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

fix(mode): stabilize plan-mode model experience

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-20 22:13:59 +08:00
parent 28a74d6d7e
commit 897dc82d9b
40 changed files with 620 additions and 298 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
examples/plan-acp-agent/README.md
View File

@@ -4,7 +4,9 @@ The coding agent as an ACP server with **session modes** composed — the live c
## What it demonstrates
`session/new` advertises the mode picker (`default` / `plan`) plus the sandbox-mode and approval config options — two independent axes on one session, the composition this example exists to demonstrate. Plan mode adds the plan guidance section and the `exit_plan_mode` tool and touches nothing else: the sandbox keeps whatever mode its own knob says (workspace-write here by default), escalation prompts work in plan exactly as in default, and switching either axis never disturbs the other, in any order. A user who wants a hard read-only floor while planning flips the sandbox-mode option to read-only alongside the mode picker. There is deliberately no per-mode tool list either: `write`/`edit`/`bash` stay present in plan and the section's guidance is what defers changes to after the review (the effects-based generalization is the RFC's deferred item). A blocking decision goes to the user through `ask_user_question`. The model leaves by presenting its plan through `exit_plan_mode`: the plan markdown renders as the tool's call card, the review question arrives as an elicitation form (approve / keep planning, free text welcome), and a keep-planning answer returns the feedback to the model verbatim.
`session/new` advertises the mode picker (`default` / `plan`) plus the sandbox-mode and approval config options — independent axes on one session. The composition owns its full plan instructions in [`cordis.yml`](cordis.yml): persist in the selected mode, inspect before asking, avoid mutations, resolve discoverable facts from the repository, and produce a decision-complete plan through `exit_plan_mode`. These are the most instrumental behaviors shared by the local Codex and Claude Code plan-mode references without importing their product-specific plan files, phase machinery, or protocol tags.
Plan mode adds only the configured guidance section. Every other tool, including `exit_plan_mode`, has the same schema in `default` and `plan`; the exit tool describes itself as plan-only and rejects if called outside plan mode. Keeping both native schemas and Code Mode's SDK stable avoids tool-catalog churn at the transition. The sandbox retains its own mode (workspace-write here by default), escalation prompts work identically, and a user who wants a hard read-only floor selects read-only separately. A blocking user-owned choice goes through `ask_user_question`. In plan mode, `exit_plan_mode` renders the submitted markdown as a call card and asks for approval or corrective feedback through ACP elicitation.
## Run
@@ -12,8 +14,8 @@ The coding agent as an ACP server with **session modes** composed — the live c
pnpm run demo:plan-acp # needs DEEPSEEK_API_KEY (repo-root .env works)
```
Drive it from Zed or any ACP client; the mode picker appears on the session beside the sandbox/approval selects. Switching back to `default` (or an approved `exit_plan_mode`) drops the plan section and the exit tool on the next step; the sandbox and approval knobs stay exactly where the user left them.
Drive it from Zed or any ACP client; the mode picker appears beside the sandbox and approval selects. Switching back to `default`, directly or through an approved `exit_plan_mode`, drops only the plan section on the next step. The tool catalog and the independent knobs stay unchanged.
## Tests
`pnpm run test:snapshot` replays three scenarios keyless (the recorded bash re-executes for real under the host's sandbox runner — Seatbelt on macOS, bwrap on Linux CI). `modes-advertise` (authored): the `modes` advertisement and both config options on `session/new`, both `session/set_mode` round-trips with their optimistic `current_mode_update`, and the loud rejection of an unknown mode id, as committed wire bytes. `plan-mode` (recorded, the header pin): the full arc — setMode(plan), the plan-shaped initial header (full toolset + exit tool + section), a real `cat` run inside plan (under the sandbox's own workspace-write default — the mode does not change it), the plan presented via `exit_plan_mode`, a scripted elicitation approve, the boundary-flushed `mode/set` back with a complete changed `request/header`, then a real edit mid-turn. `plan-mode-reject` (recorded): the keep-planning branch, whose corrective `isError` carries the reviewer's free-text feedback verbatim and leaves the session in plan mode. The sandbox-denial marker stays pinned at the unit tier (`packages/bash/tool-bash/tests` — a recorded denial's stderr would be the backend's dialect and replay only where it was recorded).
`pnpm run test:snapshot` replays the ACP mode and plan-review surfaces keyless, including stable schemas across approval and real filesystem calls under Seatbelt on macOS or bwrap on Linux. `pnpm run test:e2e` adds a self-skipping live-model smoke that verifies the file is unchanged when review appears and changed only after approval. Sandbox denial remains covered at the `dsh-tool-bash` unit tier because recorded backend stderr is platform-specific.

