Merge origin/master into worktree/tui-session-controls
This commit is contained in:
Tianyi Cui
@@ -31,6 +31,7 @@ const WORKSPACE_CONTEXT_CONFIG = fileURLToPath(new URL('../workspace-context.cor
|
||||
const ADVANCED_CONFIG = fileURLToPath(new URL('../advanced.cordis.yml', import.meta.url))
|
||||
const FS_CONFIG = fileURLToPath(new URL('../fs.cordis.yml', import.meta.url))
|
||||
const DEPTH_TWO_CONFIG = fileURLToPath(new URL('../depth-two.cordis.yml', import.meta.url))
|
||||
const LSP_CONFIG = fileURLToPath(new URL('./lsp.cordis.yml', import.meta.url))
|
||||
|
||||
function snapshotModeFromEnv(value: string | undefined): SnapshotSuiteOptions['mode'] {
|
||||
switch (value) {
|
||||
@@ -68,6 +69,7 @@ const SCENARIOS: Scenario[] = [
|
||||
{ name: 'fs-terminal-card', hasModelTurn: true, recorded: true },
|
||||
{ name: 'todo-plan', hasModelTurn: true, recorded: true },
|
||||
{ name: 'skill-load', hasModelTurn: true, recorded: false, pinsHeader: true, headerClass: 'skill' },
|
||||
{ name: 'lsp-definition', hasModelTurn: true, recorded: false, pinsHeader: true, headerClass: 'lsp', configPath: LSP_CONFIG },
|
||||
{ name: 'workspace-edit', hasModelTurn: true, recorded: true },
|
||||
{ name: 'fs-read', hasModelTurn: true, recorded: true },
|
||||
{ name: 'fs-write', hasModelTurn: true, recorded: true },
|
||||
|
||||
41
examples/acp-agent/tests/fixtures/subagent/subagent-acp/cordis.yml
vendored
Normal file
41
examples/acp-agent/tests/fixtures/subagent/subagent-acp/cordis.yml
vendored
Normal file
@@ -0,0 +1,41 @@
|
||||
# Test-only composition: the ACP subagent backend on the real Loader/app path.
|
||||
# The scripted model delegates once; the scripted mock ACP child (MOCK_ECHO_CWD)
|
||||
# echoes its process cwd and announced session cwd, so parent-session cwd
|
||||
# inheritance is asserted keylessly end to end. `cwd` is deliberately omitted —
|
||||
# the inheritance branch under test. The child command path is machine-absolute,
|
||||
# so the driving e2e supplies it via DSH_TEST_MOCK_ACP_SERVER.
|
||||
- id: mock-llm
|
||||
name: './mock-delegating-llm.ts'
|
||||
|
||||
- id: subagent
|
||||
name: '@deepseek-ai/dsh-subagent'
|
||||
|
||||
- id: subagent-acp
|
||||
name: '@deepseek-ai/dsh-subagent-acp'
|
||||
config:
|
||||
providerName: acp
|
||||
command: !!js process.execPath
|
||||
args:
|
||||
- !!js process.env.DSH_TEST_MOCK_ACP_SERVER
|
||||
permission: reject
|
||||
env:
|
||||
MOCK_ECHO_CWD: '1'
|
||||
|
||||
- id: tool-subagent
|
||||
name: '@deepseek-ai/dsh-tool-subagent'
|
||||
config:
|
||||
provider: acp
|
||||
toolName: subagent
|
||||
# ACP advertises no depthLimit: the child harness owns its own recursion
|
||||
# budget, so the local numeric default cannot apply here.
|
||||
maxDepth: 'provider-managed'
|
||||
|
||||
- id: cli-agent
|
||||
name: '@deepseek-ai/dsh-cli-demo'
|
||||
config:
|
||||
provider: mock
|
||||
model: mock-delegate
|
||||
persona: 'Test ACP subagent cwd inheritance.'
