diff --git a/apps/cli/config/core-web.cordis.yml b/apps/cli/config/core-web.cordis.yml
index d025aef7f4..2a5205cd0d 100644
--- a/apps/cli/config/core-web.cordis.yml
+++ b/apps/cli/config/core-web.cordis.yml
@@ -25,6 +25,9 @@
 - id: plan-mode
   disabled: true
 
+- id: tool-subagent-control
+  disabled: true
+
 - id: tool-subagent
   disabled: true
 
diff --git a/apps/cli/tests/shipped-composition.e2e.ts b/apps/cli/tests/shipped-composition.e2e.ts
index b6c5adba06..8371f795c8 100644
--- a/apps/cli/tests/shipped-composition.e2e.ts
+++ b/apps/cli/tests/shipped-composition.e2e.ts
@@ -35,6 +35,7 @@ const EXPECTED_TUI_TOOLS = [
   'get_goal',
   'ralph',
   'read',
+  'send_message',
   'skill',
   'str_replace_editor',
   'subagent',
diff --git a/apps/web/tests/shipped-composition.e2e.ts b/apps/web/tests/shipped-composition.e2e.ts
index 3f5ce4e4fa..a9162b631a 100644
--- a/apps/web/tests/shipped-composition.e2e.ts
+++ b/apps/web/tests/shipped-composition.e2e.ts
@@ -30,6 +30,7 @@ const EXPECTED_TOOLS = [
   'get_goal',
   'ralph',
   'read',
+  'send_message',
   'skill',
   'str_replace_editor',
   'subagent',
diff --git a/docs/core-data-structures/core.i18n.yaml b/docs/core-data-structures/core.i18n.yaml
index b1bdfb1a14..a156394d97 100644
--- a/docs/core-data-structures/core.i18n.yaml
+++ b/docs/core-data-structures/core.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write docs/core-data-structures/core.md
-core.md: 70c63d8a84963f56468b5fcdacb580a798de2e10
-core.zh.md: 280529b7de6c3e8546b71791367710c588ad9282
+core.md: 795256a2b30e44771baf8bcb7c1d541134692a02
+core.zh.md: 5cebff049aae53df9f0494da1fadc8dfa5d9ad09
diff --git a/docs/core-data-structures/core.zh.md b/docs/core-data-structures/core.zh.md
index 280529b7de..5cebff049a 100644
--- a/docs/core-data-structures/core.zh.md
+++ b/docs/core-data-structures/core.zh.md
@@ -568,6 +568,8 @@ interface CancelOptions {
 }
 ```
 
+`SteeringReceipt.outcome` 始终会解析。`admitted` 标识其不可变请求历史包含该确切消息的轮次与步骤；`rejected` 表示生命周期或终止策略先丢弃了该消息。同步输入校验仍会从 `steer()` 抛出异常。
+
 ```ts type-equiv
 /** Stable runtime cause accepted by {@link Agent.cancel}. */
 type AgentCancelCause =
@@ -669,16 +671,18 @@ interface Agent {
   followup(message: UserMessage): void
 
   /**
-   * Submit steering during prompt admission or an open turn — the
-   * `next-step`/wakeup preset of {@link send}. It stages for the next steering
-   * checkpoint before a request or stop decision. If the activity fails before
-   * that boundary, the remainder stays staged without waking the agent; retry
-   * or a later prompt takes it. Outside that window steering falls back to a
-   * woken follow-up turn, while cancellation or disposal may discard pending
-   * steering.
+   * Submit steering with a message-owned admission receipt — the
+   * `next-step`/wakeup preset of {@link send}. During prompt admission or an
+   * open turn, the message waits in the steering FIFO until a committed step
+   * snapshots it; outside that window it enters the ordinary queued FIFO. The
+   * receipt resolves `admitted` only after the message joins that step's
+   * immutable request history, or `rejected` when terminal policy,
+   * cancellation, or disposal discards it first. A non-terminal turn close may
+   * leave it staged for a later admitted prompt without settling the receipt.
    * @param message - identified steering content and its producer provenance.
+   * @returns the receipt for this exact message's eventual admission outcome.
    */
-  steer(message: UserMessage): void
+  steer(message: UserMessage): SteeringReceipt
 
   /**
    * Append model-facing context without running the model — the
diff --git a/examples/acp-agent/depth-two.cordis.snapshot.yml b/examples/acp-agent/depth-two.cordis.snapshot.yml
index 4e849d7835..3e292699d1 100644
--- a/examples/acp-agent/depth-two.cordis.snapshot.yml
+++ b/examples/acp-agent/depth-two.cordis.snapshot.yml
@@ -23,6 +23,7 @@
         config:
           provider: spawn
           toolName: subagent
+          backgroundMode: continuable
           maxDepth: 2
       # Re-pin the recorded model: cordis.yml ships deepseek-v4-pro, but this
       # scenario's corpus was captured on flash. A config patch replaces the
diff --git a/examples/acp-agent/depth-two.cordis.yml b/examples/acp-agent/depth-two.cordis.yml
index 25b0ee8e38..1af96e9283 100644
--- a/examples/acp-agent/depth-two.cordis.yml
+++ b/examples/acp-agent/depth-two.cordis.yml
@@ -10,4 +10,5 @@
         config:
           provider: spawn
           toolName: subagent
+          backgroundMode: continuable
           maxDepth: 2
diff --git a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl
index d264b20da8..4588ebb898 100644
--- a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl
@@ -2,8 +2,8 @@
 {"type":"turn/start","seq":0,"time":1785014475014,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
 {"type":"user/message","seq":1,"time":1785014475015,"data":{"content":[{"type":"text","text":"Using ONE run_code program, call tools.read on nested/task.txt. After the program finishes, answer the workspace handshake question using the newly discovered instructions: What is the Code Mode workspace handshake?"}],"source":{"kind":"user"},"role":"user","id":"a5066d26-ed57-4f98-8672-b34e883e1299"},"surfaceOp":"append"}
 {"type":"session/title","seq":2,"time":1785014475022,"data":{"title":"Using ONE run_code program, call","messageSeqs":[1],"source":{"kind":"fallback"}}}
-{"type":"user/message","seq":3,"time":1785122256262,"data":{"content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nWorkspace snapshot root instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","baseline":true,"changes":[{"action":"set","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"2119a7072358cc727f8d9c4cb7388e905b075fe6"}]},"role":"user","id":"c9aaa351-f7e6-40ef-955a-c5b8ee07667f"},"surfaceOp":"append"}
-{"type":"user/message","seq":4,"time":1785464674590,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"68f653ef-7b05-4a60-a517-6dda5d3f4be4"},"surfaceOp":"append"}
+{"type":"user/message","seq":3,"time":1785122256262,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"c9aaa351-f7e6-40ef-955a-c5b8ee07667f"},"surfaceOp":"append"}
+{"type":"user/message","seq":4,"time":1785464674590,"data":{"content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nWorkspace snapshot root instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","baseline":true,"changes":[{"action":"set","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"2119a7072358cc727f8d9c4cb7388e905b075fe6"}]},"role":"user","id":"68f653ef-7b05-4a60-a517-6dda5d3f4be4"},"surfaceOp":"append"}
 {"type":"step/start","seq":5,"time":1785464674590,"data":{"turn":1,"step":1}}
 {"type":"request/header","seq":6,"time":1785464674590,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/context","seq":7,"time":1785487644564,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
diff --git a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl
index 6b366448f1..81703a533d 100644
--- a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl
@@ -2,8 +2,8 @@
 {"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
 {"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"2243ae1a-2d65-4f9c-a972-d360b8cc08aa"},"surfaceOp":"append"}
 {"type":"session/title","seq":2,"time":1783654655603,"data":{"title":"Load the snapshot-skill skill with","messageSeqs":[1],"source":{"kind":"fallback"}}}
-{"type":"user/message","seq":3,"time":1784903324926,"data":{"content":[{"type":"text","text":"<system-reminder>\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n<available_skills>\n- `model-only-skill`: Prove user-disabled skills remain available to the model.\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n</available_skills>\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"dsh-tool-skill"},"role":"user","id":"021a7fcb-3d54-4ed9-8c2c-ca7565599fd8"},"surfaceOp":"append"}
-{"type":"user/message","seq":4,"time":1785464638477,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"22b51be2-4727-4990-96cd-7017c137152e"},"surfaceOp":"append"}
+{"type":"user/message","seq":3,"time":1784903324926,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"021a7fcb-3d54-4ed9-8c2c-ca7565599fd8"},"surfaceOp":"append"}
+{"type":"user/message","seq":4,"time":1785464638477,"data":{"content":[{"type":"text","text":"<system-reminder>\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n<available_skills>\n- `model-only-skill`: Prove user-disabled skills remain available to the model.\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n</available_skills>\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"dsh-tool-skill"},"role":"user","id":"22b51be2-4727-4990-96cd-7017c137152e"},"surfaceOp":"append"}
 {"type":"step/start","seq":5,"time":1785464638477,"data":{"turn":1,"step":1}}
 {"type":"request/header","seq":6,"time":1785464638478,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/context","seq":7,"time":1785487588943,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
diff --git a/examples/acp-agent/tests/snapshots/workspace-context/session.jsonl b/examples/acp-agent/tests/snapshots/workspace-context/session.jsonl
index 339ba5480d..0a568d3460 100644
--- a/examples/acp-agent/tests/snapshots/workspace-context/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/workspace-context/session.jsonl
@@ -2,8 +2,8 @@
 {"type":"turn/start","seq":0,"time":1783778297065,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
 {"type":"user/message","seq":1,"time":1783778297066,"data":{"content":[{"type":"text","text":"Read nested/task.txt, then read scope</system-reminder>/task.txt with the read tool, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"7cb62d32-ef8e-4d45-9b5e-d2a1fbdbabbd"},"surfaceOp":"append"}
 {"type":"session/title","seq":2,"time":1783778297066,"data":{"title":"Read nested/task.txt, then read scope</s","messageSeqs":[1],"source":{"kind":"fallback"}}}
-{"type":"user/message","seq":3,"time":1784903339799,"data":{"content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nRoot snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","baseline":true,"changes":[{"action":"set","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"2e18766c26603608f321508caae00ea8f4434d59"}]},"role":"user","id":"c95810d8-2b1e-42b9-9d81-82269ddb0035"},"surfaceOp":"append"}
-{"type":"user/message","seq":4,"time":1785464650864,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"6dd61dad-f320-4dda-a481-63ee420df9af"},"surfaceOp":"append"}
+{"type":"user/message","seq":3,"time":1784903339799,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"c95810d8-2b1e-42b9-9d81-82269ddb0035"},"surfaceOp":"append"}
+{"type":"user/message","seq":4,"time":1785464650864,"data":{"content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nRoot snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","baseline":true,"changes":[{"action":"set","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"2e18766c26603608f321508caae00ea8f4434d59"}]},"role":"user","id":"6dd61dad-f320-4dda-a481-63ee420df9af"},"surfaceOp":"append"}
 {"type":"step/start","seq":5,"time":1785464650864,"data":{"turn":1,"step":1}}
 {"type":"request/header","seq":6,"time":1785464650864,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/context","seq":7,"time":1785487608778,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
index 70ddefa5ea..ee0434e48c 100644
--- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
+++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
@@ -3,7 +3,7 @@
 {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"85750b5e-389a-4dfb-83e7-3341025692da"},"surfaceOp":"append"}
 {"type":"session/title","seq":2,"time":1783957884563,"data":{"title":"Reply with exactly DIRECT_CHILD_OK and","messageSeqs":[1],"source":{"kind":"fallback"}}}
 {"type":"step/start","seq":3,"time":1783957884564,"data":{"turn":1,"step":1}}
-{"type":"request/header","seq":4,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack 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.\n\nUse 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.\n\nUse 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.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n  /** 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`. */\n  bash: {\n    /** The bash command to execute. */\n    command: string;\n    /** 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\". */\n    description: string;\n    /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n    timeoutMs?: number;\n    /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n    workdir?: string;\n    /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n    run_in_background?: boolean;\n  } & Record<string, JsonValue>;\n  /** Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n  cordis_inspect: {\n    /** Limit the report to one section. Omit for all sections. */\n    what?: \"services\" | \"plugins\" | \"tools\" | \"temporary\" | \"api\" | \"events\";\n    /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n    name?: string;\n  } & Record<string, JsonValue>;\n  /** Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement a normal local, project, or repository Plugin through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n  cordis_mount: {\n    /** JavaScript body returning a temporary Plugin; evaluated now and saved nowhere. */\n    code: string;\n  } & Record<string, JsonValue>;\n  /** Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins. */\n  cordis_unmount: {\n    /** The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart. */\n    id: string;\n  } & Record<string, JsonValue>;\n  /** Edit an existing UTF-8 text file by replacing literal text. */\n  edit: {\n    /** Path to edit, resolved by the filesystem backend. */\n    file_path: string;\n    /** Literal text to replace. Must match exactly. */\n    old_string: string;\n    /** Literal replacement text. Use an empty string to delete the match. */\n    new_string: string;\n    /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n    replace_all?: boolean;\n  } & Record<string, JsonValue>;\n  /** 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. */\n  ralph: {\n    /** The immutable completion objective for every fresh Ralph round. */\n    objective: string;\n    /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n    maxRounds?: number;\n  } & Record<string, JsonValue>;\n  /** Read a UTF-8 text file and return line-numbered content. */\n  read: {\n    /** Path to read, resolved by the filesystem backend. */\n    file_path: string;\n    /** 1-based first line to return. Defaults to 1. */\n    offset?: number;\n    /** Maximum number of lines to return. Defaults to 2000. */\n    limit?: number;\n  } & Record<string, JsonValue>;\n  /** Send a follow-up message to a background subagent by its subagent id. If it is still working, the message joins its current task; if it has finished, this starts a new task that continues the same subagent conversation. Either way the response arrives through the returned task id — collect it with `task_output`. A failure means the message was NOT delivered. */\n  send_message: {\n    /** The subagent id returned when the background subagent was started. */\n    subagent_id: string;\n    /** The message to deliver to the subagent. */\n    message: string;\n  } & Record<string, JsonValue>;\n  /** 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. */\n  skill: {\n    /** The exact skill name from the available skills list. */\n    name: string;\n  } & Record<string, JsonValue>;\n  /** 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 start a continuable background subagent: you receive its subagent id and a task id; collect the result with `task_output`, stop it with `task_kill`, and send follow-up messages with `send_message`. */\n  subagent: {\n    /** A short (3-5 word) description of the delegated task, for display. */\n    description: string;\n    /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n    prompt: string;\n    /** Run as a continuable background subagent