@mindfoldhq/trellis 0.6.0-beta.9 → 0.6.0

package/dist/migrations/manifests/0.6.0-beta.18.json

@@ -0,0 +1,16 @@
+{
+  "version": "0.6.0-beta.18",
+  "description": "Beta patch: channel worker OOM guard, simplified channel message routing, bundled Trellis spec bootstrap skill docs, and safer task archive auto-commit failures.",
+  "breaking": false,
+  "recommendMigrate": false,
+  "changelog": "**Enhancements:**\n- feat(channel): default OOM guard for `trellis channel spawn`. Workers that stay continuously idle past `channel.worker_guard.idle_timeout` (default `5m`) are self-terminated with `killed{reason:\"idle-timeout\"}`. Mid-turn workers are not killed by idle cleanup.\n- feat(channel): spawn-time live-worker budget per project/scope. Default `channel.worker_guard.max_live_workers: 6`. Expired idle workers are cleaned first; if the budget is still exhausted, `spawn` rejects with live-worker details and kill / override hints.\n- feat(channel): simplified worker message routing by removing message tags from channel send/wait/run internals.\n- feat(config): `.trellis/config.yaml` gains a `channel.worker_guard` section via `trellis update`.\n- feat(skills): Trellis beta bundle includes the built-in `trellis-spec-bootstarp` skill for bootstrapping `.trellis/spec/` from the real codebase.\n**Bug Fixes:**\n- fix(cli): `task.py archive` now fails when its auto-commit fails instead of reporting a successful archive with uncommitted changes.",
+  "migrations": [],
+  "configSectionsAdded": [
+    {
+      "file": ".trellis/config.yaml",
+      "sentinel": "worker_guard:",
+      "sectionHeading": "Channel worker OOM guard"
+    }
+  ],
+  "notes": "Beta patch on top of 0.6.0-beta.17. `trellis update` appends `channel.worker_guard` defaults for existing projects. To opt out, set `channel.worker_guard.idle_timeout: 0` and / or `channel.worker_guard.max_live_workers: 0`, or pass `--idle-timeout 0` / `--max-live-workers 0` per spawn."
+}

package/dist/migrations/manifests/0.6.0-beta.19.json

@@ -0,0 +1,9 @@
+{
+  "version": "0.6.0-beta.19",
+  "description": "Beta patch: Pi trellis_subagent native progress cards, durable channel idempotency, task create/archive collision guard, workflow breadcrumb clarification, and Codex 0.131 timeout bounds.",
+  "breaking": false,
+  "recommendMigrate": false,
+  "changelog": "**Enhancements:**\n- feat(pi): Pi extension now exposes `trellis_subagent` with native progress cards, `single` / `parallel` / `chain` dispatch modes, throttled live updates, and Trellis-agent validation (#286, #290).\n**Bug Fixes:**\n- fix(core): channel `sendMessage` and `postThread` accept durable `idempotencyKey` values so retries return the original JSONL event and do not duplicate strict-delivery `undeliverable` events.\n- fix(cli): `task.py create` now rejects slugs that already exist under `.trellis/tasks/archive/**` and prints the archived path (#291).\n- fix(workflow): `[workflow-state:in_progress]` now distinguishes sub-agent types from skills so agents do not call missing `trellis-implement` / `trellis-research` skills (#283).\n- fix(codex): `.codex/config.toml` emits `min_wait_timeout_ms`, `default_wait_timeout_ms`, and `max_wait_timeout_ms` together so Codex CLI 0.131+ accepts merged multi_agent_v2 timeout config (#294).\n**Internal:**\n- chore(release): restore the shipped `0.5.17` migration manifest so manifest continuity and update-chain checks pass for the beta release.",
+  "migrations": [],
+  "notes": "Beta patch on top of 0.6.0-beta.18. Run `trellis update` to refresh Pi, Codex, workflow, and task templates. No migration command is required."
+}

package/dist/migrations/manifests/0.6.0-beta.20.json

@@ -0,0 +1,9 @@
+{
+  "version": "0.6.0-beta.20",
+  "description": "Beta patch: bundle the Trellis spec bootstrap skill in the CLI package and clarify Codex CLI 0.131+ timeout-bounds requirements.",
+  "breaking": false,
+  "recommendMigrate": false,
+  "changelog": "**Bug Fixes:**\n- fix(skills): `trellis-spec-bootstarp` is now included under `dist/templates/common/bundled-skills/`, so fresh `trellis init` and `trellis update` install the built-in spec bootstrap skill and track its reference files.\n- fix(docs): the v0.6.0-beta.19 changelog now states that the full Codex `multi_agent_v2` timeout-bounds config requires Codex CLI 0.131.0+.",
+  "migrations": [],
+  "notes": "Beta patch on top of 0.6.0-beta.19. Run `trellis update` to install the bundled `trellis-spec-bootstarp` skill. Codex users should use Codex CLI 0.131.0+ for the full multi_agent_v2 timeout-bounds config."
+}