|
||||
persistenceRoot: './.sessions'
|
||||
persistenceCompression: 'none'
|
||||
workspaceContext: false
|
||||
15
examples/acp-agent/tests/fixtures/subagent/subagent-acp/driver.ts
vendored
Normal file
15
examples/acp-agent/tests/fixtures/subagent/subagent-acp/driver.ts
vendored
Normal file
@@ -0,0 +1,15 @@
|
||||
#!/usr/bin/env node
|
||||
/** Test driver: one delegation turn through a headless Loader composition. */
|
||||
|
||||
import { boot, resolveConfigPath } from '@deepseek-ai/dsh-app-boot'
|
||||
import { runOneShot } from '@deepseek-ai/dsh-cli-demo/src/cli.ts'
|
||||
|
||||
const configPath = process.argv[2]
|
||||
if (configPath === undefined) throw new Error('acp-subagent cwd driver requires a config path')
|
||||
|
||||
const ctx = await boot('acp-subagent-cwd-e2e', resolveConfigPath(configPath, undefined))
|
||||
try {
|
||||
await runOneShot(ctx, { task: 'delegate' })
|
||||
} finally {
|
||||
await ctx.fiber.dispose()
|
||||
}
|
||||
48
examples/acp-agent/tests/fixtures/subagent/subagent-acp/mock-delegating-llm.ts
vendored
Normal file
48
examples/acp-agent/tests/fixtures/subagent/subagent-acp/mock-delegating-llm.ts
vendored
Normal file
@@ -0,0 +1,48 @@
|
||||
import type { Context } from 'cordis'
|
||||
import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
|
||||
import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm'
|
||||
|
||||
/**
|
||||
* Test adapter for the `mock-delegate` model: the first request calls the
|
||||
* `subagent` tool once, and the follow-up streams the tool result text back
|
||||
* verbatim — so the ACP child's answer (the scripted mock server's cwd echo)
|
||||
* reaches the REPL stdout for the driving e2e to assert.
|
||||
*/
|
||||
class MockDelegatingAdapter extends LlmAdapter {
|
||||
async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
|
||||
const toolResultText = options.messages.at(-1)?.content
|
||||
.filter(block => block.type === 'tool-result')
|
||||
.flatMap(block => block.content)
|
||||
.filter(block => block.type === 'text')
|
||||
.map(block => block.text)
|
||||
.join('') ?? ''
|
||||
|
||||
if (toolResultText.length === 0) {
|
||||
const args = JSON.stringify({ description: 'cwd probe', prompt: 'report your workspace' })
|
||||
yield { type: 'block-start', index: 0, blockType: 'tool-call' }
|
||||
yield { type: 'tool-call-delta', index: 0, id: CallId('call-delegate'), name: 'subagent', argumentsDelta: args }
|
||||
yield { type: 'block-end', index: 0, block: { type: 'tool-call', id: CallId('call-delegate'), name: 'subagent', arguments: args } }
|
||||
yield { type: 'usage', usage: { inputTokens: 10, outputTokens: 5 } }
|
||||
yield { type: 'finish', reason: { kind: 'tool-calls' } }
|
||||
return
|
||||
}
|
||||
|
||||
const reply = `child reported:\n${toolResultText}`
|
||||
yield { type: 'block-start', index: 0, blockType: 'text' }
|
||||
yield { type: 'text-delta', index: 0, text: reply }
|
||||
yield { type: 'block-end', index: 0, block: { type: 'text', text: reply } }
|
||||
yield { type: 'usage', usage: { inputTokens: 10, outputTokens: reply.length } }
|
||||
yield { type: 'finish', reason: { kind: 'stop' } }
|
||||
}
|
||||
}
|
||||
|
||||
export const name = 'mock-llm'
|
||||
export const inject = ['llm']
|
||||
|
||||
/**
|
||||
* Register the delegating mock adapter under the `mock` provider.
|
||||
* @param ctx - the plugin context supplying `ctx.llm`.