and return its subagent and task ids; collect with task_output, stop with task_kill, follow up with send_message. */\n    run_in_background?: boolean;\n  } & Record<string, JsonValue>;\n  /** 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 start a continuable background subagent: you receive its subagent id and a task id; collect the result with `task_output`, stop it with `task_kill`, and send follow-up messages with `send_message`. */\n  subagent_fork: {\n    /** A short (3-5 word) description of the delegated task, for display. */\n    description: string;\n    /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n    prompt: string;\n    /** Run as a continuable background subagent and return its subagent and task ids; collect with task_output, stop with task_kill, follow up with send_message. */\n    run_in_background?: boolean;\n  } & Record<string, JsonValue>;\n  /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n  task_kill: {\n    /** Task id returned by the tool that started the background work. */\n    task_id: string;\n    /** Optional short reason, recorded in the log and forwarded to the task. */\n    reason?: string;\n  } & Record<string, JsonValue>;\n  /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n  task_list: Record<string, JsonValue>;\n  /** 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. */\n  task_output: {\n    /** Task id returned by the tool that started the background work. */\n    task_id: string;\n    /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n    wait?: boolean;\n    /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n    timeout_ms?: number;\n  } & Record<string, JsonValue>;\n  /** 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). */\n  todo_write: {\n    /** The COMPLETE task list, replacing any previous list. */\n    todos: ({\n      /** What the task is — a short imperative line. */\n      content: string;\n      /** pending (not started) | in_progress (now) | completed (done). */\n      status: \"pending\" | \"in_progress\" | \"completed\";\n    })[];\n  } & Record<string, JsonValue>;\n  /** 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. The 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. Script-body hooks: - `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */\n  workflow: {\n    /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`). */\n    script: string;\n    /** The workflow identity block (plain JSON — never code). */\n    meta: {\n      /** Short kebab-case workflow name. */\n      name: string;\n      /** One-line description of what the workflow does. */\n      description: string;\n      /** Optional guidance on when this workflow applies. */\n      whenToUse?: string;\n      /** Optional phase declarations matched by phase() calls. */\n      phases?: ({\n        /** The phase title phase() calls match by exact string. */\n        title: string;\n        /** Optional one-line description of the phase. */\n        detail?: string;\n        /** Optional provider override this phase is expected to use. */\n        provider?: string;\n        /** Optional model override this phase is expected to use. */\n        model?: string;\n      } & Record<string, JsonValue>)[];\n    } & Record<string, JsonValue>;\n    /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n    args?: Record<string, JsonValue>;\n  } & Record<string, JsonValue>;\n  /** Create or fully replace a UTF-8 text file. */\n  write: {\n    /** Path to write, resolved by the filesystem backend. */\n    file_path: string;\n    /** Full UTF-8 text content to write. */\n    content: string;\n  } & Record<string, JsonValue>;\n}\n\ninterface ToolOutputMap {\n  bash: {\n    kind: \"background\";\n    taskId: string;\n  } | {\n    kind: \"foreground\";\n    exitCode: number | null;\n    signal: string | null;\n    timedOut: boolean;\n    aborted: boolean;\n    timeoutMs: number;\n    stdout: {\n      text: string;\n      truncated: boolean;\n      spillPath?: string;\n    };\n    stderr: {\n      text: string;\n      truncated: boolean;\n      spillPath?: string;\n    };\n    sandbox?: {\n      mode: string;\n      denied: boolean;\n      enforcement?: string;\n      runnerFailed?: boolean;\n    };\n  };\n  cordis_inspect: string;\n  cordis_mount: {\n    id: string;\n    pluginName: string;\n    state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n    provides: string[];\n    waitingFor: string[];\n  };\n  cordis_unmount: {\n    id: string;\n    pluginName: string;\n  };\n  edit: {\n    path: string;\n    before: string;\n    after: string;\n  };\n  ralph: {\n    runId: string;\n    agentsStarted: number;\n    result: JsonValue;\n  };\n  read: {\n    path: string;\n    offset: number;\n    lines: {\n      number: number;\n      text: string;\n    }[];\n    totalLines: number;\n  };\n  send_message: {\n    route: \"steered\" | \"started\";\n    taskId: string;\n  };\n  skill: {\n    name: string;\n    provider: string;\n    resourceBase?: {\n      kind: \"directory\";\n      path: string;\n    } | {\n      kind: \"url\";\n      url: string;\n    } | {\n      kind: \"opaque\";\n      description: string;\n    };\n    content: string;\n  };\n  subagent: {\n    kind: \"background\";\n    taskId: string;\n    subagentId?: string;\n  } | {\n    kind: \"foreground\";\n    runId: string;\n    output: JsonValue[];\n  };\n  subagent_fork: {\n    kind: \"background\";\n    taskId: string;\n    subagentId?: string;\n  } | {\n    kind: \"foreground\";\n    runId: string;\n    output: JsonValue[];\n  };\n  task_kill: {\n    outcome: \"cancellation-requested\" | \"already-finished\";\n    task: {\n      id: string;\n      kind: string;\n      label: string;\n      status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n      detail?: string;\n      startedAt: number;\n      finishedAt?: number;\n    };\n  };\n  task_list: ({\n    id: string;\n    kind: string;\n    label: string;\n    status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n    detail?: string;\n    startedAt: number;\n    finishedAt?: number;\n  })[];\n  task_output: {\n    text: string;\n    task: {\n      id: string;\n      kind: string;\n      label: string;\n      status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n      detail?: string;\n      startedAt: number;\n      finishedAt?: number;\n    };\n  };\n  todo_write: {\n    todos: ({\n      content: string;\n      status: \"pending\" | \"in_progress\" | \"completed\";\n    })[];\n    counts: {\n      pending: number;\n      inProgress: number;\n      completed: number;\n    };\n  };\n  workflow: {\n    runId: string;\n    agentsStarted: number;\n    result: JsonValue;\n  };\n  write: {\n    path: string;\n    operation: \"create\" | \"update\";\n    before: string | null;\n    after: string;\n  };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n  readonly name: \"ToolCallError\";\n  readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n  [K in ToolName]: (args: ToolArgsMap[K]) => Promise<ToolOutputMap[K]>;\n}\n```","tools":[{"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`.","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."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","temporary","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement a normal local, project, or repository Plugin through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"JavaScript body returning a temporary Plugin; evaluated now and saved nowhere."}},"required":["code"]}},{"name":"cordis_unmount","description":"Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins.","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart."}},"required":["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":"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":"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."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"name":"send_message","description":"Send a follow-up message to a background subagent by its subagent id. If it is still working, the message joins its current task; if it has finished, this starts a new task that continues the same subagent conversation. Either way the response arrives through the returned task id — collect it with `task_output`. A failure means the message was NOT delivered.","parameters":{"type":"object","properties":{"subagent_id":{"type":"string","description":"The subagent id returned when the background subagent was started."},"message":{"type":"string","description":"The message to deliver to the subagent."}},"required":["subagent_id","message"]}},{"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 start a continuable background subagent: you receive its subagent id and a task id; collect the result with `task_output`, stop it with `task_kill`, and send follow-up messages with `send_message`.","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 continuable background subagent and return its subagent and task ids; collect with task_output, stop with task_kill, follow up with send_message."}},"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 start a continuable background subagent: you receive its subagent id and a task id; collect the result with `task_output`, stop it with `task_kill`, and send follow-up messages with `send_message`.","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 continuable background subagent and return its subagent and task ids; collect with task_output, stop with task_kill, follow up with send_message."}},"required":["description","prompt"]}},{"name":"task_kill","description":"Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"reason":{"type":"string","description":"Optional short reason, recorded in the log and forwarded to the task."}},"required":["task_id"]}},{"name":"task_list","description":"List your background tasks (running and finished) with their ids, kinds, and statuses.","parameters":{"type":"object","properties":{}}},{"name":"task_output","description":"Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"wait":{"type":"boolean","description":"Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."},"timeout_ms":{"type":"number","description":"Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."}},"required":["task_id"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","additionalProperties":true,"properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","additionalProperties":true,"properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).","additionalProperties":true}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}}
+{"type":"request/header","seq":4,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack 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.\n\nUse 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.\n\nUse 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.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n  /** 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`. */\n  bash: {\n    /** The bash command to execute. */\n    command: string;\n    /** 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\". */\n    description: string;\n    /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n    timeoutMs?: number;\n    /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n    workdir?: string;\n    /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n    run_in_background?: boolean;\n  } & Record<string, JsonValue>;\n  /** Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n  cordis_inspect: {\n    /** Limit the report to one section. Omit for all sections. */\n    what?: \"services\" | \"plugins\" | \"tools\" | \"temporary\" | \"api\" | \"events\";\n    /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n    name?: string;\n  } & Record<string, JsonValue>;\n  /** Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement a normal local, project, or repository Plugin through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n  cordis_mount: {\n    /** JavaScript body returning a temporary Plugin; evaluated now and saved nowhere. */\n    code: string;\n  } & Record<string, JsonValue>;\n  /** Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins. */\n  cordis_unmount: {\n    /** The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart. */\n    id: string;\n  } & Record<string, JsonValue>;\n  /** Edit an existing UTF-8 text file by replacing literal text. */\n  edit: {\n    /** Path to edit, resolved by the filesystem backend. */\n    file_path: string;\n    /** Literal text to replace. Must match exactly. */\n    old_string: string;\n    /** Literal replacement text. Use an empty string to delete the match. */\n    new_string: string;\n    /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n    replace_all?: boolean;\n  } & Record<string, JsonValue>;\n  /** 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. */\n  ralph: {\n    /** The immutable completion objective for every fresh Ralph round. */\n    objective: string;\n    /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n    maxRounds?: number;\n  } & Record<string, JsonValue>;\n  /** Read a UTF-8 text file and return line-numbered content. */\n  read: {\n    /** Path to read, resolved by the filesystem backend. */\n    file_path: string;\n    /** 1-based first line to return. Defaults to 1. */\n    offset?: number;\n    /** Maximum number of lines to return. Defaults to 2000. */\n    limit?: number;\n  } & Record<string, JsonValue>;\n  /** Send a follow-up message to a background subagent by its subagent id. If it is still working, the message joins its current task; if it has finished, this starts a new task that continues the same subagent conversation. Either way the response arrives through the returned task id — collect it with `task_output`. A failure means the message was NOT delivered. */\n  send_message: {\n    /** The subagent id returned when the background subagent was started. */\n    subagent_id: string;\n    /** The message to deliver to the subagent. */\n    message: string;\n  } & Record<string, JsonValue>;\n  /** 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. */\n  skill: {\n    /** The exact skill name from the available skills list. */\n    name: string;\n  } & Record<string, JsonValue>;\n  /** 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 start a continuable background subagent: you receive its stable subagent id and current task id; collect the result with `task_output` and stop it with `task_kill`. */\n  subagent: {\n    /** A short (3-5 word) description of the delegated task, for display. */\n    description: string;\n    /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n    prompt: string;\n    /** Run as a continuable background subagent and return its subagent and task ids; collect with task_output or stop with task_kill. */\n    run_in_background?: boolean;\n  } & Record<string, JsonValue>;\n  /** 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 start a continuable background subagent: you receive its stable subagent id and current task id; collect the result with `task_output` and stop it with `task_kill`. */\n  subagent_fork: {\n    /** A short (3-5 word) description of the delegated task, for display. */\n    description: string;\n    /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n    prompt: string;\n    /** Run as a continuable background subagent and return its subagent and task ids; collect with task_output or stop with task_kill. */\n    run_in_background?: boolean;\n  } & Record<string, JsonValue>;\n  /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n  task_kill: {\n    /** Task id returned by the tool that started the background work. */\n    task_id: string;\n    /** Optional short reason, recorded in the log and forwarded to the task. */\n    reason?: string;\n  } & Record<string, JsonValue>;\n  /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n  task_list: Record<string, JsonValue>;\n  /** 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. */\n  task_output: {\n    /** Task id returned by the tool that started the background work. */\n    