package/dist/migrations/manifests/0.6.0-beta.21.json

@@ -0,0 +1,9 @@
+{
+  "version": "0.6.0-beta.21",
+  "description": "Beta patch: stop writing the [features.multi_agent_v2] block to the generated Codex config.toml so Codex CLI 0.130 and the Codex desktop app can load the config.",
+  "breaking": false,
+  "recommendMigrate": false,
+  "changelog": "**Bug Fixes:**\n- fix(codex): `trellis init` / `trellis update` no longer write a `[features.multi_agent_v2]` block to `.codex/config.toml`. Codex CLI changed `features` deserialization between 0.130 and 0.131; the structured table form is only accepted by 0.131+. On 0.130 and earlier — including the Codex CLI bundled in the Codex desktop app — it failed with `data did not match any variant of untagged enum FeatureToml in features.multi_agent_v2`, aborting the entire config load and blocking Codex from starting. Codex's own default for multi_agent_v2 is used instead.",
+  "migrations": [],
+  "notes": "Beta patch on top of 0.6.0-beta.20. Run `trellis update` to regenerate `.codex/config.toml` without the multi_agent_v2 block. Tune multi_agent_v2 in your user-level ~/.codex/config.toml if needed."
+}

package/dist/migrations/manifests/0.6.0-beta.22.json

@@ -0,0 +1,9 @@
+{
+  "version": "0.6.0-beta.22",
+  "description": "Beta patch: remove the duplicated pull-based prelude from the generated Codex sub-agent toml files, and restore the 0.5.19 migration manifest that was missing on the beta branch.",
+  "breaking": false,
+  "recommendMigrate": false,
+  "changelog": "**Bug Fixes:**\n- fix(codex): the generated `.codex/agents/trellis-check.toml` and `trellis-implement.toml` no longer contain the \"Required: Load Trellis Context First\" prelude twice. The codex toml source templates carried an inline copy that predated the code-injected prelude (`injectPullBasedPreludeToml`); the injector then added a second copy. The inline copies are removed so the injector is the single source, and a regression test asserts the prelude appears exactly once across all class-2 platforms.\n- fix(migrations): restore `src/migrations/manifests/0.5.19.json`, which was missing on the 0.6.0-beta branch. Its absence broke the manifest-continuity guard and would break `trellis update` for users on 0.5.19.",
+  "migrations": [],
+  "notes": "Beta patch on top of 0.6.0-beta.21. Run `trellis update` to regenerate `.codex/agents/` without the duplicated prelude."
+}