|
||||
*/
|
||||
export function apply(ctx: Context): void {
|
||||
ctx.llm.registerAdapter(['mock'], new MockDelegatingAdapter())
|
||||
}
|
||||
29
examples/acp-agent/tests/lsp.cordis.snapshot.yml
Normal file
29
examples/acp-agent/tests/lsp.cordis.snapshot.yml
Normal file
@@ -0,0 +1,29 @@
|
||||
# Keyless replay keeps the LSP composition intact and replaces only the model adapter.
|
||||
- id: base
|
||||
name: '@cordisjs/plugin-include'
|
||||
config:
|
||||
path: ../cordis.yml
|
||||
patches:
|
||||
- id: llm-deepseek
|
||||
name: '@deepseek-ai/dsh-llm-deepseek'
|
||||
disabled: true
|
||||
- insert:
|
||||
- id: lsp
|
||||
name: '@deepseek-ai/dsh-lsp'
|
||||
- id: lsp-local
|
||||
name: '@deepseek-ai/dsh-lsp-local'
|
||||
config:
|
||||
servers:
|
||||
fixture:
|
||||
command: !!js process.execPath
|
||||
args: ['./lsp-server.mjs']
|
||||
extensionToLanguage:
|
||||
'.ts': typescript
|
||||
- id: timeout-policy
|
||||
name: '@deepseek-ai/dsh-timeout-policy'
|
||||
- id: tool-lsp
|
||||
name: '@deepseek-ai/dsh-tool-lsp'
|
||||
config:
|
||||
maxLocations: 1
|
||||
- id: llm-replay
|
||||
name: '@deepseek-ai/dsh-llm-replay'
|
||||
25
examples/acp-agent/tests/lsp.cordis.yml
Normal file
25
examples/acp-agent/tests/lsp.cordis.yml
Normal file
@@ -0,0 +1,25 @@
|
||||
# Exercise the model-facing LSP tool through the shipped ACP app and Loader entry path.
|
||||
# The scenario workspace supplies the deterministic stdio server used by this test composition.
|
||||
- id: base
|
||||
name: '@cordisjs/plugin-include'
|
||||
config:
|
||||
path: ../cordis.yml
|
||||
patches:
|
||||
- insert:
|
||||
- id: lsp
|
||||
name: '@deepseek-ai/dsh-lsp'
|
||||
- id: lsp-local
|
||||
name: '@deepseek-ai/dsh-lsp-local'
|
||||
config:
|
||||
servers:
|
||||
fixture:
|
||||
command: !!js process.execPath
|
||||
args: ['./lsp-server.mjs']
|
||||
extensionToLanguage:
|
||||
'.ts': typescript
|
||||
- id: timeout-policy
|
||||
name: '@deepseek-ai/dsh-timeout-policy'
|
||||
- id: tool-lsp
|
||||
name: '@deepseek-ai/dsh-tool-lsp'
|
||||
config:
|
||||
maxLocations: 1
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"steps": [
|
||||
{ "op": "initialize" },
|
||||
{ "op": "newSession" },
|
||||
{ "op": "prompt", "text": "Use the lsp tool exactly once to find the definition at subject.ts line 1 character 7, then reply with exactly DONE." }
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,23 @@
|
||||
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}","delegationDepth":0}
|
||||
{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Use the lsp tool exactly once to find the definition at subject.ts line 1 character 7, then reply with exactly DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_lsp_definition","name":"lsp","argumentsDelta":"{\"operation\":\"goToDefinition\",\"file_path\":\"subject.ts\",\"line\":1,\"character\":7}"}}}
|
||||
{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_lsp_definition","name":"lsp","arguments":"{\"operation\":\"goToDefinition\",\"file_path\":\"subject.ts\",\"line\":1,\"character\":7}"}}}}
|
||||
{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
|
||||
{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":9,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_lsp_definition","name":"lsp","arguments":"{\"operation\":\"goToDefinition\",\"file_path\":\"subject.ts\",\"line\":1,\"character\":7}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":10,"time":0,"data":{"turn":1,"step":1,"callId":"call_lsp_definition","name":"lsp","arguments":"{\"operation\":\"goToDefinition\",\"file_path\":\"subject.ts\",\"line\":1,\"character\":7}"}}
|
||||
{"type":"tool/result","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_lsp_definition","content":[{"type":"text","text":"subject.ts:1:7\n… 1 more location omitted (limit 1)."}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":12,"time":0,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":13,"time":0,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"DONE"}}}
|
||||
{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}}
|
||||
{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":2}}}}
|
||||
{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":19,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":2}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":20,"time":0,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":21,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
@@ -0,0 +1,7 @@
|
||||
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
|
||||
{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[<objective>|clear|edit <objective>|pause|resume]"}}]}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_lsp_definition","title":"LSP goToDefinition subject.ts:1:7","kind":"search","status":"in_progress","locations":[{"path":"subject.ts","line":1}]}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_lsp_definition","status":"completed","content":[{"type":"content","content":{"type":"text","text":"subject.ts:1:7\n… 1 more location omitted (limit 1)."}}]}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"DONE"}}}}
|
||||
{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}
|
||||
@@ -0,0 +1,27 @@
|
||||
You are an AI agent powered by the DeepSeek Harness SDK.
