test(snapshot): split pinned schemas into sidecars
This commit is contained in:
Tianyi Cui
@@ -48,7 +48,7 @@ const SCENARIOS: Scenario[] = [
|
||||
{ name: 'handshake', hasModelTurn: false, recorded: false },
|
||||
{ name: 'reject-extra-dirs', hasModelTurn: false, recorded: false },
|
||||
// text-turn is the pinned-header scenario: the minimal single text turn.
|
||||
// Its system-prompt.golden.md and JSONL tool list pin the composed header.
|
||||
// Its prompt and tool-schema sidecars pin the composed header.
|
||||
{ name: 'text-turn', hasModelTurn: true, recorded: true, pinsHeader: true },
|
||||
{ name: 'tool-call-turn', hasModelTurn: true, recorded: true },
|
||||
{ name: 'fs-terminal-card', hasModelTurn: true, recorded: true },
|
||||
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -0,0 +1,314 @@
|
||||
{
|
||||
"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]`. 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 (a background task reports the same marker via bash_output once it has finished). 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; poll it with `bash_output` and stop it with `bash_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. 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": "bash_kill",
|
||||
"description": "Ask the executor to kill a running background bash task by task id.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"task_id": {
|
||||
"type": "string",
|
||||
"description": "Task id returned by the bash tool."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"task_id"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "bash_output",
|
||||
"description": "Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"task_id": {
|
||||
"type": "string",
|
||||
"description": "Task id returned by the bash tool."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"task_id"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "cordis_inspect",
|
||||
"description": "Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"what": {
|
||||
"type": "string",
|
||||
"description": "Limit the report to one section. Omit for all sections.",
|
||||
"enum": [
|
||||
"services",
|
||||
"plugins",
|
||||
"tools",
|
||||
"dynamic",
|
||||
"api",
|
||||
"events"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "cordis_mount",
|
||||
"description": "Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"code": {
|
||||
"type": "string",
|
||||
"description": "Body of an async JS function; must `return` the plugin to mount."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"code"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "cordis_unmount",
|
||||
"description": "Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"id": {
|
||||
"type": "string",
|
||||
"description": "The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"id"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "run_code",
|
||||
"description": "Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"code": {
|
||||
"type": "string",
|
||||
"description": "The program: the body of an async TypeScript function."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"code"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"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.",
|
||||
"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."
|
||||
}
|
||||
},
|
||||
"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.",
|
||||
"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."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"description",
|
||||
"prompt"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"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": "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?, 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), `model` (override). 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."
|
||||
},
|
||||
"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"
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"deltas": []
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,261 @@
|
||||
{
|
||||
"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]`. 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 (a background task reports the same marker via bash_output once it has finished). 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; poll it with `bash_output` and stop it with `bash_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. 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": "bash_kill",
|
||||
"description": "Ask the executor to kill a running background bash task by task id.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"task_id": {
|
||||
"type": "string",
|
||||
"description": "Task id returned by the bash tool."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"task_id"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "bash_output",
|
||||
"description": "Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"task_id": {
|
||||
"type": "string",
|
||||
"description": "Task id returned by the bash tool."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"task_id"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "run_code",
|
||||
"description": "Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"code": {
|
||||
"type": "string",
|
||||
"description": "The program: the body of an async TypeScript function."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"code"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"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.",
|
||||
"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."
|
||||
}
|
||||
},
|
||||
"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.",
|
||||
"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."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"description",
|
||||
"prompt"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"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": "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?, 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), `model` (override). 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."