21
examples/plan-acp-agent/cordis.yml
View File

@@ -25,10 +25,24 @@
Verify your work by running the code or tests. Keep answers brief and factual.
# Session modes: dsh-mode owns logged state, built-in plan guidance, and the
# plan-only exit tool.
# Deployment-owned plan guidance; dsh-mode owns state and the stable exit tool.
- id: mode
name: '@deepseek-ai/dsh-mode'
config:
modes:
plan:
section: |
You are in plan mode. Stay in plan mode until exit_plan_mode succeeds or the user switches the session mode. Imperative language to implement changes means plan the implementation, not execute it.
Explore first. Use non-mutating reads, searches, static analysis, and checks to ground the plan in the actual repository. Do not edit or write files, change configuration, run formatters or code generation that rewrites tracked files, commit, or otherwise carry out the plan. Prefer existing functions and patterns over new machinery.
The tool catalog stays the same across modes for request-cache stability. These plan-mode rules override any later tool description or guidance that suggests using mutation tools; those tools remain listed only to keep the request shape stable. Do not use todo_write to track this planning phase: it tracks implementation after an approved plan, while the plan itself belongs in exit_plan_mode.
Resolve discoverable facts by inspection. Use ask_user_question only for user-owned choices or material ambiguity that inspection cannot answer. Do not ask the user where code lives or how current behavior works when you can find out.
Make the plan decision-complete: state the goal and success criteria; group implementation changes by subsystem; identify public API, schema, and data-flow changes; cover edge cases, failure modes, tests, acceptance criteria, and explicit assumptions. Keep it concise enough to review but detailed enough that another engineer can implement it without making design decisions.
When ready, call exit_plan_mode with the complete plan markdown, starting with a # title. Make exit_plan_mode the only and final tool call in that assistant response: it presents the plan for approval, and implementation begins only in a later step after approval. Do not paste the final plan as a plain reply or ask "should I proceed?" through prose or ask_user_question. If review rejects it, incorporate the feedback and present again. If the review channel is unavailable or aborted, stay in plan mode and ask the user to switch modes manually; do not proceed with implementation.
# One shared sandbox policy serves bash and filesystem tools in every mode.
- id: sandbox
@@ -66,6 +80,7 @@
- id: tool-fs
name: '@deepseek-ai/dsh-tool-fs'
# Model-facing task tracking remains composed in both modes.
# Kept loaded across both modes for a stable catalog; todo_write tracks
# implementation after approval, while exit_plan_mode owns the review plan.
- id: tool-todo
name: '@deepseek-ai/dsh-tool-todo'

11
examples/plan-acp-agent/tests/acp.snapshot.ts
View File

@@ -45,13 +45,10 @@ const SCENARIOS: Scenario[] = [
// class to carry a pin.
{ name: 'modes-advertise', hasModelTurn: false, recorded: false, headerClass: 'plan' },
// The full plan-mode arc, and NECESSARILY the pinned-header scenario for
// the 'plan' class: the first request ships the plan-shaped header (reason
// initial) — the full toolset plus exit_plan_mode and the mode section —
// and the approved exit narrows it back by exactly that tool and section,
// a pure removal the delta encoding CAN express (one header-delta; the
// ENTERING flip is a non-tail insertion the append-only tools delta cannot
// express, so it falls back to a snapshot — pinned at the unit tier). The
// arc: setMode(plan) → the model runs a real `cat` inside plan and
// the 'plan' class: the first request ships the configured mode section and
// the full toolset, including exit_plan_mode. Approval removes only the
// section; the following changed header carries byte-identical tool schemas.
// The arc: setMode(plan) → the model runs a real `cat` inside plan and
// presents the plan via exit_plan_mode → the scripted elicitation approves
// → the very next step already edits for real, mid-turn.