package/dist/migrations/manifests/0.6.0-beta.23.json

@@ -0,0 +1,88 @@
+{
+  "version": "0.6.0-beta.23",
+  "description": "Beta patch: dispatch channel runtime agent definitions, refresh registry-backed spec via update, add Reasonix platform support, ship trellis-session-insight bundled skill, and rename trellis-spec-bootstarp → trellis-spec-bootstrap.",
+  "breaking": false,
+  "recommendMigrate": true,
+  "changelog": "**Enhancements:**\n- feat(cli): `trellis init` and `trellis update` now ship `.trellis/agents/{check,implement}.md`, so switching to a channel-driven workflow no longer fails with \"Agent 'check' not found\" (#323).\n- feat(cli): `trellis update` refreshes registry-backed `.trellis/spec` templates through the existing hash/conflict flow. `trellis init --template <id>` persists the spec source/template in `.trellis/config.yaml` so subsequent updates can re-fetch it. Supports direct spec registries and marketplace-style registries (#324).\n- feat(platform): add **Reasonix** (DeepSeek-Reasonix) as the 15th supported AI coding tool via `trellis init --reasonix`. Subagent skills (`trellis-implement`, `trellis-check`) carry `runAs: subagent` frontmatter so Reasonix spawns them as isolated subagent loops (#301).\n- feat(skills): bundle `trellis-session-insight` skill that teaches the AI how and when to reach for `trellis mem` to recall past conversations across Claude Code and Codex sessions. Auto-dispatched to every supported platform on init/update.\n- feat(workflow): `trellis workflow --template <id>` and `trellis init --workflow <id>` print a stderr warning when the resolved workflow references `.trellis/agents/<name>.md` files that are missing on disk, pointing the user at `trellis update`.\n\n**Bug Fixes:**\n- fix(skills): rename bundled `trellis-spec-bootstarp` → `trellis-spec-bootstrap` (typo). `trellis update --migrate` ships a `rename-dir` migration that renames the installed directory across 13 platform skill roots; missing roots are silently skipped. Historical migration manifests `0.5.17.json` and `0.6.0-beta.18.json` keep the typoed text because they describe what already shipped to users on those versions (#296).",
+  "migrations": [
+    {
+      "type": "rename-dir",
+      "from": ".claude/skills/trellis-spec-bootstarp",
+      "to": ".claude/skills/trellis-spec-bootstrap",
+      "description": "Claude Code: rename installed bundled skill directory from typoed name to corrected name."
+    },
+    {
+      "type": "rename-dir",
+      "from": ".cursor/skills/trellis-spec-bootstarp",
+      "to": ".cursor/skills/trellis-spec-bootstrap",
+      "description": "Cursor: rename installed bundled skill directory from typoed name to corrected name."
+    },
+    {
+      "type": "rename-dir",
+      "from": ".opencode/skills/trellis-spec-bootstarp",
+      "to": ".opencode/skills/trellis-spec-bootstrap",
+      "description": "OpenCode: rename installed bundled skill directory from typoed name to corrected name."
+    },
+    {
+      "type": "rename-dir",
+      "from": ".agents/skills/trellis-spec-bootstarp",
+      "to": ".agents/skills/trellis-spec-bootstrap",
+      "description": "Codex / Gemini CLI (shared): rename installed bundled skill directory from typoed name to corrected name."
+    },
+    {
+      "type": "rename-dir",
+      "from": ".kiro/skills/trellis-spec-bootstarp",
+      "to": ".kiro/skills/trellis-spec-bootstrap",
+      "description": "Kiro: rename installed bundled skill directory from typoed name to corrected name."
+    },
+    {
+      "type": "rename-dir",
+      "from": ".qoder/skills/trellis-spec-bootstarp",
+      "to": ".qoder/skills/trellis-spec-bootstrap",
+      "description": "Qoder: rename installed bundled skill directory from typoed name to corrected name."
+    },
+    {
+      "type": "rename-dir",
+      "from": ".codebuddy/skills/trellis-spec-bootstarp",
+      "to": ".codebuddy/skills/trellis-spec-bootstrap",
+      "description": "CodeBuddy: rename installed bundled skill directory from typoed name to corrected name."
+    },
+    {
+      "type": "rename-dir",
+      "from": ".github/skills/trellis-spec-bootstarp",
+      "to": ".github/skills/trellis-spec-bootstrap",
+      "description": "GitHub Copilot: rename installed bundled skill directory from typoed name to corrected name."
+    },
+    {
+      "type": "rename-dir",
+      "from": ".factory/skills/trellis-spec-bootstarp",
+      "to": ".factory/skills/trellis-spec-bootstrap",
+      "description": "Droid: rename installed bundled skill directory from typoed name to corrected name."
+    },
+    {
+      "type": "rename-dir",
+      "from": ".pi/skills/trellis-spec-bootstarp",
+      "to": ".pi/skills/trellis-spec-bootstrap",
+      "description": "Pi Agent: rename installed bundled skill directory from typoed name to corrected name."
+    },
+    {
+      "type": "rename-dir",
+      "from": ".agent/skills/trellis-spec-bootstarp",
+      "to": ".agent/skills/trellis-spec-bootstrap",
+      "description": "Antigravity: rename installed bundled skill directory from typoed name to corrected name."
+    },
+    {
+      "type": "rename-dir",
+      "from": ".windsurf/skills/trellis-spec-bootstarp",
+      "to": ".windsurf/skills/trellis-spec-bootstrap",
+      "description": "Windsurf: rename installed bundled skill directory from typoed name to corrected name."
+    },
+    {
+      "type": "rename-dir",
+      "from": ".kilocode/skills/trellis-spec-bootstarp",
+      "to": ".kilocode/skills/trellis-spec-bootstrap",
+      "description": "Kilo: rename installed bundled skill directory from typoed name to corrected name."
+    }
+  ],
+  "notes": "Beta patch on top of 0.6.0-beta.22. Run `trellis update --migrate` to rename installed `trellis-spec-bootstarp/` skill directories to `trellis-spec-bootstrap/` across every platform you have configured (silently skips ones you do not). Plain `trellis update` also installs the new `trellis-session-insight` bundled skill and the `.trellis/agents/{check,implement}.md` channel runtime files."
+}

package/dist/migrations/manifests/0.6.0-rc.0.json

@@ -0,0 +1,9 @@
+{
+  "version": "0.6.0-rc.0",
+  "description": "First release candidate for v0.6.0. Feature surface frozen; entering stabilization. Only fix since 0.6.0-beta.23 is removing explicit mcp__exa__* tools from bundled Claude-style sub-agent defs so they no longer silent-skip on installs without the Exa MCP server.",
+  "breaking": false,
+  "recommendMigrate": false,
+  "changelog": "**Bug Fixes:**\n- fix(agents): drop explicit `mcp__exa__*` tools from bundled `trellis-implement` and `trellis-check` agent definitions. Claude Code silently skips agent registration when an explicit MCP tool name fails to resolve, so users without the Exa MCP server installed had every Trellis sub-agent disappear from the dispatch list. `trellis-research` keeps external search by folding `mcp__exa__*` + `mcp__chrome-devtools__*` into a single `mcp__*` wildcard, which Claude Code resolves lazily and does not silent-skip on. OpenCode files use a different permission syntax and are unchanged (#302).\n\n**Internal:**\n- chore(release): v0.6 feature surface frozen at this RC. Open feature requests (#193, #318, #320, #325, #326, etc.) are deferred to v0.7 or later. Further changes on this line will be bug-only `0.6.0-rc.*` cuts.",
+  "migrations": [],
+  "notes": "First release candidate for v0.6.0. Run `npm install -g @mindfoldhq/trellis@rc && trellis update` to pick up the agent silent-skip fix. If you are coming from a beta older than 0.6.0-beta.23, also pass `--migrate` to apply the rename-dir migration that moves `trellis-spec-bootstarp/` to `trellis-spec-bootstrap/` across configured platform skill roots."
+}