|
||||
},
|
||||
"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"
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"deltas": []
|
||||
}
|
||||
@@ -2,7 +2,7 @@
|
||||
{"type":"turn/start","seq":0,"time":1783611771394,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":1783611771394,"data":{"content":[{"type":"text","text":"Using ONE run_code program: call the bash tool twice — exactly `echo CODE_ONE` then exactly `echo CODE_TWO` — and return the two outputs joined with a plus sign. Then reply with that joined string only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":2,"time":1783611771396,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":3,"time":1783611771396,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}}]},"reason":"initial"}}
|
||||
{"type":"request/header","seq":3,"time":1783611771396,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":4,"time":1783611771869,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1783611771869,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}}
|
||||
{"type":"assistant/chunk","seq":6,"time":1783611771978,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}}
|
||||
|
||||
@@ -0,0 +1,21 @@
|
||||
{
|
||||
"initial": [
|
||||
{
|
||||
"name": "run_code",
|
||||
"description": "Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"code": {
|
||||
"type": "string",
|
||||
"description": "The program: the body of an async TypeScript function."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"code"
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"deltas": []
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,245 @@
|
||||
{
|
||||
"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]`. 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 (a background task reports the same marker via bash_output once it has finished). 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; poll it with `bash_output` and stop it with `bash_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. 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": "bash_kill",
|
||||
"description": "Ask the executor to kill a running background bash task by task id.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"task_id": {
|
||||
"type": "string",
|
||||
"description": "Task id returned by the bash tool."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"task_id"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "bash_output",
|
||||
"description": "Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"task_id": {
|
||||
"type": "string",
|
||||
"description": "Task id returned by the bash tool."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"task_id"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"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.",
|
||||
"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."
|
||||
}
|
||||
},
|
||||
"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.",
|
||||
"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."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"description",
|
||||
"prompt"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"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": "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?, 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), `model` (override). 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."
|
||||
},
|
||||
"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"
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"deltas": []
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,245 @@
|
||||
{
|
||||
"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]`. 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 (a background task reports the same marker via bash_output once it has finished). 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; poll it with `bash_output` and stop it with `bash_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. 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": "bash_kill",
|
||||
"description": "Ask the executor to kill a running background bash task by task id.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"task_id": {
|
||||
"type": "string",
|
||||
"description": "Task id returned by the bash tool."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"task_id"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "bash_output",
|
||||
"description": "Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"task_id": {
|
||||
"type": "string",
|
||||
"description": "Task id returned by the bash tool."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"task_id"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"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.",
|
||||
"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."
|
||||
}
|
||||
},
|
||||
"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.",
|
||||
"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."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"description",
|
||||
"prompt"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"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": "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?, 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), `model` (override). 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."
|
||||
},
|
||||
"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"
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"deltas": []
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,245 @@
|
||||
{
|
||||
"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]`. 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 (a background task reports the same marker via bash_output once it has finished). 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; poll it with `bash_output` and stop it with `bash_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. 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": "bash_kill",
|
||||
"description": "Ask the executor to kill a running background bash task by task id.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"task_id": {
|
||||
"type": "string",
|
||||
"description": "Task id returned by the bash tool."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"task_id"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "bash_output",
|
||||
"description": "Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"task_id": {
|
||||
"type": "string",
|
||||
"description": "Task id returned by the bash tool."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"task_id"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"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.",
|
||||
"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."
|
||||
}
|
||||
},
|
||||
"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.",
|
||||
"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."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"description",
|
||||
"prompt"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"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": "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?, 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), `model` (override). 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."
|
||||
},
|
||||
"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"
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"deltas": []
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,320 @@
|
||||
{
|
||||
"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]`. 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 (a background task reports the same marker via bash_output once it has finished). 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; poll it with `bash_output` and stop it with `bash_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. 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": "bash_kill",
|
||||
"description": "Ask the executor to kill a running background bash task by task id.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"task_id": {
|
||||
"type": "string",
|
||||
"description": "Task id returned by the bash tool."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"task_id"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "bash_output",
|
||||
"description": "Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"task_id": {
|
||||
"type": "string",
|
||||
"description": "Task id returned by the bash tool."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"task_id"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"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."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"file_path",
|
||||
"old_string",
|
||||
"new_string"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"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.",
|
||||
"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."
|
||||
}
|
||||
},
|
||||
"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.",
|
||||
"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."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"description",
|
||||
"prompt"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"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": "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?, 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), `model` (override). 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."
|
||||
},
|
||||
"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."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"file_path",
|
||||
"content"
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"deltas": []
|
||||
}
|
||||
Reference in New Issue
Block a user