Merge branch 'master' of code.crashlabs.io:crashlabs/huskies

855 deleted the HTTP /mcp route and pointed agents at ws://...crdt-sync,
but Claude Code's .mcp.json doesn't speak ws:// and the rendezvous WS
never had MCP method handlers wired up — so every spawned Claude Code
agent (gateway-routed and local) booted with zero huskies tools and
died on --permission-prompt-tool=mcp__huskies__prompt_permission.

Restore mcp_post_handler / mcp_get_handler / handle_initialize, re-add
the /mcp route, and revert all three .mcp.json writers to emit
http://localhost:{port}/mcp with explicit "type": "http". Reuses the
already-extracted gateway::jsonrpc types and the surviving
dispatch_tool_call / list_tools surfaces — net add ~140 lines.

Federation work is unaffected: /crdt-sync continues to do CRDT sync,
which is what it was actually doing. MCP-over-WebSocket for cross-LAN
agents was never wired up by 855 and can be done as a proper follow-up
with a regression test that boots a real claude and verifies tool
registration.

Verified end-to-end: /mcp initialize, tools/list (74 tools incl.
prompt_permission), and tools/call all respond correctly from inside
the rebuilt container.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

.claude/commands/coverage.md

@@ -0,0 +1,21 @@
+Show test coverage from the cached `.coverage_baseline` file, or rerun the full test suite with `$ARGUMENTS`.
+
+## Usage
+
+- `/coverage` — read cached coverage from `.coverage_baseline` (instant)
+- `/coverage run` — run `script/test_coverage` and report fresh results
+
+## What it does
+
+**Cached mode (default):** Reads `.coverage_baseline` and displays the stored coverage percentage(s). This is instant and does not run any tests.
+
+**Run mode (`run`):** Executes `script/test_coverage` which runs:
+1. Rust tests with `cargo llvm-cov` (reports line coverage %)
+2. Frontend tests with `npm run test:coverage` (reports line coverage %)
+3. Computes the overall average and compares to the threshold
+
+Reports Rust coverage, Frontend coverage, Overall coverage, and whether the run passed the threshold.
+
+---
+
+If the arguments (`$ARGUMENTS`) equal `run`, execute `bash script/test_coverage` from the project root and show the Coverage Summary section from the output. Otherwise, read `.coverage_baseline` and display the stored coverage value(s).

.claude/settings.json

@@ -1,76 +1,28 @@
 {
-  "enabledMcpjsonServers": [
-    "storkit"
-  ],
   "permissions": {
     "allow": [
-      "Bash(./server/target/debug/storkit:*)",
-      "Bash(./target/debug/storkit:*)",
-      "Bash(STORKIT_PORT=*)",
       "Bash(cargo build:*)",
       "Bash(cargo check:*)",
-      "Bash(cargo clippy:*)",
-      "Bash(cargo doc:*)",
-      "Bash(cargo llvm-cov:*)",
-      "Bash(cargo nextest run:*)",
-      "Bash(cargo run:*)",
-      "Bash(cargo test:*)",
-      "Bash(cargo watch:*)",
-      "Bash(cd *)",
-      "Bash(claude:*)",
-      "Bash(curl:*)",
-      "Bash(echo:*)",
-      "Bash(env:*)",
       "Bash(git *)",
-      "Bash(grep:*)",
-      "Bash(kill *)",
       "Bash(ls *)",
-      "Bash(lsof *)",
       "Bash(mkdir *)",
       "Bash(mv *)",
-      "Bash(npm run build:*)",
-      "Bash(npx @biomejs/biome check:*)",
-      "Bash(npx @playwright/test test:*)",
-      "Bash(npx biome check:*)",
-      "Bash(npx playwright test:*)",
-      "Bash(npx tsc:*)",
-      "Bash(npx vitest:*)",
-      "Bash(pnpm add:*)",
-      "Bash(pnpm build:*)",
-      "Bash(pnpm dev:*)",
-      "Bash(pnpm install:*)",
-      "Bash(pnpm run build:*)",
-      "Bash(pnpm run test:*)",
-      "Bash(pnpm test:*)",
-      "Bash(printf:*)",
-      "Bash(ps *)",
-      "Bash(python3:*)",
-      "Bash(pwd *)",
       "Bash(rm *)",
-      "Bash(sleep *)",
       "Bash(touch *)",
-      "Bash(xargs:*)",
+      "Bash(echo:*)",
-      "WebFetch(domain:crates.io)",
+      "Bash(pwd *)",
-      "WebFetch(domain:docs.rs)",
+      "Bash(grep:*)",
-      "WebFetch(domain:github.com)",
-      "WebFetch(domain:portkey.ai)",
-      "WebFetch(domain:www.shuttle.dev)",
-      "WebSearch",
-      "mcp__storkit__*",
-      "Edit",
-      "Write",
       "Bash(find *)",
-      "Bash(sqlite3 *)",
-      "Bash(cat <<:*)",
-      "Bash(cat <<'ENDJSON:*)",
-      "Bash(make release:*)",
-      "Bash(npm test:*)",
       "Bash(head *)",
       "Bash(tail *)",
       "Bash(wc *)",
-      "Bash(npx vite:*)",
+      "Bash(cat *)",
-      "Bash(npm run dev:*)",
+      "Edit",
-      "Bash(stat *)"
+      "Write",
+      "mcp__huskies__*"
     ]
-  }
+  },
-}
+  "enabledMcpjsonServers": [
+    "huskies"
+  ]
+}

.dockerignore

@@ -2,9 +2,9 @@
 **/target/
 **/node_modules/
 frontend/dist/
-.storkit/worktrees/
+.huskies/worktrees/
-.storkit/logs/
+.huskies/logs/
-.storkit/work/6_archived/
+.huskies/work/6_archived/
 .git/
 *.swp
 *.swo