{ name: 'plan-mode', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'plan', expectedHeaderChanges: 1 },

84
examples/plan-acp-agent/tests/plan-mode.e2e.ts Normal file
View File

@@ -0,0 +1,84 @@
import { mkdtemp, readFile, rm, writeFile } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { fileURLToPath } from 'node:url'
import { afterEach, describe, expect, it } from 'vitest'
import {
PROTOCOL_VERSION,
type CreateElicitationRequest,
type CreateElicitationResponse,
} from '@agentclientprotocol/sdk'
import {
launchAcpTestAgent,
type AgentUnderTest,
type LaunchedAcpTestAgent,
} from '@deepseek-ai/dsh-acp-snapshot'
/** The shipped plan-mode ACP leaf exercised through its real subprocess entry. */
const AGENT: AgentUnderTest = {
binScript: fileURLToPath(new URL('../../../packages/examples/acp-demo/src/bin.ts', import.meta.url)),
configPath: fileURLToPath(new URL('../cordis.yml', import.meta.url)),
tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)),
}
let spawned: LaunchedAcpTestAgent | undefined
let workdir: string | undefined
afterEach(async () => {
const ownedSpawned = spawned
const ownedWorkdir = workdir
spawned = undefined
workdir = undefined
try {
if (ownedSpawned !== undefined) {
await ownedSpawned.close('SIGKILL').catch((error: unknown) => {
throw new Error(`plan ACP cleanup failed; child stderr:\n${ownedSpawned.stderr()}`, { cause: error })
})
}
} finally {
if (ownedWorkdir !== undefined) await rm(ownedWorkdir, { recursive: true, force: true })
}
})
describe.skipIf(!process.env.DEEPSEEK_API_KEY)('plan-acp-agent e2e: approval gates implementation (real model)', () => {
it('keeps the file unchanged through review, then applies the approved plan', async () => {
workdir = await mkdtemp(join(tmpdir(), 'plan-acp-e2e-'))
const proofPath = join(workdir, 'proof.txt')
await writeFile(proofPath, 'BEFORE\n')
const reviews: CreateElicitationRequest[] = []
let contentAtReview: string | undefined
const createElicitation = async (request: CreateElicitationRequest): Promise<CreateElicitationResponse> => {
if (request.mode !== 'form' || request.requestedSchema.title !== 'Plan review') return { action: 'cancel' }
reviews.push(request)
contentAtReview = await readFile(proofPath, 'utf8')
return { action: 'accept', content: { choice: 'Approve' } }
}
spawned = launchAcpTestAgent({ agent: AGENT, cwd: workdir, createElicitation })
const { client, updates } = spawned
const rpc = async <T>(stage: string, operation: Promise<T>): Promise<T> => operation.catch((error: unknown) => {
throw new Error(`plan ACP ${stage} failed; child stderr:\n${spawned?.stderr() ?? '<unavailable>'}`, { cause: error })
})
await rpc('initialize', client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }))
const created = await rpc('session/new', client.newSession({ cwd: workdir, mcpServers: [] }))
expect(created.modes?.availableModes.map(mode => mode.id)).toEqual(['default', 'plan'])
await rpc('session/set_mode', client.setSessionMode({ sessionId: created.sessionId, modeId: 'plan' }))
const result = await rpc('prompt', client.prompt({
sessionId: created.sessionId,
prompt: [{
type: 'text',
text: 'Inspect proof.txt and plan the smallest change that replaces its contents with exactly AFTER followed by one newline. Present the complete plan through exit_plan_mode. After I approve it, implement the change with the filesystem tools, verify the exact file contents, and stop. Do not ask questions.',
}],
}))
expect(['end_turn', 'max_tokens']).toContain(result.stopReason)
expect(reviews).toHaveLength(1)
expect(contentAtReview).toBe('BEFORE\n')
expect(await readFile(proofPath, 'utf8')).toBe('AFTER\n')
expect(updates
.filter(update => update.sessionUpdate === 'current_mode_update')
.map(update => update.currentModeId)).toEqual(['plan', 'default'])
}, 240_000)
})

2
examples/plan-acp-agent/tests/snapshots/plan-mode-reject/stdout.expected.jsonl
View File

@@ -82,7 +82,7 @@
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"o"}}}}
{"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_ucsiIH3qJOCb1B6d3dmm4387","title":"Fix the greeting typo","kind":"other","status":"in_progress","content":[{"type":"content","content":{"type":"text","text":"# Fix the greeting typo\n\n**Issue:** The greeting message currently displays \"helo wrld\" instead of the correct \"Hello World\".\n\n**Plan:**\n\n1. **Find the source file** — Locate the file that contains the greeting string \"helo wrld\".\n2. **Fix the typo** — Replace \"helo wrld\" with \"Hello World\" in that source file.\n3. **Verify** — Confirm the fix is correct by reading the changed file."}}]}}}
{"jsonrpc":"2.0","id":1,"method":"elicitation/create","params":{"sessionId":"{{sessionId}}","mode":"form","message":"Approve this plan and leave plan mode?","requestedSchema":{"type":"object","title":"Plan review","properties":{"choice":{"type":"string","title":"Approve this plan and leave plan mode?","description":"Choose one option, or fill a custom answer below.","oneOf":[{"const":"Approve","title":"Approve: Leave plan mode; the plan is carried out from the next step."},{"const":"Keep planning","title":"Keep planning: Stay in plan mode; feedback goes back to the model."}]},"custom":{"type":"string","title":"Custom answer","description":"Optional free-form answer. Leave empty to use the selected option."}},"required":[]}}}
