@enderfga/claw-orchestrator 7.6.0 → 7.6.2

package/skills/references/multi-engine.md

@@ -19,7 +19,7 @@ SessionManager
 ├── engine: 'cursor'    → PersistentCursorSession (legacy)
 │   └── Wraps: cursor-agent -p --trust --output-format stream-json (per-message spawning)
 ├── engine: 'opencode'  → PersistentOpencodeSession
-│   └── Wraps: opencode run --format json (per-message spawning)
+│   └── Wraps: opencode run --format json, message on stdin (per-message spawning)
 └── engine: 'custom'    → PersistentCustomSession
     └── Wraps: any CLI via user-provided CustomEngineConfig
 ```
@@ -28,7 +28,7 @@ SessionManager
 
 ### Claude Code (`engine: 'claude'`)
 
-Default engine. Long-running subprocess with streaming JSON I/O. Tested with Claude Code CLI **2.1.284**.
+Default engine. Long-running subprocess with streaming JSON I/O. Tested with Claude Code CLI **2.1.289**.
 
 - Persistent multi-turn conversations
 - Real-time streaming (text, tool_use, tool_result, system events)
@@ -62,7 +62,7 @@ await manager.startSession({
 
 ### OpenAI Codex (`engine: 'codex'`)
 
-Wraps the `codex exec` subcommand. Each `send()` spawns a new process. Tested with `codex` CLI **0.159.0**.
+Wraps the `codex exec` subcommand. Each `send()` spawns a new process. Tested with `codex` CLI **0.160.0**.
 
 - Non-interactive execution via `codex exec --sandbox workspace-write --skip-git-repo-check --json`
 - Real `usage` from the `turn.completed` JSON event (input, output, cached, reasoning tokens). **These are cumulative over the thread, not per turn**, so they replace the session totals rather than being added to them; subtracting consecutive values gives one turn's prompt
@@ -79,8 +79,10 @@ Wraps the `codex exec` subcommand. Each `send()` spawns a new process. Tested wi
 - One-shot execution per message (no persistent subprocess between sends)
 - Captures the real Codex thread ID and persists it, so later sends and process-level session resume use `codex exec resume <thread_id>`
 - Working directory passed via `-C` on the first turn
-- Default model: `gpt-5.5`
+- Model: with no `model`, codex runs its own default — the `model` in `~/.codex/config.toml` if set. Cost is then priced as the model codex reports it ran (the rollout's `turn_context`; `thread/start` on `codex-app`), and as `gpt-5.5` only when that cannot be read
 - Requires `codex` CLI >= 0.119 (for `exec resume`): `npm install -g @openai/codex`
+- The prompt is sent on stdin (`codex exec … -`), never on the command line.
+- **Windows:** the npm `.cmd` shim launches through `src/engine-spawn.ts` (cross-spawn), which escapes the remaining arguments for `cmd.exe`. Because the prompt is on stdin it arrives unchanged, newlines and quotes included. A timed-out turn ends the whole process tree (`taskkill /T /F`), not only `cmd.exe`.
 - **Does not support `/goal`** — for that, use `engine: 'codex-app'` below
 
 ```typescript
@@ -126,7 +128,7 @@ await manager.startSession({
 
 Wraps Google's **Antigravity CLI** (`agy`) — the successor to Gemini CLI (consumer
 Gemini CLI tiers stopped serving 2026-06-18). Each `send()` spawns a new process
-in print mode. Tested with `agy` **1.2.13**.
+in print mode. Tested with `agy` **1.2.17**.
 
 - One-shot execution per message (no persistent subprocess)
 - **Structured output and real usage** — `--output-format stream-json` emits an
@@ -211,7 +213,7 @@ await manager.startSession({
 ### Grok Build (`engine: 'grok'`)
 
 Wraps xAI's **Grok Build** CLI. Each `send()` spawns `grok -p <msg> --output-format json`, which
-prints a single JSON object and exits. Tested with `grok` **1.0.44**.
+prints a single JSON object and exits. Tested with `grok` **1.0.46**.
 