.gitignore

@@ -5,10 +5,19 @@
 # Local environment (secrets)
 .env
 
-# App specific (root-level; storkit subdirectory patterns live in .storkit/.gitignore)
+# Local-only scripts
+script/local-release
+
+# App specific (root-level; huskies subdirectory patterns live in .huskies/.gitignore)
 store.json
-.storkit_port
+_merge_parsed.json
-.storkit/bot.toml.bak
+.huskies_port
+.huskies/bot.toml.bak
+.huskies/build_hash
+
+# Coverage report (generated by script/test_coverage, not tracked in git)
+.coverage_report.json
+.coverage_baseline
 
 # Rust stuff
 target
@@ -45,3 +54,8 @@ server/target
 *.sln
 *.sw?
 /test-results/.last-run.json
+
+# Ignore old story files until we feel like deleting them
+.storkit
+.storkit_port
+/.huskies/node_identity.key

.huskies/.gitignore

@@ -23,3 +23,14 @@ token_usage.jsonl
 
 # Chat service logs
 whatsapp_history.json
+
+# Timers
+timers.json
+
+# Misc
+wishlist.md
+
+# Database
+pipeline.db
+pipeline.db.bak*
+session_store.json

.huskies/AGENT.md

@@ -0,0 +1,27 @@
+# Huskies project-local agent guidance
+
+## Documentation
+Docs live in `website/docs/*.html` (static HTML), **not** Markdown files. When a story asks you to document something, edit the relevant `.html` file in `website/docs/`.
+
+## Configuration files
+- Agent config: `.huskies/agents.toml` (preferred) or `[[agent]]` blocks in `.huskies/project.toml`
+- Project settings: `.huskies/project.toml`
+- Bot credentials: `.huskies/bot.toml` (gitignored — never commit)
+
+## Frontend build
+The frontend is embedded into the Rust binary via `rust-embed`. Run `npm run build` in `frontend/` before testing frontend changes, or the embedded assets will be stale.
+
+## Quality gates (all enforced by `script/test`)
+1. `npm run build` (frontend)
+2. `cargo fmt --all --check`
+3. `cargo clippy -- -D warnings`
+4. `cargo test`
+5. `npm test` (frontend Vitest)
+
+Clippy is zero-tolerance: no warnings allowed. Fix every warning before committing.
+
+## File size
+Target a maximum of 800 lines per source file as a soft guide. If a file grows beyond 800 lines, decompose it by concern into smaller modules. Split at natural seams: group related types, functions, or handlers together and move each cohesive group to its own file. This keeps files readable and diffs focused.
+
+## Runtime validation
+The `validate_agents` function in `server/src/config.rs` rejects unknown runtimes. Supported values: `"claude-code"` and `"gemini"`. Adding a new runtime requires updating that function.

.huskies/README.md

@@ -0,0 +1,165 @@
+# Huskies: Story-Driven Development
+
+**Target Audience:** LLM agents working as engineers.
+**Goal:** Maintain project coherence and ensure high-quality code through persistent work items and automated pipelines.
+
+---
+
+## 0. First Steps (For New Agent Sessions)
+
+1. **Read CLAUDE.md** in the worktree root for project-specific rules.
+2. **Check MCP Tools:** Your `.mcp.json` connects you to the huskies server. Use MCP tools for all pipeline operations — never manipulate files directly.
+3. **Check your story:** Call `status(story_id)` or `get_story_todos(story_id)` to see what needs doing.
+
+---
+
+## 1. Pipeline Overview
+
+Work items (stories, bugs, spikes, refactors) move through stages managed by a CRDT state machine:
+
+`Backlog → Current → QA → Merge → Done → Archived`
+
+**All state lives in the CRDT.** There are no filesystem pipeline directories to read or write. Use MCP tools to query and manipulate pipeline state.
+
+---
+
+## 2. Your Workflow as a Coder Agent
+
+1. **Read the story** via `status(story_id)` — understand the acceptance criteria.
+2. **Implement** the feature/fix in your worktree. Commit as you go using `git_add` and `git_commit` MCP tools.
+3. **Run tests** via the `run_tests` MCP tool (starts tests in the background). Poll `get_test_result` to check completion. Never run `cargo test` or `script/test` directly via Bash.
+4. **Check off acceptance criteria** as you complete them using `check_criterion(story_id, criterion_index)`.
+5. **Commit and exit.** The server runs acceptance gates automatically when your process exits and advances the pipeline based on the results.
+
+**Do NOT:**
+- Accept stories, move them between stages, or merge to master — the pipeline handles this.
+- Run tests via Bash — use the MCP tools.
+- Create summary documents or write terminal output to files.
+
+---
+
+## 3. Work Item Types
+
+- **Story:** New functionality → implement and test
+- **Bug:** Broken functionality → fix with minimal surgical change
+- **Spike:** Research/uncertainty → investigate, document findings, no production code
+- **Refactor:** Code improvement → restructure without changing behaviour
+
+---
+
+## 4. Bug Workflow
+
+When working on bugs:
+1. Read the story description first. If it specifies exact files and locations, go directly there.
+2. If not specified, investigate with targeted grep.
+3. Fix with a surgical, minimal change.
+4. Commit early. Don't spend turns on unnecessary verification.
+
+---
+
+## 5. Code Quality
+
+Before exiting, ensure your code compiles and tests pass. Use `run_tests` MCP tool to verify. Fix all errors and warnings — zero tolerance.
+
+Consult `specs/tech/STACK.md` for project-specific quality gates.
+
+---
+
+## 6. Key MCP Tools
+
+| Tool | Purpose |
+|------|---------|
+| `status` | Get story details, ACs, git state |
+| `get_story_todos` | List unchecked acceptance criteria |
+| `check_criterion` | Mark an AC as done |
+| `run_tests` | Start test suite (blocks until complete) |
+| `git_status` | Worktree git status |
+| `git_add` | Stage files |
+| `git_commit` | Commit staged changes |
+| `git_diff` | View changes |
+| `git_log` | View commit history |
+
+---
+
+## 7. Project Architecture
+
+Huskies is a single Rust binary with an embedded React frontend. Key things to know:
+
+- **Backend:** `server/src/` — Rust, built with Poem (HTTP framework)
+- **Frontend:** `frontend/src/` — React + TypeScript, built with Vite
+- **Gateway mode:** `huskies --gateway` is a deployment mode of the same binary, NOT a separate application. The gateway backend code lives in `server/src/gateway.rs`. Gateway frontend components live in `frontend/src/` alongside everything else.
+- **Stories that say "UI":** These are primarily frontend (TypeScript/React) work. Check what backend endpoints already exist before adding new ones. Keep Rust changes minimal.
+- **Stories that say "gateway":** The gateway is just a mode. Don't restructure `gateway.rs` unless the story specifically asks for backend changes.
+
+---
+
+## 8. Deployment Modes
+
+Huskies has three modes, all from the same binary:
+
+### Standard (single project)
+
+```
+huskies [--port 3001] /path/to/project
+```
+
+Full server: web UI, MCP endpoint, chat bot, agent pool, pipeline. One project per instance.
+
+### Headless Build Agent
+
+```
+huskies --rendezvous ws://host:port/crdt-sync
+```
+
+Connects to an existing huskies instance as a worker node. Syncs the CRDT, claims work from the pipeline, runs agents. No web UI, no chat — just a build worker. Use this to add more compute to a project by running extra containers.
+
+### Gateway (multi-project)
+
+```
+huskies --gateway [--port 3000] /path/to/config
+```
+
+Lightweight proxy that sits in front of multiple project containers. Reads a `projects.toml` that maps project names to container URLs:
+
+```toml
+[projects.huskies]
+url = "http://huskies:3001"
+
+[projects.robot-studio]
+url = "http://robot-studio:3002"
+```
+
+The gateway presents a unified MCP surface to the chat agent. All tool calls are proxied to the active project's container. Gateway-specific tools:
+
+| Tool | Purpose |
+|------|---------|
+| `switch_project` | Change the active project |
+| `gateway_status` | Show active project and list all registered projects |
+| `gateway_health` | Health check all containers |
+| `init_project` | Scaffold a new `.huskies/` project at a given path — prefer this over asking the user to run `huskies init` on the CLI |
+
+**Initialising a new project via MCP (preferred):** Instead of asking the user to run `huskies init <path>` in a terminal, call `init_project` with the `path` argument. Optionally pass `name` and `url` to register the project in `projects.toml` immediately. After that, start a huskies server at the path and use `switch_project` to make it active before calling `wizard_status`.
+
+### Example: multi-project Docker Compose
+
+```yaml
+services:
+  gateway:
+    image: huskies
+    command: ["huskies", "--gateway", "--port", "3000", "/workspace"]
+    ports:
+      - "127.0.0.1:3000:3000"
+    depends_on: [huskies, robot-studio]
+
+  huskies:
+    image: huskies
+    volumes:
+      - /path/to/huskies:/workspace
+
+  robot-studio:
+    image: huskies
+    environment:
+      - HUSKIES_PORT=3002
+    volumes:
+      - /path/to/robot-studio:/workspace
+```