package/dist/migrations/manifests/0.6.0.json

@@ -0,0 +1 @@
+{"version": "0.6.0", "description": "v0.6.0 stable — multi-agent channel runtime, `trellis mem`, `@mindfoldhq/trellis-core` SDK extraction, 15-platform coverage (incl. Reasonix + Pi). Stable promotion of rc.0 with no new src/ changes.", "breaking": false, "recommendMigrate": true, "changelog": "**v0.6.0 stable.** Stable promotion of rc.0 — no new src/ changes since rc.0.\n\n**Heads-up:** Trellis now ships a multi-agent channel runtime (`trellis channel`) and a memory subsystem (`trellis mem`). Both are auto-discovered via bundled skills; the single-agent workflow from 0.5 still works unchanged.\n\nCycle headlines since 0.5.0:\n\n**Channel runtime**\n- `trellis channel`: durable thread / forum channels, project/global scope, linked context, idempotent writes (`idempotencyKey`).\n- Worker lifecycle: `spawn` / `kill` / `prune` / `wait` / `run` with turn-event recording.\n- OOM guard ON by default: `idle_timeout 5m`, `max_live_workers 6` per scope; tunable via `.trellis/config.yaml` or `--idle-timeout` / `--max-live-workers`.\n- Bundled `.trellis/agents/{check,implement}.md` ship at `init` / `update` so `channel spawn --agent` works out of the box (#323).\n\n**Memory**\n- `trellis mem` reads local Claude Code / Codex sessions. Five subcommands: `projects` / `list` / `search` / `context` / `extract`.\n- `--phase brainstorm|implement|all` slices at `task.py create` / `task.py start` boundaries.\n- Library API: `@mindfoldhq/trellis-core/mem`. OpenCode 1.2+ reader degraded (see notes).\n\n**SDK extraction**\n- `@mindfoldhq/trellis-core` is now its own npm package, published in lockstep with the CLI. Subpath exports: `/channel`, `/task`, `/testing`, `/mem`.\n- v0.6.0 is the first GA shipping both packages simultaneously; `bump-versions.js` rewrites `workspace:*` → exact version at release.\n\n**Platform coverage**\n- 15 platforms total. **New: Reasonix** (DeepSeek-Reasonix) and **matured Pi Agent** native extension with `trellis_subagent` tool + project-level override.\n- Codex dispatch defaults to `inline` (was `sub-agent`); no longer writes `[features.multi_agent_v2]` to `.codex/config.toml` (fixes config-load abort on Codex CLI ≤ 0.130).\n- OpenCode `TRELLIS_CONTEXT_ID` picks shell dialect (PowerShell / Git Bash / POSIX).\n- Cursor `sessionStart` emits `additional_context` per Cursor schema; GitHub Copilot SessionStart uses `hookSpecificOutput.additionalContext`.\n\n**Workflow + planning**\n- Task triage consent: no-task turns classify the request and ask before creating a task.\n- Three planning artifacts: `prd.md` / `design.md` / `implement.md`. Parent / child task trees supported.\n- Workflow templates via `trellis init --workflow` and `trellis workflow`. Built-ins: `native`, `tdd`, `channel-driven-subagent-dispatch`.\n\n**Updater**\n- `trellis upgrade` first-class command: channel-aware defaults, `--tag`, `--dry-run`; hardened for Windows.\n- `trellis update` refreshes registry-backed `.trellis/spec` (supports direct + marketplace registries, SSH, self-hosted Git; #324).\n- Configurable hooks via `.trellis/config.yaml`: session commit / journal limits, `hooks.after_*`, `channel.worker_guard.*`, `codex.dispatch_mode`.\n\n**Bundled skills**\n- `trellis-spec-bootstrap` (renamed from typoed `trellis-spec-bootstarp`, #296): bootstraps `.trellis/spec/` from the real codebase.\n- `trellis-session-insight` (new): when to reach for `trellis mem` for cross-session recall.\n- `trellis-channel` (new in GA cycle): when to reach for `trellis channel` for multi-agent collaboration, forum/thread boards, dispatcher-wait patterns.\n- `trellis-meta` (refreshed for v0.6): SKILL.md preamble + new references (`multi-agent-channel.md`, `bundled-skills.md`) cover channel runtime, mem, dual-package SDK, parent/child tasks, workflow templates, registry-backed spec, configurable hooks, Reasonix + Pi platforms, bundled-skill auto-dispatch flow.\n\n**Migration & update flow**\n- `0.6.0-beta.0` is the load-bearing breaking manifest for 0.5.x → 0.6.0 (rename / delete chain documented in its own `migrationGuide`).\n- `0.6.0-beta.23` ships a `rename-dir` migration: `trellis-spec-bootstarp/` → `trellis-spec-bootstrap/` across 13 platform skill roots. Missing roots silently skip.\n- This `0.6.0.json` carries `migrations: []` (GA = rc.0). `recommendMigrate: true` still fires the `--migrate` guidance for users coming directly from 0.5.x.\n\n**Bug fixes (cut window)**\n- fix(agents): drop explicit `mcp__exa__*` tools from bundled `trellis-implement` / `trellis-check` defs. Claude Code silently skipped agent registration when an explicit MCP tool failed to resolve; users without Exa MCP installed lost every Trellis sub-agent. `trellis-research` keeps external search via `mcp__*` wildcard. OpenCode files unchanged (different permission syntax). (#302, rc.0)\n- Earlier 0.6 beta-line bug fixes are documented in their per-beta changelogs.\n\n**Out of scope at GA**\n- OpenCode 1.2+ `trellis mem` reader remains degraded; permanent rework deferred past 0.6.0.\n- Open feature requests (#193, #318, #320, #325, #326) deferred to 0.7+.", "migrations": [], "notes": "**Stable release.** Promoted from 0.6.0-rc.0 with no new src/ changes since.\n\n**Users on 0.5.x** (e.g. `0.5.19`, the last 0.5 stable): run `trellis update --migrate`. The `--migrate` flag is REQUIRED — the breaking-change gate from `0.6.0-beta.0` fires when traversing the migration chain, and a separate `rename-dir` migration from `0.6.0-beta.23` renames the bundled `trellis-spec-bootstarp/` skill directory to `trellis-spec-bootstrap/` across every configured platform skill root (missing roots silently skip).\n\n**Users on any 0.6.0 prerelease** (`beta.X` / `rc.0`): plain `trellis update` is a clean version bump — no `--migrate` needed because you already absorbed the breaking manifest when you adopted the beta line.\n\n**Codex users**: the v0.6 cycle flipped `codex.dispatch_mode` default from `sub-agent` to `inline`. If you previously uncommented `dispatch_mode: sub-agent` in `.trellis/config.yaml`, that opt-in still routes to the legacy sub-agent dispatch flow; if you left the line commented (the default), behavior is now inline. `trellis init` / `update` no longer write a `[features.multi_agent_v2]` block to `.codex/config.toml`, so Codex CLI ≤ 0.130 (including the desktop app's bundled CLI) no longer aborts on config load.\n\n**Channel runtime is opt-in.** The single-agent workflow you know from 0.5 still works unchanged. `trellis channel` and the bundled `trellis-session-insight` skill are auto-discovered but only fire when the AI decides the task calls for them.\n\n**OpenCode users**: `trellis mem` returns empty on OpenCode 1.2+ in this build — the SQLite reader was reverted at `0.6.0-beta.4` due to native-dependency install failures on Windows. A re-enable is planned post-0.6.0.\n\nInstall: `npm install -g @mindfoldhq/trellis`"}