task_id: string;\n    /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n    wait?: boolean;\n    /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n    timeout_ms?: number;\n  } & Record<string, JsonValue>;\n  /** 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). */\n  todo_write: {\n    /** The COMPLETE task list, replacing any previous list. */\n    todos: ({\n      /** What the task is — a short imperative line. */\n      content: string;\n      /** pending (not started) | in_progress (now) | completed (done). */\n      status: \"pending\" | \"in_progress\" | \"completed\";\n    })[];\n  } & Record<string, JsonValue>;\n  /** 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. The 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. Script-body hooks: - `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */\n  workflow: {\n    /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`). */\n    script: string;\n    /** The workflow identity block (plain JSON — never code). */\n    meta: {\n      /** Short kebab-case workflow name. */\n      name: string;\n      /** One-line description of what the workflow does. */\n      description: string;\n      /** Optional guidance on when this workflow applies. */\n      whenToUse?: string;\n      /** Optional phase declarations matched by phase() calls. */\n      phases?: ({\n        /** The phase title phase() calls match by exact string. */\n        title: string;\n        /** Optional one-line description of the phase. */\n        detail?: string;\n        /** Optional provider override this phase is expected to use. */\n        provider?: string;\n        /** Optional model override this phase is expected to use. */\n        model?: string;\n      } & Record<string, JsonValue>)[];\n    } & Record<string, JsonValue>;\n    /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n    args?: Record<string, JsonValue>;\n  } & Record<string, JsonValue>;\n  /** Create or fully replace a UTF-8 text file. */\n  write: {\n    /** Path to write, resolved by the filesystem backend. */\n    file_path: string;\n    /** Full UTF-8 text content to write. */\n    content: string;\n  } & Record<string, JsonValue>;\n}\n\ninterface ToolOutputMap {\n  bash: {\n    kind: \"background\";\n    taskId: string;\n  } | {\n    kind: \"foreground\";\n    exitCode: number | null;\n    signal: string | null;\n    timedOut: boolean;\n    aborted: boolean;\n    timeoutMs: number;\n    stdout: {\n      text: string;\n      truncated: boolean;\n      spillPath?: string;\n    };\n    stderr: {\n      text: string;\n      truncated: boolean;\n      spillPath?: string;\n    };\n    sandbox?: {\n      mode: string;\n      denied: boolean;\n      enforcement?: string;\n      runnerFailed?: boolean;\n    };\n  };\n  cordis_inspect: string;\n  cordis_mount: {\n    id: string;\n    pluginName: string;\n    state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n    provides: string[];\n    waitingFor: string[];\n  };\n  cordis_unmount: {\n    id: string;\n    pluginName: string;\n  };\n  edit: {\n    path: string;\n    before: string;\n    after: string;\n  };\n  ralph: {\n    runId: string;\n    agentsStarted: number;\n    result: JsonValue;\n  };\n  read: {\n    path: string;\n    offset: number;\n    lines: {\n      number: number;\n      text: string;\n    }[];\n    totalLines: number;\n  };\n  send_message: {\n    route: \"steered\" | \"started\";\n    taskId: string;\n  };\n  skill: {\n    name: string;\n    provider: string;\n    resourceBase?: {\n      kind: \"directory\";\n      path: string;\n    } | {\n      kind: \"url\";\n      url: string;\n    } | {\n      kind: \"opaque\";\n      description: string;\n    };\n    content: string;\n  };\n  subagent: {\n    kind: \"background\";\n    taskId: string;\n    subagentId?: string;\n  } | {\n    kind: \"foreground\";\n    runId: string;\n    output: JsonValue[];\n  };\n  subagent_fork: {\n    kind: \"background\";\n    taskId: string;\n    subagentId?: string;\n  } | {\n    kind: \"foreground\";\n    runId: string;\n    output: JsonValue[];\n  };\n  task_kill: {\n    outcome: \"cancellation-requested\" | \"already-finished\";\n    task: {\n      id: string;\n      kind: string;\n      label: string;\n      status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n      detail?: string;\n      startedAt: number;\n      finishedAt?: number;\n    };\n  };\n  task_list: ({\n    id: string;\n    kind: string;\n    label: string;\n    status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n    detail?: string;\n    startedAt: number;\n    finishedAt?: number;\n  })[];\n  task_output: {\n    text: string;\n    task: {\n      id: string;\n      kind: string;\n      label: string;\n      status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n      detail?: string;\n      startedAt: number;\n      finishedAt?: number;\n    };\n  };\n  todo_write: {\n    todos: ({\n      content: string;\n      status: \"pending\" | \"in_progress\" | \"completed\";\n    })[];\n    counts: {\n      pending: number;\n      inProgress: number;\n      completed: number;\n    };\n  };\n  workflow: {\n    runId: string;\n    agentsStarted: number;\n    result: JsonValue;\n  };\n  write: {\n    path: string;\n    operation: \"create\" | \"update\";\n    before: string | null;\n    after: string;\n  };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n  readonly name: \"ToolCallError\";\n  readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n  [K in ToolName]: (args: ToolArgsMap[K]) => Promise<ToolOutputMap[K]>;\n}\n```","tools":[{"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`.","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."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","temporary","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement a normal local, project, or repository Plugin through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"JavaScript body returning a temporary Plugin; evaluated now and saved nowhere."}},"required":["code"]}},{"name":"cordis_unmount","description":"Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins.","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart."}},"required":["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":"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":"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."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"name":"send_message","description":"Send a follow-up message to a background subagent by its subagent id. If it is still working, the message joins its current task; if it has finished, this starts a new task that continues the same subagent conversation. Either way the response arrives through the returned task id — collect it with `task_output`. A failure means the message was NOT delivered.","parameters":{"type":"object","properties":{"subagent_id":{"type":"string","description":"The subagent id returned when the background subagent was started."},"message":{"type":"string","description":"The message to deliver to the subagent."}},"required":["subagent_id","message"]}},{"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 start a continuable background subagent: you receive its stable subagent id and current task id; collect the result with `task_output` and stop it 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 continuable background subagent and return its subagent and task ids; 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 start a continuable background subagent: you receive its stable subagent id and current task id; collect the result with `task_output` and stop it 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 continuable background subagent and return its subagent and task ids; collect with task_output or stop with task_kill."}},"required":["description","prompt"]}},{"name":"task_kill","description":"Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"reason":{"type":"string","description":"Optional short reason, recorded in the log and forwarded to the task."}},"required":["task_id"]}},{"name":"task_list","description":"List your background tasks (running and finished) with their ids, kinds, and statuses.","parameters":{"type":"object","properties":{}}},{"name":"task_output","description":"Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"wait":{"type":"boolean","description":"Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."},"timeout_ms":{"type":"number","description":"Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."}},"required":["task_id"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","additionalProperties":true,"properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","additionalProperties":true,"properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).","additionalProperties":true}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}}
 {"type":"request/context","seq":5,"time":1785460681625,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
 {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
 {"type":"assistant/chunk","seq":7,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}}
diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
index 3d58a9067a..3cb4cabd02 100644
--- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
+++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
@@ -3,7 +3,7 @@
 {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"2b9d695a-5ba1-4520-8130-d618bc1a4743"},"surfaceOp":"append"}
 {"type":"session/title","seq":2,"time":1783957884700,"data":{"title":"Reply with exactly WORKFLOW_CHILD_OK and","messageSeqs":[1],"source":{"kind":"fallback"}}}
 {"type":"step/start","seq":3,"time":1783957884700,"data":{"turn":1,"step":1}}
-{"type":"request/header","seq":4,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack 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.\n\nUse 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.\n\nUse 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.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n  /** 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`. */\n  bash: {\n    /** The bash command to execute. */\n    command: string;\n    /** 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\". */\n    description: string;\n    /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n    timeoutMs?: number;\n    /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n    workdir?: string;\n    /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n    run_in_background?: boolean;\n  } & Record<string, JsonValue>;\n  /** Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n  cordis_inspect: {\n    /** Limit the report to one section. Omit for all sections. */\n    what?: \"services\" | \"plugins\" | \"tools\" | \"temporary\" | \"api\" | \"events\";\n    /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n    name?: string;\n  } & Record<string, JsonValue>;\n  /** Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement a normal local, project, or repository Plugin through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n  cordis_mount: {\n    /** JavaScript body returning a temporary Plugin; evaluated now and saved nowhere. */\n    code: string;\n  } & Record<string, JsonValue>;\n  /** Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins. */\n  cordis_unmount: {\n    /** The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart. */\n    id: string;\n  } & Record<string, JsonValue>;\n  /** Edit an existing UTF-8 text file by replacing literal text. */\n  edit: {\n    /** Path to edit, resolved by the filesystem backend. */\n    file_path: string;\n    /** Literal text to replace. Must match exactly. */\n    old_string: string;\n    /** Literal replacement text. Use an empty string to delete the match. */\n    new_string: string;\n    /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n    replace_all?: boolean;\n  } & Record<string, JsonValue>;\n  /** 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. */\n  ralph: {\n    /** The immutable completion objective for every fresh Ralph round. */\n    objective: string;\n    /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n    maxRounds?: number;\n  } & Record<string, JsonValue>;\n  /** Read a UTF-8 text file and return line-numbered content. */\n  read: {\n    /** Path to read, resolved by the filesystem backend. */\n    file_path: string;\n    /** 1-based first line to return. Defaults to 1. */\n    offset?: number;\n    /** Maximum number of lines to return. Defaults to 2000. */\n    limit?: number;\n  } & Record<string, JsonValue>;\n  /** Send a follow-up message to a background subagent by its subagent id. If it is still working, the message joins its current task; if it has finished, this starts a new task that continues the same subagent conversation. Either way the response arrives through the returned task id — collect it with `task_output`. A failure means the message was NOT delivered. */\n  send_message: {\n    /** The subagent id returned when the background subagent was started. */\n    subagent_id: string;\n    /** The message to deliver to the subagent. */\n    message: string;\n  } & Record<string, JsonValue>;\n  /** 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. */\n  skill: {\n    /** The exact skill name from the available skills list. */\n    name: string;\n  } & Record<string, JsonValue>;\n  /** 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 start a continuable background subagent: you receive its subagent id and a task id; collect the result with `task_output`, stop it with `task_kill`, and send follow-up messages with `send_message`. */\n  subagent: {\n    /** A short (3-5 word) description of the delegated task, for display. */\n    description: string;\n    /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n    prompt: string;\n    /** Run as a continuable background subagent and return its subagent and task ids; collect with task_output, stop with task_kill, follow up with send_message. */\n    run_in_background?: boolean;\n  } & Record<string, JsonValue>;\n  /** 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 start a continuable background subagent: you receive its subagent id and a task id; collect the result with `task_output`, stop it with `task_kill`, and send follow-up messages with `send_message`. */\n  subagent_fork: {\n    /** A short (3-5 word) description of the delegated task, for display. */\n    description: string;\n    /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n    prompt: string;\n    /** Run as a continuable background subagent and return its subagent and task ids; collect with task_output, stop with task_kill, follow up with send_message. */\n    run_in_background?: boolean;\n  } & Record<string, JsonValue>;\n  /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n  task_kill: {\n    /** Task id returned by the tool that started the background work. */\n    task_id: string;\n    /** Optional short reason, recorded in the log and forwarded to the task. */\n    reason?: string;\n  } & Record<string, JsonValue>;\n  /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n  task_list: Record<string, JsonValue>;\n  /** 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. */\n  task_output: {\n    /** Task id returned by the tool that started the background work. */\n    task_id: string;\n    /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n    wait?: boolean;\n    /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n    timeout_ms?: number;\n  } & Record<string, JsonValue>;\n  /** 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). */\n  todo_write: {\n    /** The COMPLETE task list, replacing any previous list. */\n    todos: ({\n      /** What the task is — a short imperative line. */\n      content: string;\n      /** pending (not started) | in_progress (now) | completed (done). */\n      status: \"pending\" | \"in_progress\" | \"completed\";\n    })[];\n  } & Record<string, JsonValue>;\n  /** 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. The 