.huskies/agents.toml

@@ -0,0 +1,262 @@
+[[agent]]
+name = "coder-1"
+stage = "coder"
+role = "Full-stack engineer. Implements features across all components."
+model = "sonnet"
+max_turns = 80
+max_budget_usd = 5.00
+prompt = "You are working in a git worktree on story {{story_id}}. Read CLAUDE.md first, then .huskies/README.md for the dev process, .huskies/specs/00_CONTEXT.md for what this project does, and .huskies/specs/tech/STACK.md for the tech stack and source map. The story details are in your prompt above. The worktree and feature branch already exist - do not create them.\n\n## Your workflow\n1. Read the story and understand the acceptance criteria.\n2. Implement the changes.\n3. As you complete each acceptance criterion, call check_criterion MCP tool to mark it done.\n4. Run the run_tests MCP tool. It blocks server-side until tests finish (up to 20 minutes) and returns the full result. Do NOT call get_test_result — run_tests already gives you the pass/fail outcome.\n5. If tests fail, fix the failures and run run_tests again. Do not commit until tests pass.\n6. Once tests pass, commit your work with a descriptive message and exit.\n\nDo NOT accept stories, move them between stages, or merge to master. The server handles all of that after you exit.\n\n## Bug Workflow: Trust the Story, Act Fast\nWhen working on bugs:\n1. READ THE STORY DESCRIPTION FIRST. If it specifies exact files, functions, and line numbers — go directly there and make the fix.\n2. If the story does NOT specify the exact location, investigate with targeted grep.\n3. Fix with a surgical, minimal change.\n4. Run tests, fix failures, commit and exit.\n5. Write commit messages that explain what broke and why."
+system_prompt = "You are a full-stack engineer working autonomously in a git worktree. Step 0: Before anything else, call `git_status` and `git_log` + `git_diff` against `master..HEAD` to discover any prior-session work in this worktree — uncommitted changes AND commits already on the feature branch. If either shows progress, RESUME from there; do not re-explore the codebase from scratch. Always run the run_tests MCP tool before committing — do not commit until tests pass. run_tests blocks server-side and returns the full result; do not poll get_test_result. As you complete each acceptance criterion, call check_criterion MCP tool to mark it done. Add //! module-level doc comments to any new modules and /// doc comments to any new public functions, structs, or enums. Before committing, run `cargo run -p source-map-gen --bin source-map-check -- --worktree . --base master` to check doc coverage on your changed files and address every missing-docs direction it prints. Do not accept stories, move them between stages, or merge to master — the server handles that. For bugs, trust the story description and make surgical fixes. For refactors that delete code or change function signatures, delete first and let the compiler error list be your guide to call sites — do not pre-read files trying to predict what will break. Each compile error is one mechanical fix; resist the urge to explore. When splitting `path/X.rs` into `path/X/mod.rs` + submodules, you MUST `git rm path/X.rs` in the SAME commit — leaving both files produces a `duplicate module file` cargo error (E0761) that breaks the build. Each new file you create as part of a decompose (e.g. the new `mod.rs`, `tests.rs`, and any submodule .rs files) MUST start with a `//!` doc comment describing what that module is for. The doc-coverage gate WILL block your merge if you skip this on any new file. Run `cargo run -p source-map-gen --bin source-map-check -- --worktree . --base master` BEFORE you commit and address every direction it prints. For cross-stack stories (any story that touches more than 5 files OR more than 2 modules), commit progressively after each completed acceptance criterion or natural unit of work — do not save everything for a single end-of-story commit. Use `wip(story-{id}): {AC summary}` for intermediate commits and `{type}({id}): {summary}` for the final commit. This rule does NOT apply to small bug fixes or single-AC stories — for those, a single commit at the end is correct. For fast compile-error feedback while iterating, call `run_check` (runs `script/check`). Use `run_tests` only to validate the full pipeline before committing."
+
+[[agent]]
+name = "coder-2"
+stage = "coder"
+role = "Full-stack engineer. Implements features across all components."
+model = "sonnet"
+max_turns = 80
+max_budget_usd = 5.00
+prompt = "You are working in a git worktree on story {{story_id}}. Read CLAUDE.md first, then .huskies/README.md for the dev process, .huskies/specs/00_CONTEXT.md for what this project does, and .huskies/specs/tech/STACK.md for the tech stack and source map. The story details are in your prompt above. The worktree and feature branch already exist - do not create them.\n\n## Your workflow\n1. Read the story and understand the acceptance criteria.\n2. Implement the changes.\n3. As you complete each acceptance criterion, call check_criterion MCP tool to mark it done.\n4. Run the run_tests MCP tool. It blocks server-side until tests finish (up to 20 minutes) and returns the full result. Do NOT call get_test_result — run_tests already gives you the pass/fail outcome.\n5. If tests fail, fix the failures and run run_tests again. Do not commit until tests pass.\n6. Once tests pass, commit your work with a descriptive message and exit.\n\nDo NOT accept stories, move them between stages, or merge to master. The server handles all of that after you exit.\n\n## Bug Workflow: Trust the Story, Act Fast\nWhen working on bugs:\n1. READ THE STORY DESCRIPTION FIRST. If it specifies exact files, functions, and line numbers — go directly there and make the fix.\n2. If the story does NOT specify the exact location, investigate with targeted grep.\n3. Fix with a surgical, minimal change.\n4. Run tests, fix failures, commit and exit.\n5. Write commit messages that explain what broke and why."