 - **Cost comes from the engine, not from the price table.** The result object carries
   `total_cost_usd`, and the wrapper writes it straight into the session's spend, so the run ledger
@@ -344,7 +346,7 @@ Wraps the [sst/opencode](https://github.com/sst/opencode) CLI with `run --format
   - if the `clawo-readonly` agent fails to load, the turn is refused rather than run with write access
   - to test a change to this config, use adversarial prompts that include asking the agent to delegate; `opencode agent list` shows compiled rules that look the same for a safe and an unsafe agent
 - Requires opencode installed: `brew install sst/tap/opencode` or `npm install -g opencode-ai`. Auth via `opencode auth login` **or** any provider env var (`ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, `GEMINI_API_KEY`, etc.) — opencode picks up either path
-- Binary: `opencode` (set `OPENCODE_BIN` env var to override)
+- Binary: `opencode` (set `OPENCODE_BIN` env var to override). The message is sent on stdin, never on the command line. **Windows:** the npm `.cmd` shim launches through `src/engine-spawn.ts` (cross-spawn), as for codex above.
 
 ```typescript
 await manager.startSession({

package/skills/references/tools.md

@@ -351,16 +351,16 @@ Run one task across N engine/model agents **in parallel** and collect their answ
 
 ### `fanout_start`
 
-| Parameter                            | Type    | Required | Description                                                                            |
-| ------------------------------------ | ------- | -------- | -------------------------------------------------------------------------------------- |
-| `task`                               | string  | yes      | Shared task sent to every agent, optionally after its `persona`.                       |
-| `projectDir`                         | string  | yes      | Working directory all agents run in.                                                   |
+| Parameter                            | Type    | Required | Description                                                                                               |
+| ------------------------------------ | ------- | -------- | --------------------------------------------------------------------------------------------------------- |
+| `task`                               | string  | yes      | Shared task sent to every agent, optionally after its `persona`.                                          |
+| `projectDir`                         | string  | yes      | Working directory all agents run in.                                                                      |
 | `agents`                             | array   | yes      | Specs: `{ name, engine?, model?, effort?, prompt?, persona?, baseUrl?, permissionMode?, customEngine? }`. |
-| `synthesize`                         | boolean |          | Run a final synthesis pass over the successful results (needs ≥2).                     |
-| `synthesisModel` / `synthesisEngine` | string  |          | Model/engine for the synthesis pass (default engine `claude`).                         |
-| `agentTimeoutMs`                     | number  |          | Per-agent timeout (default 600000).                                                    |
-| `maxTurnsPerAgent`                   | number  |          | Max agent loop turns (default 30).                                                     |
-| `maxBudgetUsd`                       | number  |          | Per-agent spend cap.                                                                   |
+| `synthesize`                         | boolean |          | Run a final synthesis pass over the successful results (needs ≥2).                                        |
+| `synthesisModel` / `synthesisEngine` | string  |          | Model/engine for the synthesis pass (default engine `claude`).                                            |
+| `agentTimeoutMs`                     | number  |          | Per-agent timeout (default 600000).                                                                       |
+| `maxTurnsPerAgent`                   | number  |          | Max agent loop turns (default 30).                                                                        |
+| `maxBudgetUsd`                       | number  |          | Per-agent spend cap.                                                                                      |
 
 Runs in the background; returns `{ ok, id, status, ... }`. Poll with `fanout_status`.
 Each agent's optional `effort` accepts `low`, `medium`, `high`, `xhigh`, `max`,
@@ -578,25 +578,25 @@ Three-agent autonomous iteration loop (Planner / Coder / Reviewer) over a git wo
 
 Start a chat-mode autoloop. Planner starts immediately; Coder + Reviewer start only after the Planner receives plan approval and emits `spawn_subagents`.
 
-| Parameter                  | Type       | Required | Description                                                                                      |
-| -------------------------- | ---------- | -------- | ------------------------------------------------------------------------------------------------ |