package/dist/templates/claude/agents/trellis-check.md

@@ -2,7 +2,7 @@
 name: trellis-check
 description: |
   Code quality check expert. Reviews code changes against specs and self-fixes issues.
-tools: Read, Write, Edit, Bash, Glob, Grep, mcp__exa__web_search_exa, mcp__exa__get_code_context_exa
+tools: Read, Write, Edit, Bash, Glob, Grep
 ---
 # Check Agent
 
@@ -27,14 +27,18 @@ Look for the `<!-- trellis-hook-injected -->` marker in your input above.
 
 Before checking, read:
 - `.trellis/spec/` - Development guidelines
+- Task `prd.md` - Requirements document
+- Task `design.md` - Technical design (if exists)
+- Task `implement.md` - Execution plan (if exists)
 - Pre-commit checklist for quality standards
 
 ## Core Responsibilities
 
 1. **Get code changes** - Use git diff to get uncommitted code
-2. **Check against specs** - Verify code follows guidelines
-3. **Self-fix** - Fix issues yourself, not just report them
-4. **Run verification** - typecheck and lint
+2. **Review task artifacts** - Check changes against prd.md, design.md if present, and implement.md if present
+3. **Check against specs** - Verify code follows guidelines
+4. **Self-fix** - Fix issues yourself, not just report them
+5. **Run verification** - typecheck and lint
 