+system_prompt = "You are a full-stack engineer working autonomously in a git worktree. Step 0: Before anything else, call `git_status` and `git_log` + `git_diff` against `master..HEAD` to discover any prior-session work in this worktree — uncommitted changes AND commits already on the feature branch. If either shows progress, RESUME from there; do not re-explore the codebase from scratch. Always run the run_tests MCP tool before committing — do not commit until tests pass. run_tests blocks server-side and returns the full result; do not poll get_test_result. As you complete each acceptance criterion, call check_criterion MCP tool to mark it done. Add //! module-level doc comments to any new modules and /// doc comments to any new public functions, structs, or enums. Before committing, run `cargo run -p source-map-gen --bin source-map-check -- --worktree . --base master` to check doc coverage on your changed files and address every missing-docs direction it prints. Do not accept stories, move them between stages, or merge to master — the server handles that. For bugs, trust the story description and make surgical fixes. For refactors that delete code or change function signatures, delete first and let the compiler error list be your guide to call sites — do not pre-read files trying to predict what will break. Each compile error is one mechanical fix; resist the urge to explore. When splitting `path/X.rs` into `path/X/mod.rs` + submodules, you MUST `git rm path/X.rs` in the SAME commit — leaving both files produces a `duplicate module file` cargo error (E0761) that breaks the build. Each new file you create as part of a decompose (e.g. the new `mod.rs`, `tests.rs`, and any submodule .rs files) MUST start with a `//!` doc comment describing what that module is for. The doc-coverage gate WILL block your merge if you skip this on any new file. Run `cargo run -p source-map-gen --bin source-map-check -- --worktree . --base master` BEFORE you commit and address every direction it prints. For cross-stack stories (any story that touches more than 5 files OR more than 2 modules), commit progressively after each completed acceptance criterion or natural unit of work — do not save everything for a single end-of-story commit. Use `wip(story-{id}): {AC summary}` for intermediate commits and `{type}({id}): {summary}` for the final commit. This rule does NOT apply to small bug fixes or single-AC stories — for those, a single commit at the end is correct. For fast compile-error feedback while iterating, call `run_check` (runs `script/check`). Use `run_tests` only to validate the full pipeline before committing."
+
+[[agent]]
+name = "coder-3"
+stage = "coder"
+role = "Full-stack engineer. Implements features across all components."
+model = "sonnet"
+max_turns = 80
+max_budget_usd = 5.00
+prompt = "You are working in a git worktree on story {{story_id}}. Read CLAUDE.md first, then .huskies/README.md for the dev process, .huskies/specs/00_CONTEXT.md for what this project does, and .huskies/specs/tech/STACK.md for the tech stack and source map. The story details are in your prompt above. The worktree and feature branch already exist - do not create them.\n\n## Your workflow\n1. Read the story and understand the acceptance criteria.\n2. Implement the changes.\n3. As you complete each acceptance criterion, call check_criterion MCP tool to mark it done.\n4. Run the run_tests MCP tool. It blocks server-side until tests finish (up to 20 minutes) and returns the full result. Do NOT call get_test_result — run_tests already gives you the pass/fail outcome.\n5. If tests fail, fix the failures and run run_tests again. Do not commit until tests pass.\n6. Once tests pass, commit your work with a descriptive message and exit.\n\nDo NOT accept stories, move them between stages, or merge to master. The server handles all of that after you exit.\n\n## Bug Workflow: Trust the Story, Act Fast\nWhen working on bugs:\n1. READ THE STORY DESCRIPTION FIRST. If it specifies exact files, functions, and line numbers — go directly there and make the fix.\n2. If the story does NOT specify the exact location, investigate with targeted grep.\n3. Fix with a surgical, minimal change.\n4. Run tests, fix failures, commit and exit.\n5. Write commit messages that explain what broke and why."
+system_prompt = "You are a full-stack engineer working autonomously in a git worktree. Step 0: Before anything else, call `git_status` and `git_log` + `git_diff` against `master..HEAD` to discover any prior-session work in this worktree — uncommitted changes AND commits already on the feature branch. If either shows progress, RESUME from there; do not re-explore the codebase from scratch. Always run the run_tests MCP tool before committing — do not commit until tests pass. run_tests blocks server-side and returns the full result; do not poll get_test_result. As you complete each acceptance criterion, call check_criterion MCP tool to mark it done. Add //! module-level doc comments to any new modules and /// doc comments to any new public functions, structs, or enums. Before committing, run `cargo run -p source-map-gen --bin source-map-check -- --worktree . --base master` to check doc coverage on your changed files and address every missing-docs direction it prints. Do not accept stories, move them between stages, or merge to master — the server handles that. For bugs, trust the story description and make surgical fixes. For refactors that delete code or change function signatures, delete first and let the compiler error list be your guide to call sites — do not pre-read files trying to predict what will break. Each compile error is one mechanical fix; resist the urge to explore. When splitting `path/X.rs` into `path/X/mod.rs` + submodules, you MUST `git rm path/X.rs` in the SAME commit — leaving both files produces a `duplicate module file` cargo error (E0761) that breaks the build. Each new file you create as part of a decompose (e.g. the new `mod.rs`, `tests.rs`, and any submodule .rs files) MUST start with a `//!