|
||||
|
||||
You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug.
|
||||
|
||||
Verify your work by running the code or tests. Keep answers brief and factual.
|
||||
|
||||
|
||||
Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.
|
||||
|
||||
Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.
|
||||
|
||||
Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.
|
||||
|
||||
Check the [exit code: N] marker on every bash result; investigate failures before moving on.
|
||||
|
||||
Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.
|
||||
|
||||
Use search/read for ordinary navigation. Use lsp when textual matches are ambiguous or before a change requires precise definitions, implementations, or references. Positions are one-based line and character (UTF-16) at the cursor; an off-symbol position may return no results. findReferences always includes the declaration.
|
||||
|
||||
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked.
|
||||
|
||||
Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
|
||||
<!-- dsh-user-approval-policy:never -->
|
||||
|
||||
Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.
|
||||
|
||||
Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.
|
||||
@@ -0,0 +1,506 @@
|
||||
{
|
||||
"initial": [
|
||||
{
|
||||
"name": "bash",
|
||||
"description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"command": {
|
||||
"type": "string",
|
||||
"description": "The bash command to execute."
|
||||
},
|
||||
"description": {
|
||||
"type": "string",
|
||||
"description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."
|
||||
},
|
||||
"timeoutMs": {
|
||||
"type": "number",
|
||||
"description": "Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."
|
||||
},
|
||||
"workdir": {
|
||||
"type": "string",
|
||||
"description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."
|
||||
},
|
||||
"run_in_background": {
|
||||
"type": "boolean",
|
||||
"description": "Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies."
|
||||
},
|
||||
"sandbox_permissions": {
|
||||
"type": "string",
|
||||
"description": "The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.",
|
||||
"enum": [
|
||||
"workspace-write",
|
||||
"danger-full-access"
|
||||
]
|
||||
},
|
||||
"justification": {
|
||||
"type": "string",
|
||||
"description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"command",
|
||||
"description"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "create_goal",
|
||||
"description": "Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say \"create a goal\". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"objective": {
|
||||
"type": "string",
|
||||
"description": "The concrete completion objective inferred from the direct human request."
|
||||
},
|
||||
"max_goal_rounds": {
|
||||
"type": "number",
|
||||
"description": "Optional positive safe-integer limit on automatic continuation rounds."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"objective"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "edit",
|
||||
"description": "Edit an existing UTF-8 text file by replacing literal text.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"file_path": {
|
||||
"type": "string",
|
||||
"description": "Path to edit, resolved by the filesystem backend."
|
||||
},
|
||||
"old_string": {
|
||||
"type": "string",
|
||||
"description": "Literal text to replace. Must match exactly."
|
||||
},
|
||||
"new_string": {
|
||||
"type": "string",
|
||||
"description": "Literal replacement text. Use an empty string to delete the match."
|
||||
},
|
||||
"replace_all": {
|
||||
"type": "boolean",
|
||||
"description": "Replace all matches. Defaults to false; when false, old_string must appear exactly once."