 ## Important
 
@@ -53,10 +57,12 @@ git diff --name-only  # List changed files
 git diff              # View specific changes
 ```
 
-### Step 2: Check Against Specs
+### Step 2: Check Against Specs and Task Artifacts
 
-Read relevant specs in `.trellis/spec/` to check code:
+Read the task's prd.md, design.md if present, and implement.md if present, then read relevant specs in `.trellis/spec/` to check code:
 
+- Does it satisfy the task requirements
+- Does it follow the technical design and implementation plan when present
 - Does it follow directory structure conventions
 - Does it follow naming conventions
 - Does it follow code patterns

package/dist/templates/claude/agents/trellis-implement.md

@@ -2,7 +2,7 @@
 name: trellis-implement
 description: |
   Code implementation expert. Understands specs and requirements, then implements features. No git commit allowed.
-tools: Read, Write, Edit, Bash, Glob, Grep, mcp__exa__web_search_exa, mcp__exa__get_code_context_exa
+tools: Read, Write, Edit, Bash, Glob, Grep
 ---
 # Implement Agent
 

package/dist/templates/claude/agents/trellis-research.md

@@ -2,7 +2,7 @@
 name: trellis-research
 description: |
   Code and tech search expert. Finds files, patterns, and tech solutions, and PERSISTS every finding to the current task's research/ directory. No code modifications outside that directory.
-tools: Read, Write, Glob, Grep, Bash, mcp__exa__web_search_exa, mcp__exa__get_code_context_exa, Skill, mcp__chrome-devtools__*
+tools: Read, Write, Glob, Grep, Bash, Skill, mcp__*
 ---
 # Research Agent
 

package/dist/templates/codebuddy/agents/trellis-check.md

@@ -2,7 +2,7 @@
 name: trellis-check
 description: |
   Code quality check expert. Reviews code changes against specs and self-fixes issues.
-tools: Read, Write, Edit, Bash, Glob, Grep, mcp__exa__web_search_exa, mcp__exa__get_code_context_exa
+tools: Read, Write, Edit, Bash, Glob, Grep
 ---
 # Check Agent
 
@@ -27,14 +27,18 @@ Look for the `<!-- trellis-hook-injected -->` marker in your input above.
 
 Before checking, read:
 - `.trellis/spec/` - Development guidelines
+- Task `prd.md` - Requirements document
+- Task `design.md` - Technical design (if exists)
+- Task `implement.md` - Execution plan (if exists)
 - Pre-commit checklist for quality standards
 
 ## Core Responsibilities
 
 1. **Get code changes** - Use git diff to get uncommitted code
-2. **Check against specs** - Verify code follows guidelines
-3. **Self-fix** - Fix issues yourself, not just report them
-4. **Run verification** - typecheck and lint
+2. **Review task artifacts** - Check changes against prd.md, design.md if present, and implement.md if present
+3. **Check against specs** - Verify code follows guidelines
+4. **Self-fix** - Fix issues yourself, not just report them
+5. **Run verification** - typecheck and lint
 
 ## Important
 
@@ -53,10 +57,12 @@ git diff --name-only  # List changed files
 git diff              # View specific changes
 ```
 
-### Step 2: Check Against Specs
+### Step 2: Check Against Specs and Task Artifacts
 
-Read relevant specs in `.trellis/spec/` to check code:
+Read the task's prd.md, design.md if present, and implement.md if present, then read relevant specs in `.trellis/spec/` to check code:
 
+- Does it satisfy the task requirements
+- Does it follow the technical design and implementation plan when present
 - Does it follow directory structure conventions
 - Does it follow naming conventions
 - Does it follow code patterns

package/dist/templates/codebuddy/agents/trellis-implement.md

@@ -2,7 +2,7 @@
 name: trellis-implement
 description: |
   Code implementation expert. Understands specs and requirements, then implements features. No git commit allowed.
-tools: Read, Write, Edit, Bash, Glob, Grep, mcp__exa__web_search_exa, mcp__exa__get_code_context_exa
+tools: Read, Write, Edit, Bash, Glob, Grep
 ---
 # Implement Agent
 

package/dist/templates/codebuddy/agents/trellis-research.md

@@ -2,7 +2,7 @@
 name: trellis-research
 description: |
   Code and tech search expert. Finds files, patterns, and tech solutions, and PERSISTS every finding to the current task's research/ directory. No code modifications outside that directory.
-tools: Read, Write, Glob, Grep, Bash, mcp__exa__web_search_exa, mcp__exa__get_code_context_exa, Skill, mcp__chrome-devtools__*
+tools: Read, Write, Glob, Grep, Bash, Skill, mcp__*
 ---
 # Research Agent
 

package/dist/templates/codex/agents/trellis-check.toml

@@ -12,31 +12,6 @@ CRITICAL — Recursion guard (read first):
 
 ---
 
-## Required: Load Trellis Context First
-
-This platform does NOT auto-inject task context via hook. Before doing anything else, you MUST load context yourself.
-
-### Step 1: Find the active task path
-
-Try in order — stop at the first one that yields a task path:
-
-1. **Look at the dispatch prompt** you received from the main agent. If its first line is `Active task: <path>` (e.g. `Active task: .trellis/tasks/04-17-foo`), use that path. The main agent is required to include this line on class-2 platforms.
-2. **Run** `python3 ./.trellis/scripts/task.py current --source` and read the `Current task:` line.
-3. **If both fail** (no `Active task:` line in the prompt and `task.py current` returns no task), ask the user which task to work on; do NOT guess.
-
-### Step 2: Load task context from the resolved path
-
-1. Read `<task-path>/check.jsonl` — JSONL list of spec/research files relevant to this agent.
-2. For each entry in the JSONL, Read its `file` path — these are the specs and research notes you must follow.
-   **Skip rows without a `"file"` field** (e.g. `{"_example": "..."}` seed rows left over from `task.py create` before the curator ran).
-3. Read the task's `prd.md` (requirements), then `design.md` if present (technical design), then `implement.md` if present (execution plan).
-
-If `check.jsonl` has no curated entries (only a seed row, or the file is missing), fall back to: read the task artifacts, list available specs with `python3 ./.trellis/scripts/get_context.py --mode packages`, and pick the specs that match the task domain yourself. Do NOT block on the missing jsonl — lightweight tasks may be PRD-only, while complex tasks may also include `design.md` and `implement.md`.
-
-If the resolved task path has no `prd.md`, ask the user what to work on; do NOT proceed without context.
-
----
-
 You are the Trellis reviewer agent.
 