-| `run_id`                   | string     | yes      | Stable run identifier                                                                            |
-| `workspace`                | string     | yes      | Git workspace path                                                                               |
-| `planner_engine`           | EngineType |          | Planner engine (default `claude`)                                                                |
-| `planner_model`            | string     |          | Planner model (Claude default `opus`; other engines use their own default when omitted)          |
+| Parameter                  | Type        | Required | Description                                                                                      |
+| -------------------------- | ----------- | -------- | ------------------------------------------------------------------------------------------------ |
+| `run_id`                   | string      | yes      | Stable run identifier                                                                            |
+| `workspace`                | string      | yes      | Git workspace path                                                                               |
+| `planner_engine`           | EngineType  |          | Planner engine (default `claude`)                                                                |
+| `planner_model`            | string      |          | Planner model (Claude default `opus`; other engines use their own default when omitted)          |
 | `planner_effort`           | EffortLevel |          | Fixed Planner reasoning effort; omission keeps the session default                               |
-| `planner_custom_engine`    | object     |          | Trusted `CustomEngineConfig` when Planner engine is `custom`. **Local callers only** — see below |
-| `coder_engine`             | EngineType |          | Default Coder engine (default `claude`)                                                          |
-| `coder_model`              | string     |          | Default Coder model (Claude default `sonnet`)                                                    |
+| `planner_custom_engine`    | object      |          | Trusted `CustomEngineConfig` when Planner engine is `custom`. **Local callers only** — see below |
+| `coder_engine`             | EngineType  |          | Default Coder engine (default `claude`)                                                          |
+| `coder_model`              | string      |          | Default Coder model (Claude default `sonnet`)                                                    |
 | `coder_effort`             | EffortLevel |          | Fixed Coder reasoning effort; omission keeps the session default                                 |
-| `coder_custom_engine`      | object     |          | Trusted config when Coder may use `custom`. **Local callers only**                               |
-| `reviewer_engine`          | EngineType |          | Default Reviewer engine (default `claude`)                                                       |
-| `reviewer_model`           | string     |          | Default Reviewer model (Claude default `sonnet`)                                                 |
+| `coder_custom_engine`      | object      |          | Trusted config when Coder may use `custom`. **Local callers only**                               |
+| `reviewer_engine`          | EngineType  |          | Default Reviewer engine (default `claude`)                                                       |
+| `reviewer_model`           | string      |          | Default Reviewer model (Claude default `sonnet`)                                                 |
 | `reviewer_effort`          | EffortLevel |          | Fixed Reviewer reasoning effort; omission keeps the session default                              |
-| `reviewer_custom_engine`   | object     |          | Trusted config when Reviewer may use `custom`. **Local callers only**                            |
-| `send_timeout_ms`          | number     |          | Per-agent send cap in ms (default 600000; inclusive 5000–7200000)                                |
-| `activity_lease_ms`        | number     |          | Inactivity lease in ms (default 1800000; inclusive 60000–7200000)                                |
-| `autoloop_hard_timeout_ms` | number     |          | Absolute run cap in ms (default 86400000; inclusive 600000–259200000)                            |
+| `reviewer_custom_engine`   | object      |          | Trusted config when Reviewer may use `custom`. **Local callers only**                            |
+| `send_timeout_ms`          | number      |          | Per-agent send cap in ms (default 600000; inclusive 5000–7200000)                                |
+| `activity_lease_ms`        | number      |          | Inactivity lease in ms (default 1800000; inclusive 60000–7200000)                                |
+| `autoloop_hard_timeout_ms` | number      |          | Absolute run cap in ms (default 86400000; inclusive 600000–259200000)                            |
 
 > **Custom engines are local-only.** A `CustomEngineConfig` names an executable to
 > spawn plus its argv and env, so it may only be supplied by a caller that already