": "docs/core-data-structures/session.md", "symbol": "TodoItem", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/session.md", "symbol": "SessionEvent", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/session.md", "symbol": "TurnTriggerMap", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/session.md", "symbol": "TurnEndReasonMap", "source": "packages/core/session/src/types.ts" }, diff --git a/tsconfig.base.json b/tsconfig.base.json index 7f46a9105a..3f2d828cb4 100644 --- a/tsconfig.base.json +++ b/tsconfig.base.json @@ -45,6 +45,7 @@ "./packages/bash/*/src", "./packages/compact/*/src", "./packages/subagent/*/src", + "./packages/todo/*/src", "./packages/session-persistence/*/src", "./packages/ui/*/src", "./packages/util/*/src", diff --git a/tsconfig.build.json b/tsconfig.build.json index 19f9d65bb0..fd83990e1f 100644 --- a/tsconfig.build.json +++ b/tsconfig.build.json @@ -40,6 +40,7 @@ { "path": "./packages/subagent/subagent-inprocess" }, { "path": "./packages/subagent/subagent-spawn" }, { "path": "./packages/subagent/subagent-fork" }, - { "path": "./packages/subagent/subagent-acp" } + { "path": "./packages/subagent/subagent-acp" }, + { "path": "./packages/todo/tool-todo" } ] } diff --git a/tsconfig.json b/tsconfig.json index 3da543318d..27476cb949 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -51,6 +51,7 @@ { "path": "./packages/subagent/subagent-inprocess" }, { "path": "./packages/subagent/subagent-spawn" }, { "path": "./packages/subagent/subagent-fork" }, - { "path": "./packages/subagent/subagent-acp" } + { "path": "./packages/subagent/subagent-acp" }, + { "path": "./packages/todo/tool-todo" } ] }