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. Script-body hooks: - `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */\n  workflow: {\n    /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`). */\n    script: string;\n    /** The workflow identity block (plain JSON — never code). */\n    meta: {\n      /** Short kebab-case workflow name. */\n      name: string;\n      /** One-line description of what the workflow does. */\n      description: string;\n      /** Optional guidance on when this workflow applies. */\n      whenToUse?: string;\n      /** Optional phase declarations matched by phase() calls. */\n      phases?: ({\n        /** The phase title phase() calls match by exact string. */\n        title: string;\n        /** Optional one-line description of the phase. */\n        detail?: string;\n        /** Optional provider override this phase is expected to use. */\n        provider?: string;\n        /** Optional model override this phase is expected to use. */\n        model?: string;\n      } & Record<string, JsonValue>)[];\n    } & Record<string, JsonValue>;\n    /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n    args?: Record<string, JsonValue>;\n  } & Record<string, JsonValue>;\n  /** Create or fully replace a UTF-8 text file. */\n  write: {\n    /** Path to write, resolved by the filesystem backend. */\n    file_path: string;\n    /** Full UTF-8 text content to write. */\n    content: string;\n  } & Record<string, JsonValue>;\n}\n\ninterface ToolOutputMap {\n  bash: {\n    kind: \"background\";\n    taskId: string;\n  } | {\n    kind: \"foreground\";\n    exitCode: number | null;\n    signal: string | null;\n    timedOut: boolean;\n    aborted: boolean;\n    timeoutMs: number;\n    stdout: {\n      text: string;\n      truncated: boolean;\n      spillPath?: string;\n    };\n    stderr: {\n      text: string;\n      truncated: boolean;\n      spillPath?: string;\n    };\n    sandbox?: {\n      mode: string;\n      denied: boolean;\n      enforcement?: string;\n      runnerFailed?: boolean;\n    };\n  };\n  cordis_inspect: string;\n  cordis_mount: {\n    id: string;\n    pluginName: string;\n    state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n    provides: string[];\n    waitingFor: string[];\n  };\n  cordis_unmount: {\n    id: string;\n    pluginName: string;\n  };\n  edit: {\n    path: string;\n    before: string;\n    after: string;\n  };\n  ralph: {\n    runId: string;\n    agentsStarted: number;\n    result: JsonValue;\n  };\n  read: {\n    path: string;\n    offset: number;\n    lines: {\n      number: number;\n      text: string;\n    }[];\n    totalLines: number;\n  };\n  send_message: {\n    route: \"steered\" | \"started\";\n    taskId: string;\n  };\n  skill: {\n    name: string;\n    provider: string;\n    resourceBase?: {\n      kind: \"directory\";\n      path: string;\n    } | {\n      kind: \"url\";\n      url: string;\n    } | {\n      kind: \"opaque\";\n      description: string;\n    };\n    content: string;\n  };\n  subagent: {\n    kind: \"background\";\n    taskId: string;\n    subagentId?: string;\n  } | {\n    kind: \"foreground\";\n    runId: string;\n    output: JsonValue[];\n  };\n  subagent_fork: {\n    kind: \"background\";\n    taskId: string;\n    subagentId?: string;\n  } | {\n    kind: \"foreground\";\n    runId: string;\n    output: JsonValue[];\n  };\n  task_kill: {\n    outcome: \"cancellation-requested\" | \"already-finished\";\n    task: {\n      id: string;\n      kind: string;\n      label: string;\n      status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n      detail?: string;\n      startedAt: number;\n      finishedAt?: number;\n    };\n  };\n  task_list: ({\n    id: string;\n    kind: string;\n    label: string;\n    status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n    detail?: string;\n    startedAt: number;\n    finishedAt?: number;\n  })[];\n  task_output: {\n    text: string;\n    task: {\n      id: string;\n      kind: string;\n      label: string;\n      status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n      detail?: string;\n      startedAt: number;\n      finishedAt?: number;\n    };\n  };\n  todo_write: {\n    todos: ({\n      content: string;\n      status: \"pending\" | \"in_progress\" | \"completed\";\n    })[];\n    counts: {\n      pending: number;\n      inProgress: number;\n      completed: number;\n    };\n  };\n  workflow: {\n    runId: string;\n    agentsStarted: number;\n    result: JsonValue;\n  };\n  write: {\n    path: string;\n    operation: \"create\" | \"update\";\n    before: string | null;\n    after: string;\n  };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n  readonly name: \"ToolCallError\";\n  readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n  [K in ToolName]: (args: ToolArgsMap[K]) => Promise<ToolOutputMap[K]>;\n}\n```","tools":[{"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`.","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."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","temporary","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement a normal local, project, or repository Plugin through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"JavaScript body returning a temporary Plugin; evaluated now and saved nowhere."}},"required":["code"]}},{"name":"cordis_unmount","description":"Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins.","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart."}},"required":["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":"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":"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."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"name":"send_message","description":"Send a follow-up message to a background subagent by its subagent id. If it is still working, the message joins its current task; if it has finished, this starts a new task that continues the same subagent conversation. Either way the response arrives through the returned task id — collect it with `task_output`. A failure means the message was NOT delivered.","parameters":{"type":"object","properties":{"subagent_id":{"type":"string","description":"The subagent id returned when the background subagent was started."},"message":{"type":"string","description":"The message to deliver to the subagent."}},"required":["subagent_id","message"]}},{"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 start a continuable background subagent: you receive its subagent id and a task id; collect the result with `task_output`, stop it with `task_kill`, and send follow-up messages with `send_message`.","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 continuable background subagent and return its subagent and task ids; collect with task_output, stop with task_kill, follow up with send_message."}},"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 start a continuable background subagent: you receive its subagent id and a task id; collect the result with `task_output`, stop it with `task_kill`, and send follow-up messages with `send_message`.","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 continuable background subagent and return its subagent and task ids; collect with task_output, stop with task_kill, follow up with send_message."}},"required":["description","prompt"]}},{"name":"task_kill","description":"Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"reason":{"type":"string","description":"Optional short reason, recorded in the log and forwarded to the task."}},"required":["task_id"]}},{"name":"task_list","description":"List your background tasks (running and finished) with their ids, kinds, and statuses.","parameters":{"type":"object","properties":{}}},{"name":"task_output","description":"Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"wait":{"type":"boolean","description":"Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."},"timeout_ms":{"type":"number","description":"Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."}},"required":["task_id"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","additionalProperties":true,"properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","additionalProperties":true,"properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).","additionalProperties":true}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}}
+{"type":"request/header","seq":4,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack 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.\n\nUse 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.\n\nUse 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.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n  /** 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`. */\n  bash: {\n    /** The bash command to execute. */\n    command: string;\n    /** 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\". */\n    description: string;\n    /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n    timeoutMs?: number;\n    /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n    workdir?: string;\n    /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n    run_in_background?: boolean;\n  } & Record<string, JsonValue>;\n  /** Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n  cordis_inspect: {\n    /** Limit the report to one section. Omit for all sections. */\n    what?: \"services\" | \"plugins\" | \"tools\" | \"temporary\" | \"api\" | \"events\";\n    /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n    name?: string;\n  } & Record<string, JsonValue>;\n  /** Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement a normal local, project, or repository Plugin through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n  cordis_mount: {\n    /** JavaScript body returning a temporary Plugin; evaluated now and saved nowhere. */\n    code: string;\n  } & Record<string, JsonValue>;\n  /** Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins. */\n  cordis_unmount: {\n    /** The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart. */\n    id: string;\n  } & Record<string, JsonValue>;\n  /** Edit an existing UTF-8 text file by replacing literal text. */\n  edit: {\n    /** Path to edit, resolved by the filesystem backend. */\n    file_path: string;\n    /** Literal text to replace. Must match exactly. */\n    old_string: string;\n    /** Literal replacement text. Use an empty string to delete the match. */\n    new_string: string;\n    /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n    replace_all?: boolean;\n  } & Record<string, JsonValue>;\n  /** 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. */\n  ralph: {\n    /** The immutable completion objective for every fresh Ralph round. */\n    objective: string;\n    /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n    maxRounds?: number;\n  } & Record<string, JsonValue>;\n  /** Read a UTF-8 text file and return line-numbered content. */\n  read: {\n    /** Path to read, resolved by the filesystem backend. */\n    file_path: string;\n    /** 1-based first line to return. Defaults to 1. */\n    offset?: number;\n    /** Maximum number of lines to return. Defaults to 2000. */\n    limit?: number;\n  } & Record<string, JsonValue>;\n  /** Send a follow-up message to a background subagent by its subagent id. If it is still working, the message joins its current task; if it has finished, this starts a new task that continues the same subagent conversation. Either way the response arrives through the returned task id — collect it with `task_output`. A failure means the message was NOT delivered. */\n  send_message: {\n    /** The subagent id returned when the background subagent was started. */\n    subagent_id: string;\n    /** The message to deliver to the subagent. */\n    message: string;\n  } & Record<string, JsonValue>;\n  /** 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. */\n  skill: {\n    /** The exact skill name from the available skills list. */\n    name: string;\n  } & Record<string, JsonValue>;\n  /** 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 start a continuable background subagent: you receive its stable subagent id and current task id; collect the result with `task_output` and stop it with `task_kill`. */\n  subagent: {\n    /** A short (3-5 word) description of the delegated task, for display. */\n    description: string;\n    /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n    prompt: string;\n    /** Run as a continuable background subagent and return its subagent and task ids; collect with task_output or stop with task_kill. */\n    run_in_background?: boolean;\n  } & Record<string, JsonValue>;\n  /** 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 start a continuable background subagent: you receive its stable subagent id and current task id; collect the result with `task_output` and stop it with `task_kill`. */\n  subagent_fork: {\n    /** A short (3-5 word) description of the delegated task, for display. */\n    description: string;\n    /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n    prompt: string;\n    /** Run as a continuable background subagent and return its subagent and task ids; collect with task_output or stop with task_kill. */\n    run_in_background?: boolean;\n  } & Record<string, JsonValue>;\n  /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n  task_kill: {\n    /** Task id returned by the tool that started the background work. */\n    task_id: string;\n    /** Optional short reason, recorded in the log and forwarded to the task. */\n    reason?: string;\n  } & Record<string, JsonValue>;\n  /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n  task_list: Record<string, JsonValue>;\n  /** 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. */\n  task_output: {\n    /** Task id returned by the tool that started the background work. */\n    task_id: string;\n    /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n    wait?: boolean;\n    /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n    timeout_ms?: number;\n  } & Record<string, JsonValue>;\n  /** 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). */\n  todo_write: {\n    /** The COMPLETE task list, replacing any previous list. */\n    todos: ({\n      /** What the task is — a short imperative line. */\n      content: string;\n      /** pending (not started) | in_progress (now) | completed (done). */\n      status: \"pending\" | \"in_progress\" | \"completed\";\n    })[];\n  } & Record<string, JsonValue>;\n  /** 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. The 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. Script-body hooks: - `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */\n  workflow: {\n    /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`). */\n    script: string;\n    /** The workflow identity block (plain JSON — never code). */\n    meta: {\n      /** Short kebab-case workflow name. */\n      name: string;\n      /** One-line description of what the workflow does. */\n      description: string;\n      /** Optional guidance on when this workflow applies. */\n      whenToUse?: string;\n      /** Optional phase declarations matched by phase() calls. */\n      phases?: ({\n        /** The phase title phase() calls match by exact string. */\n        title: string;\n        /** Optional one-line description of the phase. */\n        detail?: string;\n        /** Optional provider override this phase is expected to use. */\n        provider?: string;\n        /** Optional model override this phase is expected to use. */\n        model?: string;\n      } & Record<string, JsonValue>)[];\n    } & Record<string, JsonValue>;\n    /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n    args?: Record<string, JsonValue>;\n  } & Record<string, JsonValue>;\n  /** Create or fully replace a UTF-8 text file. */\n  write: {\n    /** Path to write, resolved by the filesystem backend. */\n    file_path: string;\n    /** Full UTF-8 text content to write. */\n    content: string;\n  } & Record<string, JsonValue>;\n}\n\ninterface ToolOutputMap {\n  bash: {\n    kind: \"background\";\n    taskId: string;\n  } | {\n    kind: \"foreground\";\n    exitCode: number | null;\n    signal: string | null;\n    timedOut: boolean;\n    aborted: boolean;\n    timeoutMs: number;\n    stdout: {\n      text: string;\n      truncated: boolean;\n      spillPath?: string;\n    };\n    stderr: {\n      text: string;\n      truncated: boolean;\n      spillPath?: string;\n    };\n    sandbox?: {\n      mode: string;\n      denied: boolean;\n      enforcement?: string;\n      runnerFailed?: boolean;\n    };\n  };\n  cordis_inspect: string;\n  cordis_mount: {\n    id: string;\n    pluginName: string;\n    state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n    provides: string[];\n    waitingFor: string[];\n  };\n  cordis_unmount: {\n    id: string;\n    pluginName: string;\n  };\n  edit: {\n    path: string;\n    before: string;\n    after: string;\n  };\n  ralph: {\n    runId: string;\n    agentsStarted: number;\n    result: JsonValue;\n  };\n  read: {\n    path: string;\n    offset: number;\n    lines: {\n      number: number;\n      text: string;\n    }[];\n    totalLines: number;\n  };\n  send_message: {\n    route: \"steered\" | \"started\";\n    taskId: string;\n  };\n  skill: {\n    name: string;\n    provider: string;\n    resourceBase?: {\n      kind: \"directory\";\n      path: string;\n    } | {\n      kind: \"url\";\n      url: string;\n    } | {\n      kind: \"opaque\";\n      description: string;\n    };\n    content: string;\n  };\n  subagent: {\n    kind: \"background\";\n    taskId: string;\n    subagentId?: string;\n  } | {\n    kind: \"foreground\";\n    runId: string;\n    output: JsonValue[];\n  };\n  subagent_fork: {\n    kind: \"background\";\n    taskId: string;\n    subagentId?: string;\n  } | {\n    kind: \"foreground\";\n    runId: string;\n    output: JsonValue[];\n  };\n  task_kill: {\n    outcome: \"cancellation-requested\" | \"already-finished\";\n    task: {\n      id: string;\n      kind: string;\n      label: string;\n      status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n      detail?: string;\n      startedAt: number;\n      finishedAt?: number;\n    };\n  };\n  task_list: ({\n    id: string;\n    kind: string;\n    label: string;\n    status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n    detail?: string;\n    startedAt: number;\n    finishedAt?: number;\n  })[];\n  task_output: {\n    text: string;\n    task: {\n      id: string;\n      kind: string;\n      label: string;\n      status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n      detail?: string;\n      startedAt: number;\n      finishedAt?: number;\n    };\n  };\n  todo_write: {\n    todos: ({\n      content: string;\n      status: \"pending\" | \"in_progress\" | \"completed\";\n    })[];\n    counts: {\n      pending: number;\n      inProgress: number;\n      completed: number;\n    };\n  };\n  workflow: {\n    runId: string;\n    agentsStarted: number;\n    result: JsonValue;\n  };\n  write: {\n    path: string;\n    operation: \"create\" | \"update\";\n    before: string | null;\n    after: string;\n  };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n  readonly name: \"ToolCallError\";\n  readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n  [K in ToolName]: (args: ToolArgsMap[K]) => Promise<ToolOutputMap[K]>;\n}\n```","tools":[{"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`.","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."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","temporary","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement a normal local, project, or repository Plugin through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"JavaScript body returning a temporary Plugin; evaluated now and saved nowhere."}},"required":["code"]}},{"name":"cordis_unmount","description":"Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins.","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart."}},"required":["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":"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":"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."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"name":"send_message","description":"Send a follow-up message to a background subagent by its subagent id. If it is still working, the message joins its current task; if it has finished, this starts a new task that continues the same subagent conversation. Either way the response arrives through the returned task id — collect it with `task_output`. A failure means the message was NOT delivered.","parameters":{"type":"object","properties":{"subagent_id":{"type":"string","description":"The subagent id returned when the background subagent was started."},"message":{"type":"string","description":"The message to deliver to the subagent."}},"required":["subagent_id","message"]}},{"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 start a continuable background subagent: you receive its stable subagent id and current task id; collect the result with `task_output` and stop it 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 continuable background subagent and return its subagent and task ids; 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 start a continuable background subagent: you receive its stable subagent id and current task id; collect the result with `task_output` and stop it 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 continuable background subagent and return its subagent and task ids; collect with task_output or stop with task_kill."}},"required":["description","prompt"]}},{"name":"task_kill","description":"Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"reason":{"type":"string","description":"Optional short reason, recorded in the log and forwarded to the task."}},"required":["task_id"]}},{"name":"task_list","description":"List your background tasks (running and finished) with their ids, kinds, and statuses.","parameters":{"type":"object","properties":{}}},{"name":"task_output","description":"Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"wait":{"type":"boolean","description":"Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."},"timeout_ms":{"type":"number","description":"Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."}},"required":["task_id"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","additionalProperties":true,"properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","additionalProperties":true,"properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).","additionalProperties":true}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}}
 {"type":"request/context","seq":5,"time":1785460681788,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
 {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
 {"type":"assistant/chunk","seq":7,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}}
diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl
index 39d437b56c..d1a5852ea4 100644
--- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl
+++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl
@@ -3,7 +3,7 @@
 {"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: try a no-op temporary Cordis Plugin named snapshot-marker; use run_code to inspect the live temporary Plugins through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; stop dyn-1; then reply with exactly ADVANCED_HEADLESS_OK."}],"source":{"kind":"user"},"role":"user","id":"50d7fdd8-0423-43a2-b8f4-4aef2829c82e"},"surfaceOp":"append"}
 {"type":"session/title","seq":2,"time":1783957884479,"data":{"title":"Run this advanced flow exactly","messageSeqs":[1],"source":{"kind":"fallback"}}}
 {"type":"step/start","seq":3,"time":1783957884486,"data":{"turn":1,"step":1}}
-{"type":"request/header","seq":4,"time":1783957884486,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack 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.\n\nUse 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.\n\nUse 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.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n  /** 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`. */\n  bash: {\n    /** The bash command to execute. */\n    command: string;\n    /** 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\". */\n    description: string;\n    /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n    timeoutMs?: number;\n    /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n    workdir?: string;\n    /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n    run_in_background?: boolean;\n  } & Record<string, JsonValue>;\n  /** Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n  cordis_inspect: {\n    /** Limit the report to one section. Omit for all sections. */\n    what?: \"services\" | \"plugins\" | \"tools\" | \"temporary\" | \"api\" | \"events\";\n    /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n    name?: string;\n  } & Record<string, JsonValue>;\n  /** Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement a normal local, project, or repository Plugin through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n  cordis_mount: {\n    /** JavaScript body returning a temporary Plugin; evaluated now and saved nowhere. */\n    code: string;\n  } & Record<string, JsonValue>;\n  /** Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins. */\n  cordis_unmount: {\n    /** The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart. */\n    id: string;\n  } & Record<string, JsonValue>;\n  /** Edit an existing UTF-8 text file by replacing literal text. */\n  edit: {\n    /** Path to edit, resolved by the filesystem backend. */\n    file_path: string;\n    /** Literal text to replace. Must match exactly. */\n    old_string: string;\n    /** Literal replacement text. Use an empty string to delete the match. */\n    new_string: string;\n    /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n    replace_all?: boolean;\n  } & Record<string, JsonValue>;\n  /** 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. */\n  ralph: {\n    /** The immutable completion objective for every fresh Ralph round. */\n    objective: string;\n    /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n    maxRounds?: number;\n  } & Record<string, JsonValue>;\n  /** Read a UTF-8 text file and return line-numbered content. */\n  read: {\n    /** Path to read, resolved by the filesystem backend. */\n    file_path: string;\n    /** 1-based first line to return. Defaults to 1. */\n    offset?: number;\n    /** Maximum number of lines to return. Defaults to 2000. */\n    limit?: number;\n  } & Record<string, JsonValue>;\n  /** Send a follow-up message to a background subagent by its subagent id. If it is still working, the message joins its current task; if it has finished, this starts a new task that continues the same subagent conversation. Either way the response arrives through the returned task id — collect it with `task_output`. A failure means the message was NOT delivered. */\n  send_message: {\n    /** The subagent id returned when the background subagent was started. */\n    subagent_id: string;\n    /** The message to deliver to the subagent. */\n    message: string;\n  } & Record<string, JsonValue>;\n  /** 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. */\n  skill: {\n    /** The exact skill name from the available skills list. */\n    name: string;\n  } & Record<string, JsonValue>;\n  /** 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 start a continuable background subagent: you receive its subagent id and a task id; collect the result with `task_output`, stop it with `task_kill`, and send follow-up messages with `send_message`. */\n  subagent: {\n    /** A short (3-5 word) description of the delegated task, for display. */\n    description: string;\n    /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n    prompt: string;\n    /** Run as a continuable background subagent and return its subagent and task ids; collect with task_output, stop with task_kill, follow up with send_message. */\n    run_in_background?: boolean;\n  } & Record<string, JsonValue>;\n  /** 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 start a continuable background subagent: you receive its subagent id and a task id; collect the result with `task_output`, stop it with `task_kill`, and send follow-up messages with `send_message`. */\n  subagent_fork: {\n    /** A short (3-5 word) description of the delegated task, for display. */\n    description: string;\n    /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n    prompt: string;\n    /** Run as a continuable background subagent and return its subagent and task ids; collect with task_output, stop with task_kill, follow up with send_message. */\n    run_in_background?: boolean;\n  } & Record<string, JsonValue>;\n  /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n  task_kill: {\n    /** Task id returned by the tool that started the background work. */\n    task_id: string;\n    /** Optional short reason, recorded in the log and forwarded to the task. */\n    reason?: string;\n  } & Record<string, JsonValue>;\n  /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n  task_list: Record<string, JsonValue>;\n  /** 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. */\n  task_output: {\n    /** Task id returned by the tool that started the background work. */\n    task_id: string;\n    /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n    wait?: boolean;\n    /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n    timeout_ms?: number;\n  } & Record<string, JsonValue>;\n  /** 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). */\n  todo_write: {\n    /** The COMPLETE task list, replacing any previous list. */\n    todos: ({\n      /** What the task is — a short imperative line. */\n      content: string;\n      /** pending (not started) | in_progress (now) | completed (done). */\n      status: \"pending\" | \"in_progress\" | \"completed\";\n    })[];\n  } & Record<string, JsonValue>;\n  /** 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. The 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. Script-body hooks: - `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */\n  workflow: {\n    /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`). */\n    script: string;\n    /** The workflow identity block (plain JSON — never code). */\n    meta: {\n      /** Short kebab-case workflow name. */\n      name: string;\n      /** One-line description of what the workflow does. */\n      description: string;\n      /** Optional guidance on when this workflow applies. */\n      whenToUse?: string;\n      /** Optional phase declarations matched by phase() calls. */\n      phases?: ({\n        /** The phase title phase() calls match by exact string. */\n        title: string;\n        /** Optional one-line description of the phase. */\n        detail?: string;\n        /** Optional provider override this phase is expected to use. */\n        provider?: string;\n        /** Optional model override this phase is expected to use. */\n        model?: string;\n      } & Record<string, JsonValue>)[];\n    } & Record<string, JsonValue>;\n    /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n    args?: Record<string, JsonValue>;\n  } & Record<string, JsonValue>;\n  /** Create or fully replace a UTF-8 text file. */\n  write: {\n    /** Path to write, resolved by the filesystem backend. */\n    file_path: string;\n    /** Full UTF-8 text content to write. */\n    content: string;\n  } & Record<string, JsonValue>;\n}\n\ninterface ToolOutputMap {\n  bash: {\n    kind: \"background\";\n    taskId: string;\n  } | {\n    kind: \"foreground\";\n    exitCode: number | null;\n    signal: string | null;\n    timedOut: boolean;\n    aborted: boolean;\n    timeoutMs: number;\n    stdout: {\n      text: string;\n      truncated: boolean;\n      spillPath?: string;\n    };\n    stderr: {\n      text: string;\n      