{"jsonrpc":"2.0","id":1,"method":"elicitation/create","params":{"sessionId":"{{sessionId}}","mode":"form","message":"Approve this plan and leave plan mode?\n\n# Fix the greeting typo\n\n**Issue:** The greeting message currently displays \"helo wrld\" instead of the correct \"Hello World\".\n\n**Plan:**\n\n1. **Find the source file** — Locate the file that contains the greeting string \"helo wrld\".\n2. **Fix the typo** — Replace \"helo wrld\" with \"Hello World\" in that source file.\n3. **Verify** — Confirm the fix is correct by reading the changed file.","requestedSchema":{"type":"object","title":"Plan review","properties":{"choice":{"type":"string","title":"Approve this plan and leave plan mode?","description":"Choose one option, or fill a custom answer below.","oneOf":[{"const":"Approve","title":"Approve: Leave plan mode; the plan is carried out from the next step."},{"const":"Keep planning","title":"Keep planning: Stay in plan mode; feedback goes back to the model."}]},"custom":{"type":"string","title":"Custom answer","description":"Optional free-form answer. Leave empty to use the selected option."}},"required":[]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_ucsiIH3qJOCb1B6d3dmm4387","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: The user chose to keep planning; their feedback: Also add a verification step that re-reads the file after the fix."}}],"title":"Plan review"}}}
{"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"}}}}

2
examples/plan-acp-agent/tests/snapshots/plan-mode/session.jsonl
View File

@@ -229,7 +229,7 @@
{"type":"step/end","seq":227,"time":1784525378329,"data":{"turn":1,"step":2}}
{"type":"mode/set","seq":228,"time":1784525378329,"data":{"mode":"default"}}
{"type":"step/start","seq":229,"time":1784525378330,"data":{"turn":1,"step":3}}
{"type":"request/header","seq":230,"time":1784560735611,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"change"}}
{"type":"request/header","seq":230,"time":1784553020470,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"change"}}
{"type":"assistant/chunk","seq":231,"time":1784525378723,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"assistant/chunk","seq":232,"time":1784525378723,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}}
{"type":"assistant/chunk","seq":233,"time":1784525378807,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" plan"}}}

2
examples/plan-acp-agent/tests/snapshots/plan-mode/stdout.expected.jsonl
View File

@@ -122,7 +122,7 @@
{"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":"."}}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_6RLxuiGtAFswvfLnWdt63143","title":"Fix the greeting typo","kind":"other","status":"in_progress","content":[{"type":"content","content":{"type":"text","text":"# Fix the greeting typo\n\n## Single step\n1. **Edit line 2 of `notes.txt`** — Replace the content of line 2 (`- the greeting message still says \"helo wrld\"`) with `hello world`."}}]}}}
{"jsonrpc":"2.0","id":1,"method":"elicitation/create","params":{"sessionId":"{{sessionId}}","mode":"form","message":"Approve this plan and leave plan mode?","requestedSchema":{"type":"object","title":"Plan review","properties":{"choice":{"type":"string","title":"Approve this plan and leave plan mode?","description":"Choose one option, or fill a custom answer below.","oneOf":[{"const":"Approve","title":"Approve: Leave plan mode; the plan is carried out from the next step."},{"const":"Keep planning","title":"Keep planning: Stay in plan mode; feedback goes back to the model."}]},"custom":{"type":"string","title":"Custom answer","description":"Optional free-form answer. Leave empty to use the selected option."}},"required":[]}}}
{"jsonrpc":"2.0","id":1,"method":"elicitation/create","params":{"sessionId":"{{sessionId}}","mode":"form","message":"Approve this plan and leave plan mode?\n\n# Fix the greeting typo\n\n## Single step\n1. **Edit line 2 of `notes.txt`** — Replace the content of line 2 (`- the greeting message still says \"helo wrld\"`) with `hello world`.","requestedSchema":{"type":"object","title":"Plan review","properties":{"choice":{"type":"string","title":"Approve this plan and leave plan mode?","description":"Choose one option, or fill a custom answer below.","oneOf":[{"const":"Approve","title":"Approve: Leave plan mode; the plan is carried out from the next step."},{"const":"Keep planning","title":"Keep planning: Stay in plan mode; feedback goes back to the model."}]},"custom":{"type":"string","title":"Custom answer","description":"Optional free-form answer. Leave empty to use the selected option."}},"required":[]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_6RLxuiGtAFswvfLnWdt63143","status":"completed","content":[{"type":"content","content":{"type":"text","text":"Plan approved — plan mode exited; carry out the plan starting with your next step."}}],"title":"Plan review"}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"current_mode_update","currentModeId":"default"}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}

13
examples/plan-acp-agent/tests/snapshots/plan-mode/system-prompt.expected.md
View File

@@ -5,7 +5,18 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working
Verify your work by running the code or tests. Keep answers brief and factual.