 Your job is to review code changes against specs AND fix issues directly — not just report them. You have write access; use it.

package/dist/templates/codex/agents/trellis-implement.toml

@@ -12,31 +12,6 @@ CRITICAL — Recursion guard (read first):
 
 ---
 
-## Required: Load Trellis Context First
-
-This platform does NOT auto-inject task context via hook. Before doing anything else, you MUST load context yourself.
-
-### Step 1: Find the active task path
-
-Try in order — stop at the first one that yields a task path:
-
-1. **Look at the dispatch prompt** you received from the main agent. If its first line is `Active task: <path>` (e.g. `Active task: .trellis/tasks/04-17-foo`), use that path. The main agent is required to include this line on class-2 platforms.
-2. **Run** `python3 ./.trellis/scripts/task.py current --source` and read the `Current task:` line.
-3. **If both fail** (no `Active task:` line in the prompt and `task.py current` returns no task), ask the user which task to work on; do NOT guess.
-
-### Step 2: Load task context from the resolved path
-
-1. Read `<task-path>/implement.jsonl` — JSONL list of spec/research files relevant to this agent.
-2. For each entry in the JSONL, Read its `file` path — these are the specs and research notes you must follow.
-   **Skip rows without a `"file"` field** (e.g. `{"_example": "..."}` seed rows left over from `task.py create` before the curator ran).
-3. Read the task's `prd.md` (requirements), then `design.md` if present (technical design), then `implement.md` if present (execution plan).
-
-If `implement.jsonl` has no curated entries (only a seed row, or the file is missing), fall back to: read the task artifacts, list available specs with `python3 ./.trellis/scripts/get_context.py --mode packages`, and pick the specs that match the task domain yourself. Do NOT block on the missing jsonl — lightweight tasks may be PRD-only, while complex tasks may also include `design.md` and `implement.md`.
-
-If the resolved task path has no `prd.md`, ask the user what to work on; do NOT proceed without context.
-
----
-
 You are the Trellis implementer agent.
 
 Rules:

package/dist/templates/codex/config.toml

@@ -5,8 +5,6 @@
 #
 #   [projects."/abs/path/to/this/repo"]
 #   trust_level = "trusted"
-#
-# Without trust, the [features] block below is loaded but disabled.
 
 # Keep AGENTS.md as the primary project instruction file.
 project_doc_fallback_filenames = ["AGENTS.md"]
@@ -19,17 +17,12 @@ project_doc_fallback_filenames = ["AGENTS.md"]
 # Codex 0.129+ additionally gates each installed hook behind a one-time
 # `/hooks` TUI review; until the user approves it, the hook stays inactive.
 
-# multi_agent_v2 forces structured subagent orchestration with the
-# `wait` tool — parent must block on terminal status before acting,
-# instead of cancelling / re-spawning. Incompatible with
-# [agents].max_threads (codex will reject the combination).
-# `enabled = true` is required inside the table — the table form does
-# NOT auto-enable the feature without it.
-# - max_concurrent_threads_per_session: bumps default 4 → 6.
-# - min_wait_timeout_ms: 480000 ms = 8 min. Codex default is 10 s, too
-#   short for Trellis subagents that routinely take 2-10 min. Hard
-#   ceiling is 3,600,000 (1 h).
-[features.multi_agent_v2]
-enabled = true
-max_concurrent_threads_per_session = 6
-min_wait_timeout_ms = 480000
+# NOTE: Trellis intentionally does NOT write a [features.multi_agent_v2]
+# block here. Codex CLI changed `features` deserialization between 0.130
+# and 0.131: the structured table form (with max_concurrent_threads_per_session
+# / *_wait_timeout_ms) is only accepted by 0.131+. On 0.130 and earlier —
+# including the codex CLI bundled inside the Codex desktop app — it fails
+# with `data did not match any variant of untagged enum FeatureToml`, which
+# aborts the entire config load and blocks Codex from starting. Codex's own
+# default for multi_agent_v2 is used instead; tune it in your user-level
+# config if needed.

package/dist/templates/codex/hooks/session-start.py

@@ -18,6 +18,28 @@ import warnings
 from io import StringIO
 from pathlib import Path
 
+# Force UTF-8 on stdin/stdout/stderr on Windows. Default codepage there is
+# cp936 / cp1252 / etc. — non-ASCII content (Chinese task names, prd snippets)
+# both in stdin (hook payload from host CLI) and stdout (our emitted blocks)
+# raises UnicodeDecodeError / UnicodeEncodeError. Equivalent to `python -X utf8`
+# but applied per-stream so we don't depend on host CLI's command wiring.
+if sys.platform.startswith("win"):
+    import io as _io
+    for _stream_name in ("stdin", "stdout", "stderr"):
+        _stream = getattr(sys, _stream_name, None)
+        if _stream is None:
+            continue
+        if hasattr(_stream, "reconfigure"):
+            try:
+                _stream.reconfigure(encoding="utf-8", errors="replace")  # type: ignore[union-attr]
+            except Exception:
+                pass
+        elif hasattr(_stream, "detach"):
+            try:
+                setattr(sys, _stream_name, _io.TextIOWrapper(_stream.detach(), encoding="utf-8", errors="replace"))
+            except Exception:
+                pass
+
 
 def _normalize_windows_shell_path(path_str: str) -> str:
     """Normalize Unix-style shell paths to real Windows paths.