truncated: boolean;\n      spillPath?: string;\n    };\n    sandbox?: {\n      mode: string;\n      denied: boolean;\n      enforcement?: string;\n      runnerFailed?: boolean;\n    };\n  };\n  cordis_inspect: string;\n  cordis_mount: {\n    id: string;\n    pluginName: string;\n    state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n    provides: string[];\n    waitingFor: string[];\n  };\n  cordis_unmount: {\n    id: string;\n    pluginName: string;\n  };\n  edit: {\n    path: string;\n    before: string;\n    after: string;\n  };\n  ralph: {\n    runId: string;\n    agentsStarted: number;\n    result: JsonValue;\n  };\n  read: {\n    path: string;\n    offset: number;\n    lines: {\n      number: number;\n      text: string;\n    }[];\n    totalLines: number;\n  };\n  send_message: {\n    route: \"steered\" | \"started\";\n    taskId: string;\n  };\n  skill: {\n    name: string;\n    provider: string;\n    resourceBase?: {\n      kind: \"directory\";\n      path: string;\n    } | {\n      kind: \"url\";\n      url: string;\n    } | {\n      kind: \"opaque\";\n      description: string;\n    };\n    content: string;\n  };\n  subagent: {\n    kind: \"background\";\n    taskId: string;\n    subagentId?: string;\n  } | {\n    kind: \"foreground\";\n    runId: string;\n    output: JsonValue[];\n  };\n  subagent_fork: {\n    kind: \"background\";\n    taskId: string;\n    subagentId?: string;\n  } | {\n    kind: \"foreground\";\n    runId: string;\n    output: JsonValue[];\n  };\n  task_kill: {\n    outcome: \"cancellation-requested\" | \"already-finished\";\n    task: {\n      id: string;\n      kind: string;\n      label: string;\n      status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n      detail?: string;\n      startedAt: number;\n      finishedAt?: number;\n    };\n  };\n  task_list: ({\n    id: string;\n    kind: string;\n    label: string;\n    status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n    detail?: string;\n    startedAt: number;\n    finishedAt?: number;\n  })[];\n  task_output: {\n    text: string;\n    task: {\n      id: string;\n      kind: string;\n      label: string;\n      status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n      detail?: string;\n      startedAt: number;\n      finishedAt?: number;\n    };\n  };\n  todo_write: {\n    todos: ({\n      content: string;\n      status: \"pending\" | \"in_progress\" | \"completed\";\n    })[];\n    counts: {\n      pending: number;\n      inProgress: number;\n      completed: number;\n    };\n  };\n  workflow: {\n    runId: string;\n    agentsStarted: number;\n    result: JsonValue;\n  };\n  write: {\n    path: string;\n    operation: \"create\" | \"update\";\n    before: string | null;\n    after: string;\n  };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n  readonly name: \"ToolCallError\";\n  readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n  [K in ToolName]: (args: ToolArgsMap[K]) => Promise<ToolOutputMap[K]>;\n}\n```","tools":[{"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`.","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."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","temporary","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement a normal local, project, or repository Plugin through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"JavaScript body returning a temporary Plugin; evaluated now and saved nowhere."}},"required":["code"]}},{"name":"cordis_unmount","description":"Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins.","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart."}},"required":["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":"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":"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."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"name":"send_message","description":"Send a follow-up message to a background subagent by its subagent id. If it is still working, the message joins its current task; if it has finished, this starts a new task that continues the same subagent conversation. Either way the response arrives through the returned task id — collect it with `task_output`. A failure means the message was NOT delivered.","parameters":{"type":"object","properties":{"subagent_id":{"type":"string","description":"The subagent id returned when the background subagent was started."},"message":{"type":"string","description":"The message to deliver to the subagent."}},"required":["subagent_id","message"]}},{"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 start a continuable background subagent: you receive its subagent id and a task id; collect the result with `task_output`, stop it with `task_kill`, and send follow-up messages with `send_message`.","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 continuable background subagent and return its subagent and task ids; collect with task_output, stop with task_kill, follow up with send_message."}},"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 start a continuable background subagent: you receive its subagent id and a task id; collect the result with `task_output`, stop it with `task_kill`, and send follow-up messages with `send_message`.","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 continuable background subagent and return its subagent and task ids; collect with task_output, stop with task_kill, follow up with send_message."}},"required":["description","prompt"]}},{"name":"task_kill","description":"Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"reason":{"type":"string","description":"Optional short reason, recorded in the log and forwarded to the task."}},"required":["task_id"]}},{"name":"task_list","description":"List your background tasks (running and finished) with their ids, kinds, and statuses.","parameters":{"type":"object","properties":{}}},{"name":"task_output","description":"Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"wait":{"type":"boolean","description":"Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."},"timeout_ms":{"type":"number","description":"Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."}},"required":["task_id"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","additionalProperties":true,"properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","additionalProperties":true,"properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).","additionalProperties":true}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}}
+{"type":"request/header","seq":4,"time":1783957884486,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack 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.\n\nUse 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.\n\nUse 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.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n  /** 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`. */\n  bash: {\n    /** The bash command to execute. */\n    command: string;\n    /** 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\". */\n    description: string;\n    /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n    timeoutMs?: number;\n    /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n    workdir?: string;\n    /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n    run_in_background?: boolean;\n  } & Record<string, JsonValue>;\n  /** Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n  cordis_inspect: {\n    /** Limit the report to one section. Omit for all sections. */\n    what?: \"services\" | \"plugins\" | \"tools\" | \"temporary\" | \"api\" | \"events\";\n    /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n    name?: string;\n  } & Record<string, JsonValue>;\n  /** Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement a normal local, project, or repository Plugin through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n  cordis_mount: {\n    /** JavaScript body returning a temporary Plugin; evaluated now and saved nowhere. */\n    code: string;\n  } & Record<string, JsonValue>;\n  /** Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins. */\n  cordis_unmount: {\n    /** The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart. */\n    id: string;\n  } & Record<string, JsonValue>;\n  /** Edit an existing UTF-8 text file by replacing literal text. */\n  edit: {\n    /** Path to edit, resolved by the filesystem backend. */\n    file_path: string;\n    /** Literal text to replace. Must match exactly. */\n    old_string: string;\n    /** Literal replacement text. Use an empty string to delete the match. */\n    new_string: string;\n    /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n    replace_all?: boolean;\n  } & Record<string, JsonValue>;\n  /** 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. */\n  ralph: {\n    /** The immutable completion objective for every fresh Ralph round. */\n    objective: string;\n    /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n    maxRounds?: number;\n  } & Record<string, JsonValue>;\n  /** Read a UTF-8 text file and return line-numbered content. */\n  read: {\n    /** Path to read, resolved by the filesystem backend. */\n    file_path: string;\n    /** 1-based first line to return. Defaults to 1. */\n    offset?: number;\n    /** Maximum number of lines to return. Defaults to 2000. */\n    limit?: number;\n  } & Record<string, JsonValue>;\n  /** Send a follow-up message to a background subagent by its subagent id. If it is still working, the message joins its current task; if it has finished, this starts a new task that continues the same subagent conversation. Either way the response arrives through the returned task id — collect it with `task_output`. A failure means the message was NOT delivered. */\n  send_message: {\n    /** The subagent id returned when the background subagent was started. */\n    subagent_id: string;\n    /** The message to deliver to the subagent. */\n    message: string;\n  } & Record<string, JsonValue>;\n  /** 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. */\n  skill: {\n    /** The exact skill name from the available skills list. */\n    name: string;\n  } & Record<string, JsonValue>;\n  /** 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 start a continuable background subagent: you receive its stable subagent id and current task id; collect the result with `task_output` and stop it with `task_kill`. */\n  subagent: {\n    /** A short (3-5 word) description of the delegated task, for display. */\n    description: string;\n    /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n    prompt: string;\n    /** Run as a continuable background subagent and return its subagent and task ids; collect with task_output or stop with task_kill. */\n    run_in_background?: boolean;\n  } & Record<string, JsonValue>;\n  /** 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 start a continuable background subagent: you receive its stable subagent id and current task id; collect the result with `task_output` and stop it with `task_kill`. */\n  subagent_fork: {\n    /** A short (3-5 word) description of the delegated task, for display. */\n    description: string;\n    /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n    prompt: string;\n    /** Run as a continuable background subagent and return its subagent and task ids; collect with task_output or stop with task_kill. */\n    run_in_background?: boolean;\n  } & Record<string, JsonValue>;\n  /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n  task_kill: {\n    /** Task id returned by the tool that started the background work. */\n    task_id: string;\n    /** Optional short reason, recorded in the log and forwarded to the task. */\n    reason?: string;\n  } & Record<string, JsonValue>;\n  /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n  task_list: Record<string, JsonValue>;\n  /** 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. */\n  task_output: {\n    /** Task id returned by the tool that started the background work. */\n    task_id: string;\n    /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n    wait?: boolean;\n    /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n    timeout_ms?: number;\n  } & Record<string, JsonValue>;\n  /** 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). */\n  todo_write: {\n    /** The COMPLETE task list, replacing any previous list. */\n    todos: ({\n      /** What the task is — a short imperative line. */\n      content: string;\n      /** pending (not started) | in_progress (now) | completed (done). */\n      status: \"pending\" | \"in_progress\" | \"completed\";\n    })[];\n  } & Record<string, JsonValue>;\n  /** 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. The 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. Script-body hooks: - `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `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. - `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`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: 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. */\n  workflow: {\n    /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`). */\n    script: string;\n    /** The workflow identity block (plain JSON — never code). */\n    meta: {\n      /** Short kebab-case workflow name. */\n      name: string;\n      /** One-line description of what the workflow does. */\n      description: string;\n      /** Optional guidance on when this workflow applies. */\n      whenToUse?: string;\n      /** Optional phase declarations matched by phase() calls. */\n      phases?: ({\n        /** The phase title phase() calls match by exact string. */\n        title: string;\n        /** Optional one-line description of the phase. */\n        detail?: string;\n        /** Optional provider override this phase is expected to use. */\n        provider?: string;\n        /** Optional model override this phase is expected to use. */\n        model?: string;\n      } & Record<string, JsonValue>)[];\n    } & Record<string, JsonValue>;\n    /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n    args?: Record<string, JsonValue>;\n  } & Record<string, JsonValue>;\n  /** Create or fully replace a UTF-8 text file. */\n  write: {\n    /** Path to write, resolved by the filesystem backend. */\n    file_path: string;\n    /** Full UTF-8 text content to write. */\n    content: string;\n  } & Record<string, JsonValue>;\n}\n\ninterface ToolOutputMap {\n  bash: {\n    kind: \"background\";\n    taskId: string;\n  } | {\n    kind: \"foreground\";\n    exitCode: number | null;\n    signal: string | null;\n    timedOut: boolean;\n    aborted: boolean;\n    timeoutMs: number;\n    stdout: {\n      text: string;\n      truncated: boolean;\n      spillPath?: string;\n    };\n    stderr: {\n      text: string;\n      truncated: boolean;\n      spillPath?: string;\n    };\n    sandbox?: {\n      mode: string;\n      denied: boolean;\n      enforcement?: string;\n      runnerFailed?: boolean;\n    };\n  };\n  cordis_inspect: string;\n  cordis_mount: {\n    id: string;\n    pluginName: string;\n    state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n    provides: string[];\n    waitingFor: string[];\n  };\n  cordis_unmount: {\n    id: string;\n    pluginName: string;\n  };\n  edit: {\n    path: string;\n    before: string;\n    after: string;\n  };\n  ralph: {\n    runId: string;\n    agentsStarted: number;\n    result: JsonValue;\n  };\n  read: {\n    path: string;\n    offset: number;\n    lines: {\n      number: number;\n      text: string;\n    }[];\n    totalLines: number;\n  };\n  send_message: {\n    route: \"steered\" | \"started\";\n    taskId: string;\n  };\n  skill: {\n    name: string;\n    provider: string;\n    resourceBase?: {\n      kind: \"directory\";\n      path: string;\n    } | {\n      kind: \"url\";\n      url: string;\n    } | {\n      kind: \"opaque\";\n      description: string;\n    };\n    content: string;\n  };\n  subagent: {\n    kind: \"background\";\n    taskId: string;\n    subagentId?: string;\n  } | {\n    kind: \"foreground\";\n    runId: string;\n    output: JsonValue[];\n  };\n  subagent_fork: {\n    kind: \"background\";\n    taskId: string;\n    subagentId?: string;\n  } | {\n    kind: \"foreground\";\n    runId: string;\n    output: JsonValue[];\n  };\n  task_kill: {\n    outcome: \"cancellation-requested\" | \"already-finished\";\n    task: {\n      id: string;\n      kind: string;\n      label: string;\n      status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n      detail?: string;\n      startedAt: number;\n      finishedAt?: number;\n    };\n  };\n  task_list: ({\n    id: string;\n    kind: string;\n    label: string;\n    status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n    detail?: string;\n    startedAt: number;\n    finishedAt?: number;\n  })[];\n  task_output: {\n    text: string;\n    task: {\n      id: string;\n      kind: string;\n      label: string;\n      status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n      detail?: string;\n      startedAt: number;\n      finishedAt?: number;\n    };\n  };\n  todo_write: {\n    todos: ({\n      content: string;\n      status: \"pending\" | \"in_progress\" | \"completed\";\n    })[];\n    counts: {\n      pending: number;\n      inProgress: number;\n      completed: number;\n    };\n  };\n  workflow: {\n    runId: string;\n    agentsStarted: number;\n    result: JsonValue;\n  };\n  write: {\n    path: string;\n    operation: \"create\" | \"update\";\n    before: string | null;\n    after: string;\n  };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n  readonly name: \"ToolCallError\";\n  readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n  [K in ToolName]: (args: ToolArgsMap[K]) => Promise<ToolOutputMap[K]>;\n}\n```","tools":[{"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`.","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."