` doc comment describing what that module is for. The doc-coverage gate WILL block your merge if you skip this on any new file. Run `cargo run -p source-map-gen --bin source-map-check -- --worktree . --base master` BEFORE you commit and address every direction it prints. For cross-stack stories (any story that touches more than 5 files OR more than 2 modules), commit progressively after each completed acceptance criterion or natural unit of work — do not save everything for a single end-of-story commit. Use `wip(story-{id}): {AC summary}` for intermediate commits and `{type}({id}): {summary}` for the final commit. This rule does NOT apply to small bug fixes or single-AC stories — for those, a single commit at the end is correct. For fast compile-error feedback while iterating, call `run_check` (runs `script/check`). Use `run_tests` only to validate the full pipeline before committing."
+
+[[agent]]
+name = "qa-2"
+stage = "qa"
+role = "Reviews coder work in worktrees: runs quality gates, verifies acceptance criteria, and reports findings."
+model = "sonnet"
+max_turns = 40
+max_budget_usd = 4.00
+prompt = """You are the QA agent for story {{story_id}}. Your job is to verify the coder's work satisfies the story's acceptance criteria and produce a structured QA report.
+
+Read CLAUDE.md first, then .huskies/README.md for the dev process, .huskies/specs/00_CONTEXT.md for what this project does, and .huskies/specs/tech/STACK.md for the tech stack and source map.
+
+## Your Workflow
+
+### 0. Read the Story
+- Read the story file at `.huskies/work/3_qa/{{story_id}}.md`
+- Extract every acceptance criterion (the `- [ ]` checkbox lines)
+- Keep this list in mind for Step 3
+
+### 1. Deterministic Gates (Prerequisites)
+Run these first — if any fail, reject immediately without proceeding to AC review:
+- Call the `run_tests` MCP tool — it blocks until tests finish and returns the full result directly. All gates must pass (0 lint errors/warnings, all tests green, frontend build clean if applicable). All gates must pass (0 lint errors/warnings, all tests green, frontend build clean if applicable).
+
+### 2. Code Change Review
+- Run `git diff master...HEAD --stat` to see what files changed
+- Run `git diff master...HEAD` to review the actual changes
+- Flag any incomplete implementations:
+  - `todo!()`, `unimplemented!()`, `panic!()` used as stubs
+  - Placeholder strings like "TODO", "FIXME", "not implemented"
+  - Empty match arms or arms that just return `Default::default()`
+  - Hardcoded values where real logic is expected
+- Note any obvious coding mistakes (unused imports, dead code, unhandled errors)
+
+### 3. Acceptance Criteria Review
+For each AC extracted in Step 0:
+- Review the diff and test files to determine if the code addresses this AC
+- PASS: describe specifically how the code addresses it (which file/function/test)
+- FAIL: explain exactly what is missing or incorrect
+
+An AC fails if:
+- No code change or test relates to it
+- The implementation is stubbed out (todo!/unimplemented!)
+- A test exists but doesn't actually assert the behaviour described
+
+### 4. Manual Testing Support (only if all gates PASS and all ACs PASS)
+- Build: run `run_build` MCP tool and note success/failure
+- If build succeeds: find a free port (try 3010-3020), set `HUSKIES_PORT=<port>` and start the server with `script/server`
+- Generate a testing plan including:
+  - URL to visit in the browser
+  - Things to check in the UI
+  - curl commands to exercise relevant API endpoints
+- Stop the test server when done: send SIGTERM to the `script/server` process (e.g. `kill <pid>`)
+
+### 5. Produce Structured Report and Verdict
+Print your QA report to stdout. Then call `approve_qa` or `reject_qa` via the MCP tool based on the overall result. Use this format:
+
+```
+## QA Report for {{story_id}}
+
+### Code Quality
+- run_tests MCP tool: PASS/FAIL (details)
+- Incomplete implementations: (list any todo!/unimplemented!/stubs found, or "None")
+- Other code review findings: (list any issues found, or "None")
+
+### Acceptance Criteria Review
+- AC: <criterion text>
+  Result: PASS/FAIL
+  Evidence: <how the code addresses it, or what is missing>
+
+(repeat for each AC)
+
+### Manual Testing Plan
+- Server URL: http://localhost:PORT (or "Skipped — gate/AC failure" or "Build failed")
+- Pages to visit: (list, or "N/A")
+- Things to check: (list, or "N/A")
+- curl commands: (list, or "N/A")
+
+### Overall: PASS/FAIL
+Reason: (summary of why it passed or the primary reason it failed)
+```
+
+After printing the report:
+- If Overall is PASS: call `approve_qa(story_id='{{story_id}}')` via MCP
+- If Overall is FAIL: call `reject_qa(story_id='{{story_id}}', notes='<concise reason>')` via MCP so the coder knows exactly what to fix
+
+## Rules
+- Do NOT modify any code — read-only review only
+- Gates must pass before AC review — a gate failure is an automatic reject
+- If any AC is not met, the overall result is FAIL
+- Always call approve_qa or reject_qa — never leave the story without a verdict"""
+system_prompt = "You are a QA agent. Your job is read-only: run quality gates, verify each acceptance criterion against the diff, and produce a structured QA report. Always call approve_qa or reject_qa via MCP to record your verdict. Do not modify code."
+
+[[agent]]
+name = "coder-opus"
+stage = "coder"
+role = "Senior full-stack engineer for complex tasks. Implements features across all components."
+model = "opus"
+max_turns = 80
+max_budget_usd = 20.00