package/dist/templates/codex/hooks.json

@@ -5,7 +5,7 @@
         "hooks": [
           {
             "type": "command",
-            "command": "{{PYTHON_CMD}} .codex/hooks/inject-workflow-state.py",
+            "command": "{{PYTHON_CMD}} -X utf8 .codex/hooks/inject-workflow-state.py",
             "timeout": 15
           }
         ]

package/dist/templates/common/bundled-skills/trellis-channel/SKILL.md

@@ -0,0 +1,67 @@
+---
+name: trellis-channel
+description: Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.
+---
+
+# trellis-channel
+
+`trellis channel` is the local multi-agent collaboration runtime. Reach for it when agents need to talk through a durable event log, when a worker should be spawned as a peer process, when an in-flight worker needs interrupt / debugging, or when feedback should be recorded on a durable `--type forum` channel.
+
+Typical user signals: "和 codex/claude 讨论", "brainstorm with another agent", "spawn an implement/check worker", "let agent review", "open an issue board / changelog forum", "look at this thread", "channel is stuck / no output", "progress was truncated", "how do I write that channel command".
+
+This skill is an index. Load only the reference file for the current job — do not preload all of them.
+
+## First Commands
+
+```bash
+trellis --version
+trellis channel --help
+trellis channel list --all
+trellis channel list --scope global --all
+```
+
+If the user names a channel or thread, inspect it before asking for background:
+
+```bash
+trellis channel forum <board> --scope global
+trellis channel thread <board> <thread> --scope global
+trellis channel context list <board> --scope global --thread <thread>
+```
+
+## Route By User Intent
+
+| User intent | Read |
+|---|---|
+| "和 codex/claude 讨论一下", "brainstorm with another agent" | `references/workflows.md` |
+| "派一个 implement/check agent", "让 agent review", "spawn a worker" | `references/workflows.md`, then `references/workers.md` |
+| "开 issue 区 / topic 群 / changelog / board", "make a forum" | `references/forum.md` |
+| "看看这个 thread / linked context", "inspect a thread" | `references/forum.md` |
+| "channel 卡住了 / 没输出 / progress 被截断", "worker stalled" | `references/progress-debugging.md` |
+| "具体命令怎么写", "what flags does X take" | `references/command-reference.md` |
+
+## Core Rules
+
+- New forum channels use `--type forum`. A `thread` is one item inside a forum channel.
+- Use `--context-file` / `--context-raw` and `trellis channel context add/delete/list`. `--linked-context-*` is deprecated terminology.
+- Use `--stdin` or `--text-file` for long messages. Do not put long mixed Chinese/English text in the positional shell argument.
+- Pretty `messages` output is an operator dashboard and may truncate progress. Use `--raw` for audit.
+- `--as` is the speaker or worker handle, depending on the command. Use explicit, stable names when multiple agents or sessions are involved.
+- `--scope project` (default) operates on the current cwd's project bucket; `--scope global` operates on the shared `__global__` bucket. Pick scope deliberately — a global board is invisible from project listings unless `--scope global` is passed.
+- For brainstorm, do multiple pressure-test rounds. One answer plus one confirmation is review, not brainstorm.
+- **Dispatcher wait pattern**: use `--kind done` / `--kind turn_finished` (trellis-emitted system events), NOT a user `--tag` as the completion signal. CLI help lists `phase_done` / `question` as `--tag` examples but only `interrupt` is a reserved tag with hardcoded trellis behavior; the others are opaque user labels. Relying on a worker to run `send --tag <my_signal>` is unreliable — LLM workers commonly write the tag string into prose instead of running the actual CLI command. See `references/command-reference.md` "tag vs kind".
+- Forum channels are event-sourced. Do not parse `events.jsonl` first; use `forum`, `thread`, `messages --thread`, and `context list`.
+- `@mindfoldhq/trellis-core` owns reusable channel/thread state, event append, seq allocation, context/title projection, reducers, and task helpers. The CLI owns flags, terminal rendering, prompts, worker lifecycle, and process exits.
+
+## Reference Files
+
+- `references/workflows.md` — canonical collaboration patterns A–F (peer brainstorm, spawned review, dispatch-and-wait, forum issue capture, interrupt-and-redirect, one-shot run).
+- `references/forum.md` — forum channels, context, title, rename, changelog forums, thread filtering.
+- `references/workers.md` — spawn, agent cards, context injection (`--file` / `--jsonl`), interrupts, kill semantics.
+- `references/progress-debugging.md` — progress/raw inspection, stalled worker diagnosis, OOM guard, exit codes.
+- `references/command-reference.md` — current CLI command reference (every subcommand, every flag, output conventions, scope/type model).
+
+## Not For
+
+- One static review where a markdown file and prompt are enough.
+- Replacing normal tool calls with self-logging.
+- Long-term memory retrieval. Use durable forum channels for actionable issues, and `trellis mem` (the `trellis-session-insight` skill) for session/history search.