|
||||
},
|
||||
"sandbox_permissions": {
|
||||
"type": "string",
|
||||
"description": "The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.",
|
||||
"enum": [
|
||||
"workspace-write",
|
||||
"danger-full-access"
|
||||
]
|
||||
},
|
||||
"justification": {
|
||||
"type": "string",
|
||||
"description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"file_path",
|
||||
"old_string",
|
||||
"new_string"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "get_goal",
|
||||
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {}
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "lsp",
|
||||
"description": "Query a language server for precise code navigation. operation is one of goToDefinition, findReferences, goToImplementation, hover. line and character are one-based UTF-16 cursor coordinates. findReferences includes the declaration.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"operation": {
|
||||
"type": "string",
|
||||
"description": "goToDefinition, findReferences, goToImplementation, or hover.",
|
||||
"enum": [
|
||||
"goToDefinition",
|
||||
"findReferences",
|
||||
"goToImplementation",
|
||||
"hover"
|
||||
]
|
||||
},
|
||||
"file_path": {
|
||||
"type": "string",
|
||||
"description": "The source file to query, relative to the workspace or absolute."
|
||||
},
|
||||
"line": {
|
||||
"type": "number",
|
||||
"description": "One-based line of the cursor."
|
||||
},
|
||||
"character": {
|
||||
"type": "number",
|
||||
"description": "One-based UTF-16 column of the cursor."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"operation",
|
||||
"file_path",
|
||||
"line",
|
||||
"character"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "ralph",
|
||||
"description": "Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"objective": {
|
||||
"type": "string",
|
||||
"description": "The immutable completion objective for every fresh Ralph round."
|
||||
},
|
||||
"maxRounds": {
|
||||
"type": "number",
|
||||
"description": "Optional positive safe-integer round cap, bounded by the deployment ceiling."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"objective"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "read",
|
||||
"description": "Read a UTF-8 text file and return line-numbered content.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"file_path": {
|
||||
"type": "string",
|
||||
"description": "Path to read, resolved by the filesystem backend."
|
||||
},
|
||||
"offset": {
|
||||
"type": "number",
|
||||
"description": "1-based first line to return. Defaults to 1."
|
||||
},
|
||||
"limit": {
|
||||
"type": "number",
|
||||
"description": "Maximum number of lines to return. Defaults to 2000."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"file_path"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "skill",
|
||||
"description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"name": {
|
||||
"type": "string",
|
||||
"description": "The exact skill name from the available skills list."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"name"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "subagent",
|
||||
"description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"description": {
|
||||
"type": "string",
|
||||
"description": "A short (3-5 word) description of the delegated task, for display."
|
||||
},
|
||||
"prompt": {
|
||||
"type": "string",
|
||||
"description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."
|
||||
},
|
||||
"run_in_background": {
|
||||
"type": "boolean",
|
||||
"description": "Run as a background task and return its id; collect with task_output or stop with task_kill."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"description",
|
||||
"prompt"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "subagent_fork",
|
||||
"description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"description": {
|
||||
"type": "string",
|
||||
"description": "A short (3-5 word) description of the delegated task, for display."
|
||||
},
|
||||
"prompt": {
|
||||
"type": "string",
|
||||
"description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."
|
||||
},
|
||||
"run_in_background": {
|
||||
"type": "boolean",
|
||||
"description": "Run as a background task and return its id; collect with task_output or stop with task_kill."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"description",
|
||||
"prompt"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "task_kill",
|
||||
"description": "Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"task_id": {
|
||||
"type": "string",
|
||||
"description": "Task id returned by the tool that started the background work."
|
||||
},
|
||||
"reason": {
|
||||
"type": "string",
|
||||
"description": "Optional short reason, recorded in the log and forwarded to the task."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"task_id"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "task_list",
|
||||
"description": "List your background tasks (running and finished) with their ids, kinds, and statuses.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {}
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "task_output",
|
||||
"description": "Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"task_id": {
|
||||
"type": "string",
|
||||
"description": "Task id returned by the tool that started the background work."
|
||||
},
|
||||
"wait": {
|
||||
"type": "boolean",
|
||||
"description": "Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."
|
||||
},
|
||||
"timeout_ms": {
|
||||
"type": "number",
|
||||
"description": "Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"task_id"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "todo_write",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"todos": {
|
||||
"type": "array",
|
||||
"description": "The COMPLETE task list, replacing any previous list.",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"description": "What the task is — a short imperative line."