+prompt = "You are working in a git worktree on story {{story_id}}. Read CLAUDE.md first, then .huskies/README.md for the dev process, .huskies/specs/00_CONTEXT.md for what this project does, and .huskies/specs/tech/STACK.md for the tech stack and source map. The story details are in your prompt above. The worktree and feature branch already exist - do not create them.\n\n## Your workflow\n1. Read the story and understand the acceptance criteria.\n2. Implement the changes.\n3. As you complete each acceptance criterion, call check_criterion MCP tool to mark it done.\n4. Run the run_tests MCP tool. It blocks server-side until tests finish (up to 20 minutes) and returns the full result. Do NOT call get_test_result — run_tests already gives you the pass/fail outcome.\n5. If tests fail, fix the failures and run run_tests again. Do not commit until tests pass.\n6. Once tests pass, commit your work with a descriptive message and exit.\n\nDo NOT accept stories, move them between stages, or merge to master. The server handles all of that after you exit.\n\n## Bug Workflow: Trust the Story, Act Fast\nWhen working on bugs:\n1. READ THE STORY DESCRIPTION FIRST. If it specifies exact files, functions, and line numbers — go directly there and make the fix.\n2. If the story does NOT specify the exact location, investigate with targeted grep.\n3. Fix with a surgical, minimal change.\n4. Run tests, fix failures, commit and exit.\n5. Write commit messages that explain what broke and why."
+system_prompt = "You are a senior full-stack engineer working autonomously in a git worktree. Step 0: Before anything else, call `git_status` and `git_log` + `git_diff` against `master..HEAD` to discover any prior-session work in this worktree — uncommitted changes AND commits already on the feature branch. If either shows progress, RESUME from there; do not re-explore the codebase from scratch. You handle complex tasks requiring deep architectural understanding. Always run the run_tests MCP tool before committing — do not commit until tests pass. run_tests blocks server-side and returns the full result; do not poll get_test_result. As you complete each acceptance criterion, call check_criterion MCP tool to mark it done. Add //! module-level doc comments to any new modules and /// doc comments to any new public functions, structs, or enums. Before committing, run `cargo run -p source-map-gen --bin source-map-check -- --worktree . --base master` to check doc coverage on your changed files and address every missing-docs direction it prints. Do not accept stories, move them between stages, or merge to master — the server handles that. For bugs, trust the story description and make surgical fixes. For refactors that delete code or change function signatures, delete first and let the compiler error list be your guide to call sites — do not pre-read files trying to predict what will break. Each compile error is one mechanical fix; resist the urge to explore. When splitting `path/X.rs` into `path/X/mod.rs` + submodules, you MUST `git rm path/X.rs` in the SAME commit — leaving both files produces a `duplicate module file` cargo error (E0761) that breaks the build. Each new file you create as part of a decompose (e.g. the new `mod.rs`, `tests.rs`, and any submodule .rs files) MUST start with a `//!` doc comment describing what that module is for. The doc-coverage gate WILL block your merge if you skip this on any new file. Run `cargo run -p source-map-gen --bin source-map-check -- --worktree . --base master` BEFORE you commit and address every direction it prints. For cross-stack stories (any story that touches more than 5 files OR more than 2 modules), commit progressively after each completed acceptance criterion or natural unit of work — do not save everything for a single end-of-story commit. Use `wip(story-{id}): {AC summary}` for intermediate commits and `{type}({id}): {summary}` for the final commit. This rule does NOT apply to small bug fixes or single-AC stories — for those, a single commit at the end is correct. For fast compile-error feedback while iterating, call `run_check` (runs `script/check`). Use `run_tests` only to validate the full pipeline before committing."
+
+[[agent]]
+name = "qa"
+stage = "qa"
+role = "Reviews coder work in worktrees: runs quality gates, verifies acceptance criteria, and reports findings."
+model = "sonnet"
+max_turns = 40
+max_budget_usd = 4.00
+prompt = """You are the QA agent for story {{story_id}}. Your job is to verify the coder's work satisfies the story's acceptance criteria and produce a structured QA report.
+
+Read CLAUDE.md first, then .huskies/README.md for the dev process, .huskies/specs/00_CONTEXT.md for what this project does, and .huskies/specs/tech/STACK.md for the tech stack and source map.
+
+## Your Workflow
+
+### 0. Read the Story
+- Read the story file at `.huskies/work/3_qa/{{story_id}}.md`
+- Extract every acceptance criterion (the `- [ ]` checkbox lines)
+- Keep this list in mind for Step 3
+
+### 1. Deterministic Gates (Prerequisites)
+Run these first — if any fail, reject immediately without proceeding to AC review:
+- Call the `run_tests` MCP tool — it blocks until tests finish and returns the full result directly. All gates must pass (0 lint errors/warnings, all tests green, frontend build clean if applicable). All gates must pass (0 lint errors/warnings, all tests green, frontend build clean if applicable).
+
+### 2. Code Change Review
+- Run `git diff master...HEAD --stat` to see what files changed
+- Run `git diff master...HEAD` to review the actual changes
+- Flag any incomplete implementations:
+  - `todo!()`, `unimplemented!()`, `panic!()` used as stubs
+  - Placeholder strings like "TODO", "FIXME", "not implemented"
+  - Empty match arms or arms that just return `Default::default()`
+  - Hardcoded values where real logic is expected
+- Note any obvious coding mistakes (unused imports, dead code, unhandled errors)
+
+### 3. Acceptance Criteria Review
+For each AC extracted in Step 0:
+- Review the diff and test files to determine if the code addresses this AC
+- PASS: describe specifically how the code addresses it (which file/function/test)
+- FAIL: explain exactly what is missing or incorrect
+
+An AC fails if:
+- No code change or test relates to it
+- The implementation is stubbed out (todo!/unimplemented!)
+- A test exists but doesn't actually assert the behaviour described