You are in plan mode: a planning state. Explore, analyze, and design; reading files and running read-only commands is fine, but hold off on changes — edits and other side effects belong in the plan and run after its approval, not in this mode. When a decision or a missing detail blocks the plan, ask the user through the ask_user_question tool where it is available. A finished plan is delivered by calling exit_plan_mode — that call is what puts it in front of the user for review, so prefer it over pasting the plan as a plain reply or asking the user to switch modes themselves. If exit_plan_mode is unavailable or its review fails, ask the user to switch the session out of plan mode instead of pressing on.
You are in plan mode. Stay in plan mode until exit_plan_mode succeeds or the user switches the session mode. Imperative language to implement changes means plan the implementation, not execute it.
Explore first. Use non-mutating reads, searches, static analysis, and checks to ground the plan in the actual repository. Do not edit or write files, change configuration, run formatters or code generation that rewrites tracked files, commit, or otherwise carry out the plan. Prefer existing functions and patterns over new machinery.
The tool catalog stays the same across modes for request-cache stability. These plan-mode rules override any later tool description or guidance that suggests using mutation tools; those tools remain listed only to keep the request shape stable. Do not use todo_write to track this planning phase: it tracks implementation after an approved plan, while the plan itself belongs in exit_plan_mode.
Resolve discoverable facts by inspection. Use ask_user_question only for user-owned choices or material ambiguity that inspection cannot answer. Do not ask the user where code lives or how current behavior works when you can find out.
Make the plan decision-complete: state the goal and success criteria; group implementation changes by subsystem; identify public API, schema, and data-flow changes; cover edge cases, failure modes, tests, acceptance criteria, and explicit assumptions. Keep it concise enough to review but detailed enough that another engineer can implement it without making design decisions.
When ready, call exit_plan_mode with the complete plan markdown, starting with a # title. Make exit_plan_mode the only and final tool call in that assistant response: it presents the plan for approval, and implementation begins only in a later step after approval. Do not paste the final plan as a plain reply or ask "should I proceed?" through prose or ask_user_question. If review rejects it, incorporate the feedback and present again. If the review channel is unavailable or aborted, stay in plan mode and ask the user to switch modes manually; do not proceed with implementation.
Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.

18
examples/plan-acp-agent/tests/snapshots/plan-mode/tool-schemas.expected.json
View File

@@ -150,7 +150,7 @@
},
{
"name": "exit_plan_mode",
"description": "Present your plan for the user's review and, on approval, leave plan mode. Send the COMPLETE plan as markdown, starting with a # heading that names it. The user may approve (carry out the plan from your next step) or keep planning — their feedback comes back in the tool result; revise and present again.",
"description": "Use only in plan mode. Present your plan for the user's review and, on approval, leave plan mode. Send the COMPLETE plan as markdown, starting with a # heading that names it. The user may approve (carry out the plan from your next step) or keep planning — their feedback comes back in the tool result; revise and present again.",
"parameters": {
"type": "object",
"properties": {
@@ -478,6 +478,22 @@
]
}
},
{
"name": "exit_plan_mode",
"description": "Use only in plan mode. Present your plan for the user's review and, on approval, leave plan mode. Send the COMPLETE plan as markdown, starting with a # heading that names it. The user may approve (carry out the plan from your next step) or keep planning — their feedback comes back in the tool result; revise and present again.",
"parameters": {
"type": "object",
"properties": {
"plan": {
"type": "string",
"description": "The complete plan, as markdown, starting with a # heading that names it."
}
},
"required": [
"plan"
]
}
},
{
"name": "read",
"description": "Read a UTF-8 text file and return line-numbered content.",