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live Cordis runtime in the current DSH process. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (all live plugin fibers with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `temporary` (only temporary Plugins created by cordis_mount: id, name, state, provided services, awaited services, and lifetime), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Temporary Plugins exist only in memory, remain active across later turns, and disappear after cordis_unmount, toolset unload, or DSH restart; they are not restored automatically. The `temporary` section is a subset of `plugins`. Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","temporary","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement a normal local, project, or repository Plugin through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"JavaScript body returning a temporary Plugin; evaluated now and saved nowhere."}},"required":["code"]}},{"name":"cordis_unmount","description":"Unmount a current-process temporary Plugin created by cordis_mount. Waits for its tools, listeners, services, timers, and other owned effects to clean up completely. Only dyn-N temporary ids are accepted; this cannot remove Loader, configured, or installed Plugins.","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The temporary Plugin id returned by cordis_mount (for example \"dyn-1\"); valid only in this process and invalid after unmount or restart."}},"required":["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":"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":"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."},"description":{"type":"string","description":"Clear, concise description of what this program does in active voice, 5-10 words (shown in the UI). Examples: \"Count TODO markers across packages\"; \"Read failing test and its fixture\"; \"Rename config key in every cordis.yml\"."}},"required":["code","description"]}},{"name":"send_message","description":"Send a follow-up message to a background subagent by its subagent id. If it is still working, the message joins its current task; if it has finished, this starts a new task that continues the same subagent conversation. Either way the response arrives through the returned task id — collect it with `task_output`. A failure means the message was NOT delivered.","parameters":{"type":"object","properties":{"subagent_id":{"type":"string","description":"The subagent id returned when the background subagent was started."},"message":{"type":"string","description":"The message to deliver to the subagent."}},"required":["subagent_id","message"]}},{"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 start a continuable background subagent: you receive its stable subagent id and current task id; collect the result with `task_output` and stop it 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 continuable background subagent and return its subagent and task ids; 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 start a continuable background subagent: you receive its stable subagent id and current task id; collect the result with `task_output` and stop it 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 continuable background subagent and return its subagent and task ids; collect with task_output or stop with task_kill."}},"required":["description","prompt"]}},{"name":"task_kill","description":"Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"reason":{"type":"string","description":"Optional short reason, recorded in the log and forwarded to the task."}},"required":["task_id"]}},{"name":"task_list","description":"List your background tasks (running and finished) with their ids, kinds, and statuses.","parameters":{"type":"object","properties":{}}},{"name":"task_output","description":"Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"wait":{"type":"boolean","description":"Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."},"timeout_ms":{"type":"number","description":"Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."}},"required":["task_id"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","additionalProperties":true,"properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","additionalProperties":true,"properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).","additionalProperties":true}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}}
 {"type":"request/context","seq":5,"time":1785460681498,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
 {"type":"assistant/chunk","seq":6,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
 {"type":"assistant/chunk","seq":7,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}
diff --git a/examples/headless-agent/tests/snapshots/pty-tools/session.jsonl b/examples/headless-agent/tests/snapshots/pty-tools/session.jsonl
index 076ee192f6..28a652be89 100644
--- a/examples/headless-agent/tests/snapshots/pty-tools/session.jsonl
+++ b/examples/headless-agent/tests/snapshots/pty-tools/session.jsonl
@@ -4,7 +4,7 @@
 {"type":"session/title","seq":2,"time":0,"data":{"title":"Exercise the six PTY tools","messageSeqs":[1],"source":{"kind":"fallback"}}}
 {"type":"user/message","seq":3,"time":1785464685153,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"da0842e3-2231-4abf-a85f-a16acfb0b305"},"surfaceOp":"append"}
 {"type":"step/start","seq":4,"time":1785464685153,"data":{"turn":1,"step":1}}
-{"type":"request/header","seq":5,"time":1785464685153,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse a terminal session only when work needs persistent terminal state or interactive stdin; prefer bash/read/write/edit for bounded one-shot operations. Track every terminal session id and close sessions that no longer matter. An inferred_idle or timeout result does not prove the foreground command exited.\n\nTrack 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.\n\nUse 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.\n\nUse 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.","tools":[{"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`.","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."}},"required":["command","description"]}},{"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":"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":"send_message","description":"Send a follow-up message to a background subagent by its subagent id. If it is still working, the message joins its current task; if it has finished, this starts a new task that continues the same subagent conversation. Either way the response arrives through the returned task id — collect it with `task_output`. A failure means the message was NOT delivered.","parameters":{"type":"object","properties":{"subagent_id":{"type":"string","description":"The subagent id returned when the background subagent was started."},"message":{"type":"string","description":"The message to deliver to the subagent."}},"required":["subagent_id","message"]}},{"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 start a continuable background subagent: you receive its subagent id and a task id; collect the result with `task_output`, stop it with `task_kill`, and send follow-up messages with `send_message`.","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 continuable background subagent and return its subagent and task ids; collect with task_output, stop with task_kill, follow up with send_message."}},"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 start a continuable background subagent: you receive its subagent id and a task id; collect the result with `task_output`, stop it with `task_kill`, and send follow-up messages with `send_message`.","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 continuable background subagent and return its subagent and task ids; collect with task_output, stop with task_kill, follow up with send_message."}},"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":"terminal_close","description":"Close one persistent terminal and wait until its captured owned process tree is gone.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."}},"required":["sessionId"]}},{"name":"terminal_list","description":"List persistent terminal sessions owned by the current agent.","parameters":{"type":"object","properties":{}}},{"name":"terminal_open","description":"Create a persistent, owner-isolated terminal session from a registered backend type. Use this for shell or REPL state that must survive across tool calls.","parameters":{"type":"object","properties":{"type":{"type":"string","description":"Registered terminal backend type, usually \"shell\"."},"name":{"type":"string","description":"Optional owner-local display name such as \"main\" or \"gdb\"."},"cwd":{"type":"string","description":"Initial working directory. Defaults to the deployment workspace root."}},"required":["type"]}},{"name":"terminal_read","description":"Read a bounded page of retained output from a persistent terminal without sending input.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."},"offset":{"type":"number","description":"Newest-relative line offset (default 0)."},"count":{"type":"number","description":"Requested line count (default 500; backend caps apply)."}},"required":["sessionId"]}},{"name":"terminal_send","description":"Send text to a persistent terminal. By default Enter is submitted and the call waits for a prompt, stdin wait, output silence, timeout, or session exit. Background mode returns a task id for task_output/task_kill.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id returned by terminal_open or terminal_list."},"text":{"type":"string","description":"UTF-8 text to write to the terminal."},"submit":{"type":"boolean","description":"Submit Enter after text (default true). Set false for control characters or incomplete REPL input."},"run_in_background":{"type":"boolean","description":"Return a task id immediately; collect with task_output or stop with task_kill."}},"required":["sessionId","text"]}},{"name":"terminal_signal","description":"Send an allowed signal to the current foreground process group of a persistent terminal.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."},"signal":{"type":"string","description":"Signal to deliver. Shell-targeted SIGKILL is rejected; use terminal_close.","enum":["SIGINT","SIGTERM","SIGKILL","SIGTSTP","SIGHUP"]}},"required":["sessionId","signal"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","additionalProperties":true,"properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","additionalProperties":true,"properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).","additionalProperties":true}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}}
+{"type":"request/header","seq":5,"time":1785464685153,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse 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.\n\nUse 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.\n\nUse 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.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse a terminal session only when work needs persistent terminal state or interactive stdin; prefer bash/read/write/edit for bounded one-shot operations. Track every terminal session id and close sessions that no longer matter. An inferred_idle or timeout result does not prove the foreground command exited.\n\nTrack 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.\n\nUse 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.\n\nUse 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.","tools":[{"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`.","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."}},"required":["command","description"]}},{"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":"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":"send_message","description":"Send a follow-up message to a background subagent by its subagent id. If it is still working, the message joins its current task; if it has finished, this starts a new task that continues the same subagent conversation. Either way the response arrives through the returned task id — collect it with `task_output`. A failure means the message was NOT delivered.","parameters":{"type":"object","properties":{"subagent_id":{"type":"string","description":"The subagent id returned when the background subagent was started."},"message":{"type":"string","description":"The message to deliver to the subagent."}},"required":["subagent_id","message"]}},{"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 start a continuable background subagent: you receive its stable subagent id and current task id; collect the result with `task_output` and stop it 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 continuable background subagent and return its subagent and task ids; 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 start a continuable background subagent: you receive its stable subagent id and current task id; collect the result with `task_output` and stop it 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 continuable background subagent and return its subagent and task ids; 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":"terminal_close","description":"Close one persistent terminal and wait until its captured owned process tree is gone.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."}},"required":["sessionId"]}},{"name":"terminal_list","description":"List persistent terminal sessions owned by the current agent.","parameters":{"type":"object","properties":{}}},{"name":"terminal_open","description":"Create a persistent, owner-isolated terminal session from a registered backend type. Use this for shell or REPL state that must survive across tool calls.","parameters":{"type":"object","properties":{"type":{"type":"string","description":"Registered terminal backend type, usually \"shell\"."},"name":{"type":"string","description":"Optional owner-local display name such as \"main\" or \"gdb\"."},"cwd":{"type":"string","description":"Initial working directory. Defaults to the deployment workspace root."}},"required":["type"]}},{"name":"terminal_read","description":"Read a bounded page of retained output from a persistent terminal without sending input.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."},"offset":{"type":"number","description":"Newest-relative line offset (default 0)."},"count":{"type":"number","description":"Requested line count (default 500; backend caps apply)."}},"required":["sessionId"]}},{"name":"terminal_send","description":"Send text to a persistent terminal. By default Enter is submitted and the call waits for a prompt, stdin wait, output silence, timeout, or session exit. Background mode returns a task id for task_output/task_kill.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id returned by terminal_open or terminal_list."},"text":{"type":"string","description":"UTF-8 text to write to the terminal."},"submit":{"type":"boolean","description":"Submit Enter after text (default true). Set false for control characters or incomplete REPL input."},"run_in_background":{"type":"boolean","description":"Return a task id immediately; collect with task_output or stop with task_kill."}},"required":["sessionId","text"]}},{"name":"terminal_signal","description":"Send an allowed signal to the current foreground process group of a persistent terminal.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."},"signal":{"type":"string","description":"Signal to deliver. Shell-targeted SIGKILL is rejected; use terminal_close.","enum":["SIGINT","SIGTERM","SIGKILL","SIGTSTP","SIGHUP"]}},"required":["sessionId","signal"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","additionalProperties":true,"properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","additionalProperties":true,"properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).","additionalProperties":true}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}}