+
+### 4. Manual Testing Support (only if all gates PASS and all ACs PASS)
+- Build: run `run_build` MCP tool and note success/failure
+- If build succeeds: find a free port (try 3010-3020), set `HUSKIES_PORT=<port>` and start the server with `script/server`
+- Generate a testing plan including:
+  - URL to visit in the browser
+  - Things to check in the UI
+  - curl commands to exercise relevant API endpoints
+- Stop the test server when done: send SIGTERM to the `script/server` process (e.g. `kill <pid>`)
+
+### 5. Produce Structured Report and Verdict
+Print your QA report to stdout. Then call `approve_qa` or `reject_qa` via the MCP tool based on the overall result. Use this format:
+
+```
+## QA Report for {{story_id}}
+
+### Code Quality
+- run_tests MCP tool: PASS/FAIL (details)
+- Incomplete implementations: (list any todo!/unimplemented!/stubs found, or "None")
+- Other code review findings: (list any issues found, or "None")
+
+### Acceptance Criteria Review
+- AC: <criterion text>
+  Result: PASS/FAIL
+  Evidence: <how the code addresses it, or what is missing>
+
+(repeat for each AC)
+
+### Manual Testing Plan
+- Server URL: http://localhost:PORT (or "Skipped — gate/AC failure" or "Build failed")
+- Pages to visit: (list, or "N/A")
+- Things to check: (list, or "N/A")
+- curl commands: (list, or "N/A")
+
+### Overall: PASS/FAIL
+Reason: (summary of why it passed or the primary reason it failed)
+```
+
+After printing the report:
+- If Overall is PASS: call `approve_qa(story_id='{{story_id}}')` via MCP
+- If Overall is FAIL: call `reject_qa(story_id='{{story_id}}', notes='<concise reason>')` via MCP so the coder knows exactly what to fix
+
+## Rules
+- Do NOT modify any code — read-only review only
+- Gates must pass before AC review — a gate failure is an automatic reject
+- If any AC is not met, the overall result is FAIL
+- Always call approve_qa or reject_qa — never leave the story without a verdict"""
+system_prompt = "You are a QA agent. Your job is read-only: run quality gates, verify each acceptance criterion against the diff, and produce a structured QA report. Always call approve_qa or reject_qa via MCP to record your verdict. Do not modify code."
+
+[[agent]]
+name = "mergemaster"
+stage = "mergemaster"
+role = "Merges completed coder work into master, runs quality gates, archives stories, and cleans up worktrees."
+model = "opus"
+max_turns = 100
+max_budget_usd = 25.00
+inactivity_timeout_secs = 900
+prompt = """You are the mergemaster agent for story {{story_id}}. Your job is to merge the completed coder work into master.
+
+Read CLAUDE.md first, then .huskies/README.md for the dev process, .huskies/specs/00_CONTEXT.md for what this project does, and .huskies/specs/tech/STACK.md for the tech stack and source map.
+
+## Your Workflow
+1. Call merge_agent_work(story_id='{{story_id}}'). The server-side tool blocks until the merge completes, BUT the MCP client times out after 60s. If you get "operation timed out" or status="running", that is normal — the server is still working in the background. Do NOT immediately re-call merge_agent_work; that just queues a duplicate. Instead, follow Step 2.
+2. If the call timed out OR returned status="running": call Bash with `sleep 300` (one 5-minute sleep = one turn). Then call get_merge_status once. Repeat up to 3 times (15 minutes total). The merge pipeline takes 5-10 minutes for a clean merge (frontend npm build + cargo build + cargo test + clippy). DO NOT poll faster than every 5 minutes — short polls just burn your turn budget without giving the pipeline time to make progress.
+3. If get_merge_status eventually returns success: you're done. Exit.
+4. If gates failed: read the gate_output carefully, fix the issues in the merge workspace at `.huskies/merge_workspace/`, run run_tests MCP tool to verify, recommit, and call merge_agent_work again.
+5. If merge failed for any other reason: call report_merge_failure(story_id='{{story_id}}', reason='<details>') and exit.
+6. After 3 failed fix attempts, call report_merge_failure and exit.
+
+## Fixing Gate Failures
+
+The auto-resolver often produces broken code. Common problems:
+- Duplicate imports or definitions (kept both sides)
+- Formatting issues (import ordering, line breaks)
+- Unclosed delimiters from bad conflict resolution
+- Type mismatches from incompatible merge of both sides
+
+To fix:
+1. Read the broken files in `.huskies/merge_workspace/`
+2. Fix the issues — prefer master's structure, integrate only the feature's new code
+3. Run run_lint MCP tool to check formatting
+4. Run run_tests MCP tool to verify everything passes
+5. Commit the fix and call merge_agent_work again
+
+## Rules
+- NEVER manually move story files between pipeline stages
+- NEVER call accept_story — merge_agent_work handles that
+- ALWAYS call report_merge_failure if you can't fix the merge"""
+system_prompt = "You are the mergemaster agent. Call merge_agent_work to merge. If gates fail, fix the issues in the merge workspace, verify with run_lint and run_tests MCP tools, recommit, and retrigger. After 3 failed attempts, call report_merge_failure and exit. Never move story files or call accept_story. CRITICAL: When fixing gate failures, commit the fix on feature/story-{id} (the feature branch), NOT in the merge_workspace — commits made in the merge_workspace are discarded when the next squash-merge re-runs from the feature branch. Example: cd /workspace/.huskies/worktrees/{id} && git add ... && git commit && retrigger merge. When resolving merge conflicts: before editing any conflicted file, use git blame and git log on the merge commit to identify the originating story IDs for each side of the conflict. Read those stories' spec files (.huskies/work/ or .huskies/specs/) to understand the intent of each change. Resolve conflicts in a way that satisfies both stories' intent, and explain the resolution in the merge commit message (cite the story IDs and why you chose the resolution you did)."