|
||||
},
|
||||
"status": {
|
||||
"type": "string",
|
||||
"description": "pending (not started) | in_progress (now) | completed (done).",
|
||||
"enum": [
|
||||
"pending",
|
||||
"in_progress",
|
||||
"completed"
|
||||
]
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"content",
|
||||
"status"
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"todos"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "update_goal",
|
||||
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"goal_id": {
|
||||
"type": "string",
|
||||
"description": "Exact id returned by get_goal."
|
||||
},
|
||||
"revision": {
|
||||
"type": "number",
|
||||
"description": "Exact positive revision returned by get_goal."
|
||||
},
|
||||
"action": {
|
||||
"type": "string",
|
||||
"description": "edit | pause | resume | complete | blocked",
|
||||
"enum": [
|
||||
"edit",
|
||||
"pause",
|
||||
"resume",
|
||||
"complete",
|
||||
"blocked"
|
||||
]
|
||||
},
|
||||
"objective": {
|
||||
"type": "string",
|
||||
"description": "Replacement objective; valid only with action edit."
|
||||
},
|
||||
"max_goal_rounds": {
|
||||
"type": "number",
|
||||
"description": "Replacement cap; valid only with action edit."
|
||||
},
|
||||
"blocked_reason": {
|
||||
"type": "string",
|
||||
"description": "Concrete blocking condition; required only with action blocked."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"goal_id",
|
||||
"revision",
|
||||
"action"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "workflow",
|
||||
"description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"script": {
|
||||
"type": "string",
|
||||
"description": "The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."
|
||||
},
|
||||
"meta": {
|
||||
"type": "object",
|
||||
"description": "The workflow identity block (plain JSON — never code).",
|
||||
"properties": {
|
||||
"name": {
|
||||
"type": "string",
|
||||
"description": "Short kebab-case workflow name."
|
||||
},
|
||||
"description": {
|
||||
"type": "string",
|
||||
"description": "One-line description of what the workflow does."
|
||||
},
|
||||
"whenToUse": {
|
||||
"type": "string",
|
||||
"description": "Optional guidance on when this workflow applies."
|
||||
},
|
||||
"phases": {
|
||||
"type": "array",
|
||||
"description": "Optional phase declarations matched by phase() calls.",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"title": {
|
||||
"type": "string",
|
||||
"description": "The phase title phase() calls match by exact string."
|
||||
},
|
||||
"detail": {
|
||||
"type": "string",
|
||||
"description": "Optional one-line description of the phase."
|
||||
},
|
||||
"provider": {
|
||||
"type": "string",
|
||||
"description": "Optional provider override this phase is expected to use."
|
||||
},
|
||||
"model": {
|
||||
"type": "string",
|
||||
"description": "Optional model override this phase is expected to use."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"title"
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"name",
|
||||
"description"
|
||||
]
|
||||
},
|
||||
"args": {
|
||||
"type": "object",
|
||||
"description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"script",
|
||||
"meta"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "write",
|
||||
"description": "Create or fully replace a UTF-8 text file.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"file_path": {
|
||||
"type": "string",
|
||||
"description": "Path to write, resolved by the filesystem backend."
|
||||
},
|
||||
"content": {
|
||||
"type": "string",
|
||||
"description": "Full UTF-8 text content to write."