 {"type":"request/context","seq":6,"time":1785487564325,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
 {"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
 {"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"pty-spawn","name":"terminal_open","argumentsDelta":"{\"type\":\"shell\",\"name\":\"main\"}"}}}
diff --git a/packages/core/agent-loop/src/agent.ts b/packages/core/agent-loop/src/agent.ts
index b41dd69594..90354f0cc2 100644
--- a/packages/core/agent-loop/src/agent.ts
+++ b/packages/core/agent-loop/src/agent.ts
@@ -71,6 +71,7 @@ function createSteeringDelivery(): SteeringDelivery {
   return {
     receipt: { outcome: promise },
     settle(outcome): void {
+      /* v8 ignore next -- each ownership transfer removes the delivery before another settlement path can reach it. */
       if (settled) return
       settled = true
       resolve(outcome)
@@ -544,6 +545,7 @@ export class ReactLoopAgent implements Agent {
               this.drainOutbox(turn)
               break steps
             }
+            /* v8 ignore next -- step() folded the same steering predicate into continueTurn immediately before returning. */
             if (outcome.continueTurn || this.outbox.some(item => item.steering)) continue
             break
           case 'request-failed': {
diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts
index 725e3db36a..15bfa7e0fc 100644
--- a/packages/core/agent-loop/tests/loop.spec.ts
+++ b/packages/core/agent-loop/tests/loop.spec.ts
@@ -470,7 +470,10 @@ describe('agent loop', () => {
       parameters: {},
       async execute() {
         // steer while the turn is running (during tool execution)
-        agent.steer(createUserMessage({ content: [{ type: 'text', text: 'change of plans' }], source: { kind: 'user' } }))
+        agent.send(
+          createUserMessage({ content: [{ type: 'text', text: 'change of plans' }], source: { kind: 'user' } }),
+          { target: 'next-step', wakeup: true },
+        )
         return [{ type: 'text', text: 'tool done' }]
       },
     }))
@@ -544,6 +547,120 @@ describe('agent loop', () => {
     expect(JSON.stringify(adapter.requests[0]?.messages)).toContain('pending steering')
   })
 
+  it('rejects failed steering commits while preserving later context', async () => {
+    const adapter = new MockAdapter([textResponse('recovered')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('failed-steering-commit'), { provider: 'mock', model: 'mock' })
+    let receipt: ReturnType<Agent['steer']> | undefined
+    ctx.on('agent/step', (subject) => {
+      if (subject !== agent || receipt !== undefined) return
+      receipt = subject.steer(createUserMessage({
+        content: [{ type: 'text', text: 'rejected steering' }],
+        source: { kind: 'user' },
+      }))
+      subject.inject(createUserMessage({
+        content: [{ type: 'text', text: 'preserved context' }],
+        source: { kind: 'plugin', plugin: 'loop-test' },
+      }))
+    })
+    let rejected = false
+    ctx.on('internal/dispatch', (_mode, name, args) => {
+      if (name !== 'session/event') return
+      const event = args[1] as { type: string }
+      if (event.type === 'steering/message' && !rejected) {
+        rejected = true
+        throw new Error('reject steering commit')
+      }
+    })
+
+    send(agent, 'first prompt')
+    await waitForIdle(ctx, agent)
+
+    expect(adapter.requests).toHaveLength(0)
+    if (receipt === undefined) throw new Error('agent/step did not submit steering')
+    expect(await receipt.outcome).toEqual({ status: 'rejected' })
+    expect(agent.session.events.some(event => event.type === 'steering/message')).toBe(false)
+
+    send(agent, 'recover')
+    await waitForIdle(ctx, agent)
+
+    expect(adapter.requests).toHaveLength(1)
+    const request = JSON.stringify(adapter.requests[0]?.messages)
+    expect(request).toContain('preserved context')
+    expect(request).not.toContain('rejected steering')
+  })
+
+  it('rejects committed steering when the step boundary fails', async () => {
+    const adapter = new MockAdapter([])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('failed-step-boundary'), { provider: 'mock', model: 'mock' })
+    let receipt: ReturnType<Agent['steer']> | undefined
+    ctx.on('agent/step', (subject) => {
+      if (subject !== agent || receipt !== undefined) return
+      receipt = subject.steer(createUserMessage({
+        content: [{ type: 'text', text: 'committed steering' }],
+        source: { kind: 'user' },
+      }))
+    })
+    ctx.on('internal/dispatch', (_mode, name, args) => {
+      if (name !== 'session/event') return
+      const event = args[1] as { type: string }
+      if (event.type === 'step/start') throw new Error('reject step boundary')
+    })
+
+    send(agent, 'prompt')
+    await waitForIdle(ctx, agent)
+
+    if (receipt === undefined) throw new Error('agent/step did not submit steering')
+    expect(await receipt.outcome).toEqual({ status: 'rejected' })
+    expect(adapter.requests).toHaveLength(0)
+    expect(agent.session.events.some(event => event.type === 'steering/message')).toBe(true)
+    expect(agent.session.events.some(event => event.type === 'step/start')).toBe(false)
+  })
+
+  it('retries context and steering after a context commit fails', async () => {
+    const adapter = new MockAdapter([textResponse('recovered')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('failed-context-commit'), { provider: 'mock', model: 'mock' })
+    let receipt: ReturnType<Agent['steer']> | undefined
+    ctx.on('agent/step', (subject) => {
+      if (subject !== agent || receipt !== undefined) return
+      subject.inject(createUserMessage({
+        content: [{ type: 'text', text: 'preserved context' }],
+        source: { kind: 'plugin', plugin: 'loop-test' },
+      }))
+      receipt = subject.steer(createUserMessage({
+        content: [{ type: 'text', text: 'preserved steering' }],
+        source: { kind: 'user' },
+      }))
+    })
+    let rejected = false
+    ctx.on('internal/dispatch', (_mode, name, args) => {
+      if (name !== 'session/event') return
+      const event = args[1] as { type: string; data?: { source?: { kind: string } } }
+      if (event.type === 'user/message' && event.data?.source?.kind === 'plugin' && !rejected) {
+        rejected = true
+        throw new Error('reject context commit')
+      }
+    })
+
+    send(agent, 'first prompt')
+    await waitForIdle(ctx, agent)
+
+    expect(adapter.requests).toHaveLength(0)
+    expect(agent.session.events.some(event => event.type === 'steering/message')).toBe(false)
+
+    send(agent, 'recover')
+    await waitForIdle(ctx, agent)
+
+    if (receipt === undefined) throw new Error('agent/step did not submit steering')
+    expect(await receipt.outcome).toEqual({ status: 'admitted', turn: 2, step: 1 })
+    expect(adapter.requests).toHaveLength(1)
+    const request = JSON.stringify(adapter.requests[0]?.messages)
+    expect(request).toContain('preserved context')
+    expect(request).toContain('preserved steering')
+  })
+
   it('inject() while idle appends context without opening a turn', async () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
@@ -722,12 +839,22 @@ describe('agent loop', () => {
     const ctx = await harness(adapter)
     const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
     let receipt: ReturnType<Agent['steer']> | undefined
+    let contextInjected = false
+    ctx.on('session/event', (session, event) => {
+      if (session !== agent.session || event.type !== 'step/end' || contextInjected) return
+      contextInjected = true
+      agent.inject(createUserMessage({
+        content: [{ type: 'text', text: 'final context' }],
+        source: { kind: 'plugin', plugin: 'finalize' },
+      }))
+    })
     ctx.tools.register(defineContentToolFixture({
       name: 'finalize',
       description: '',
       parameters: {},
       async execute(_args, exec) {
-        // Steering lands while the concluding tool is still executing.
+        // Steering lands while the concluding tool is still executing; the
+        // step/end listener adds ordinary context after the normal result drain.
         receipt = agent.steer(createUserMessage({ content: [{ type: 'text', text: 'late steering' }], source: { kind: 'user' } }))
         exec.concludeTurn()
         return [{ type: 'text', text: 'final' }]
@@ -744,6 +871,9 @@ describe('agent loop', () => {
     if (receipt === undefined) throw new Error('concluding tool did not submit steering')
     expect(await receipt.outcome).toEqual({ status: 'rejected' })
     expect(events).not.toContain('steering/message')
+    expect(agent.session.events.some(event => event.type === 'user/message'
+      && event.data.source.kind === 'plugin'
+      && event.data.content.some(block => block.type === 'text' && block.text === 'final context'))).toBe(true)
 
     send(agent, 'follow up')
     await waitForIdle(ctx, agent)
@@ -752,6 +882,7 @@ describe('agent loop', () => {
       .flatMap(message => message.content)
       .filter(block => block.type === 'text')
       .map(block => block.text)
+    expect(texts).toContain('final context')
     expect(texts).not.toContain('late steering')
   })
 
diff --git a/packages/core/agent/README.i18n.yaml b/packages/core/agent/README.i18n.yaml
index e94f507b99..78473df4a7 100644
--- a/packages/core/agent/README.i18n.yaml
+++ b/packages/core/agent/README.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/core/agent/README.md
-README.md: 8799bc3664b2137b386b752f905e1414fb770cb9
-README.zh.md: 851c174ba80bebbab8ee1255cb04be4bcec7eabd
+README.md: 8a6028352127c4638c0b5e0e3ee85964d1d7d734
+README.zh.md: ffa71ea987ab355ff2f30b6164376199cd5d0170
diff --git a/packages/goal/goal-session/tests/goal-session.spec.ts b/packages/goal/goal-session/tests/goal-session.spec.ts
index 073cb5002f..5a3f0bdca2 100644
--- a/packages/goal/goal-session/tests/goal-session.spec.ts
+++ b/packages/goal/goal-session/tests/goal-session.spec.ts
@@ -9,7 +9,7 @@ import type { GoalView } from '@deepseek-ai/dsh-goal'
 import { createUserMessage, LlmAdapter, LlmError  } from '@deepseek-ai/dsh-llm'
 import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
 import { SessionId } from '@deepseek-ai/dsh-session'
-import type { SessionEvent, TurnEndReason } from '@deepseek-ai/dsh-session'
+import type { TurnEndReason } from '@deepseek-ai/dsh-session'
 import * as goalSession from '../src/index.ts'
 
 declare module '@deepseek-ai/dsh-session' {
@@ -787,35 +787,6 @@ describe('same-session goal driving', () => {
     expect(test.adapter.requests).toHaveLength(1)
   })
 
-  it('yields to a round whose turn/end never committed instead of misreading it as settled', async () => {
-    const test = await harness([textResponse('round ran')])
-    // A persistent pre-commit turn/end rejection reaches idle with the
-    // attempt's turn open and no terminal reason. The driver must yield
-    // instead of clearing the reservation or scheduling another round.
-    let roundTurn: number | undefined
-    test.ctx.on('internal/dispatch', (_mode, name, args) => {
-      if (name !== 'session/event') return
-      const event = args[1] as SessionEvent
-      if (event.type === 'turn/start' && event.data.trigger.kind === 'message'
-        && event.data.trigger.source.kind === 'goal') {
-        roundTurn = event.data.turn
-      }
-      if (event.type === 'turn/end' && event.data.turn === roundTurn) {
-        throw new Error('turn close permanently rejected')
-      }
-    })
-    test.ctx.goals.create(test.agent, { objective: 'survive a lost turn end' })
-    await waitForRequests(test.adapter, 1)
-    await test.agent.whenIdle()
-    await new Promise((resolve) => { setImmediate(resolve) })
-
-    expect(test.adapter.requests).toHaveLength(1)
-    expect(test.ctx.goals.get(test.agent)).toMatchObject({
-      phase: 'active',
-      activation: 'armed',
-    })
-  })
-
   it('cancels an accepted queued round and awaits its driver task during teardown', async () => {
     const test = await harness([])
     let unloading: Promise<void> | undefined
diff --git a/packages/subagent/subagent-fork/README.i18n.yaml b/packages/subagent/subagent-fork/README.i18n.yaml
index 14b40beb88..317762e160 100644
--- a/packages/subagent/subagent-fork/README.i18n.yaml
+++ b/packages/subagent/subagent-fork/README.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/subagent/subagent-fork/README.md
-README.md: b448dc309bff07c744443530a648c7c30e4d20d9
-README.zh.md: 3e14206d5637fded9edb4e173608c55e3341f8fc
+README.md: 55475aee7841e91960de79887dfe9bf37afdf9da
+README.zh.md: 3eec8cb51a47243a1f06416a3f8f99ae8df8e734
diff --git a/packages/subagent/subagent-fork/README.zh.md b/packages/subagent/subagent-fork/README.zh.md
index 3e14206d56..3eec8cb51a 100644
--- a/packages/subagent/subagent-fork/README.zh.md
+++ b/packages/subagent/subagent-fork/README.zh.md
@@ -57,5 +57,4 @@ fork 会把保留的已完成历史复制到独立的子 agent 请求中；随
 
 ## 已知限制与暂缓事项
 
-- **运行不公开 `sendMessage`/`resume`**：进程内运行不具备这些可选运行时能力。
 - **初始内容是一次性快照**：子 agent 只能看到 fork 时父 agent 已完成的轮次，看不到父 agent 此后记录的任何内容；不会实时共享上下文。
diff --git a/packages/subagent/subagent-spawn/README.i18n.yaml b/packages/subagent/subagent-spawn/README.i18n.yaml
index 970a148213..00eb8d457f 100644
--- a/packages/subagent/subagent-spawn/README.i18n.yaml
+++ b/packages/subagent/subagent-spawn/README.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/subagent/subagent-spawn/README.md
-README.md: 868f829edbcfe2eb4d66ccd0ff9988924c70298b
-README.zh.md: 99cfdf0e633345d1152c59cbe5ce7a029eb6ec9d
+README.md: 811f19e6e68362bd14e75d0a9059ee61fda3f015
+README.zh.md: 2b189f77c4ff63ca026f472187a55c68def18ea1
diff --git a/packages/subagent/subagent-spawn/README.zh.md b/packages/subagent/subagent-spawn/README.zh.md
index 99cfdf0e63..2b189f77c4 100644
--- a/packages/subagent/subagent-spawn/README.zh.md
+++ b/packages/subagent/subagent-spawn/README.zh.md
@@ -52,5 +52,4 @@ spawn 声明 `{ outputSchema: true, depthLimit: true, toolFilter: true, persona:
 
 ## 已知限制与暂缓事项
 
-- **运行不公开 `sendMessage`/`resume`**：进程内运行不具备这些可选运行时能力。
 - **全新表示不含父 agent transcript（文本记录）**：子 agent 会继承 cwd、谱系、模型及显式配置的 persona/工具限制，但不继承父 agent 的任何对话；需要已完成轮次上下文时，请使用 fork 提供方。