|
||||
},
|
||||
"sandbox_permissions": {
|
||||
"type": "string",
|
||||
"description": "The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.",
|
||||
"enum": [
|
||||
"workspace-write",
|
||||
"danger-full-access"
|
||||
]
|
||||
},
|
||||
"justification": {
|
||||
"type": "string",
|
||||
"description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"file_path",
|
||||
"content"
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"changes": []
|
||||
}
|
||||
@@ -0,0 +1,57 @@
|
||||
import { resolve } from 'node:path'
|
||||
import { pathToFileURL } from 'node:url'
|
||||
|
||||
let buffered = Buffer.alloc(0)
|
||||
|
||||
function frame(message) {
|
||||
const body = Buffer.from(JSON.stringify({ jsonrpc: '2.0', ...message }))
|
||||
return Buffer.concat([Buffer.from(`Content-Length: ${body.length}\r\n\r\n`), body])
|
||||
}
|
||||
|
||||
function location(line) {
|
||||
return {
|
||||
uri: pathToFileURL(resolve('subject.ts')).href,
|
||||
range: { start: { line, character: 6 }, end: { line, character: 12 } },
|
||||
}
|
||||
}
|
||||
|
||||
function handle(message) {
|
||||
switch (message.method) {
|
||||
case 'initialize':
|
||||
process.stdout.write(frame({
|
||||
id: message.id,
|
||||
result: {
|
||||
capabilities: {
|
||||
positionEncoding: 'utf-16',
|
||||
textDocumentSync: 1,
|
||||
definitionProvider: true,
|
||||
},
|
||||
},
|
||||
}))
|
||||
break
|
||||
case 'textDocument/definition':
|
||||
process.stdout.write(frame({ id: message.id, result: [location(0), location(1)] }))
|
||||
break
|
||||
case 'shutdown':
|
||||
process.stdout.write(frame({ id: message.id, result: null }))
|
||||
break
|
||||
case 'exit':
|
||||
process.exit(0)
|
||||
}
|
||||
}
|
||||
|
||||
process.stdin.on('data', (chunk) => {
|
||||
buffered = Buffer.concat([buffered, chunk])
|
||||
for (;;) {
|
||||
const headerEnd = buffered.indexOf('\r\n\r\n')
|
||||
if (headerEnd < 0) return
|
||||
const match = /Content-Length: (\d+)/i.exec(buffered.toString('ascii', 0, headerEnd))
|
||||
if (match === null) throw new Error('missing Content-Length')
|
||||
const length = Number(match[1])
|
||||
const bodyStart = headerEnd + 4
|
||||
if (buffered.length < bodyStart + length) return
|
||||
const message = JSON.parse(buffered.toString('utf8', bodyStart, bodyStart + length))
|
||||
buffered = buffered.subarray(bodyStart + length)
|
||||
handle(message)
|
||||
}
|
||||
})
|
||||
@@ -0,0 +1,2 @@
|
||||
export const answer = 42
|
||||
console.log(answer)
|
||||
@@ -27,6 +27,8 @@
|
||||
"@deepseek-ai/dsh-llm": "workspace:*",
|
||||
"@deepseek-ai/dsh-llm-deepseek": "workspace:*",
|
||||
"@deepseek-ai/dsh-llm-replay": "workspace:*",
|
||||
"@deepseek-ai/dsh-lsp": "workspace:*",
|
||||
"@deepseek-ai/dsh-lsp-local": "workspace:*",
|
||||
"@deepseek-ai/dsh-permission": "workspace:*",
|
||||
"@deepseek-ai/dsh-repeat-tool-guard": "workspace:*",
|
||||
"@deepseek-ai/dsh-sandbox-local": "workspace:*",
|
||||
@@ -36,6 +38,7 @@
|
||||
"@deepseek-ai/dsh-spill-policy": "workspace:*",
|
||||
"@deepseek-ai/dsh-tui-demo": "workspace:*",
|
||||
"@deepseek-ai/dsh-subagent": "workspace:*",
|
||||
"@deepseek-ai/dsh-subagent-acp": "workspace:*",
|
||||
"@deepseek-ai/dsh-subagent-fork": "workspace:*",
|
||||
"@deepseek-ai/dsh-subagent-spawn": "workspace:*",
|
||||
"@deepseek-ai/dsh-time-context": "workspace:*",
|
||||
@@ -45,6 +48,7 @@
|
||||
"@deepseek-ai/dsh-tool-fs": "workspace:*",
|
||||
"@deepseek-ai/dsh-tool-fs-search": "workspace:*",
|
||||
"@deepseek-ai/dsh-tool-goal": "workspace:*",
|
||||
"@deepseek-ai/dsh-tool-lsp": "workspace:*",
|
||||
"@deepseek-ai/dsh-tool-ralph": "workspace:*",
|
||||
"@deepseek-ai/dsh-tool-subagent": "workspace:*",
|
||||
"@deepseek-ai/dsh-tool-todo": "workspace:*",
|
||||
|
||||
Reference in New Issue
Block a user