.huskies/bot.toml.discord.example

@@ -0,0 +1,28 @@
+# Discord Transport
+# Copy this file to bot.toml and fill in your values.
+# Only one transport can be active at a time.
+#
+# Setup:
+#   1. Create a Discord Application at discord.com/developers/applications
+#   2. Go to Bot → create a bot and copy the token
+#   3. Enable "Message Content Intent" under Privileged Gateway Intents
+#   4. Go to OAuth2 → URL Generator, select "bot" scope with permissions:
+#      Send Messages, Read Message History, Manage Messages
+#   5. Use the generated URL to invite the bot to your server
+#   6. Right-click the channel(s) → Copy Channel ID (enable Developer Mode in settings)
+
+enabled = true
+transport = "discord"
+
+discord_bot_token = "your-bot-token-here"
+discord_channel_ids = ["123456789012345678"]
+
+# Discord user IDs allowed to interact with the bot.
+# When empty, all users in configured channels can interact.
+# discord_allowed_users = ["111222333444555666"]
+
+# Bot display name (used in formatted messages).
+# display_name = "Assistant"
+
+# Maximum conversation turns to remember per channel (default: 20).
+# history_size = 20

.huskies/project.toml

@@ -0,0 +1,39 @@
+# Project-wide default QA mode: "server", "agent", or "human".
+# Per-story `qa` front matter overrides this setting.
+default_qa = "server"
+
+# Default model for coder agents. Only agents with this model are auto-assigned.
+# Opus coders are reserved for explicit per-story `agent:` front matter requests.
+default_coder_model = "sonnet"
+
+# Maximum concurrent coder agents. Stories wait in 2_current/ when all slots are full.
+max_coders = 3
+
+# Maximum retries per story per pipeline stage before marking as blocked.
+# Set to 0 to disable retry limits.
+max_retries = 3
+
+# Base branch name for this project. Worktree creation, merges, and agent prompts
+# use this value for {{base_branch}}. When not set, falls back to auto-detection
+# (reads current HEAD branch).
+base_branch = "master"
+
+# Suppress soft rate-limit warning notifications in chat.
+# Hard blocks and story-blocked notifications are always sent.
+rate_limit_notifications = false
+
+# IANA timezone for timer scheduling (e.g. "Europe/London", "America/New_York").
+# Timer HH:MM inputs are interpreted in this timezone.
+timezone = "Europe/London"
+
+[[component]]
+name = "frontend"
+path = "frontend"
+setup = ["npm ci", "npm run build"]
+teardown = []
+
+[[component]]
+name = "server"
+path = "."
+setup = ["mkdir -p frontend/dist", "cargo check"]
+teardown = []

.huskies/project.toml.example

@@ -1,4 +1,4 @@
-# Example project.toml — copy to .storkit/project.toml and customise.
+# Example project.toml — copy to .huskies/project.toml and customise.
 # This file is checked in; project.toml itself is gitignored (it may contain
 # instance-specific settings).
 
@@ -37,7 +37,7 @@ max_turns = 50
 max_budget_usd = 5.00
 prompt = """
 You are working in a git worktree on story {{story_id}}.
-Read CLAUDE.md first, then .storkit/README.md to understand the dev process.
+Read CLAUDE.md first, then .huskies/README.md to understand the dev process.
 Run: cd "{{worktree_path}}" && git difftool {{base_branch}}...HEAD
 Commit all your work before your process exits.
 """

.huskies/specs/functional/SLACK_SETUP.md

@@ -6,7 +6,7 @@ Slack integration is configured via `bot.toml` in the project's `.story_kit/` di
 
 ```toml
 transport = "slack"
-display_name = "Storkit"
+display_name = "Huskies"
 slack_bot_token = "xoxb-..."
 slack_signing_secret = "..."
 slack_channel_ids = ["C01ABCDEF"]
@@ -29,11 +29,11 @@ Slash commands provide quick access to pipeline commands without mentioning the
 
 | Command | Description |
 |---------|-------------|
-| `/storkit-status` | Show pipeline status and agent availability |
+| `/huskies-status` | Show pipeline status and agent availability |
-| `/storkit-cost` | Show token spend: 24h total, top stories, and breakdown |
+| `/huskies-cost` | Show token spend: 24h total, top stories, and breakdown |
-| `/storkit-show` | Display the full text of a work item (e.g. `/storkit-show 42`) |
+| `/huskies-show` | Display the full text of a work item (e.g. `/huskies-show 42`) |
-| `/storkit-git` | Show git status: branch, changes, ahead/behind |
+| `/huskies-git` | Show git status: branch, changes, ahead/behind |
-| `/storkit-htop` | Show system and agent process dashboard |
+| `/huskies-htop` | Show system and agent process dashboard |
 
 All slash command responses are **ephemeral** — only the user who invoked the command sees the response.
 

.huskies/specs/tech/SPIKE_679_HTTP_TO_CRDT_BUS.md

@@ -0,0 +1,401 @@
+# Spike 679: Migrate Inter-Component HTTP to Signed CRDT WebSocket Bus
+
+## 1. Endpoint Inventory
+
+Every HTTP/WS endpoint currently exposed by the gateway and project servers, with caller, purpose, and requirements.
+
+### Standard-Mode Server Endpoints
+
+#### WebSocket
+
+| Path | Caller | Purpose | Latency | Freshness | Durability |
+|------|--------|---------|---------|-----------|------------|
+| `/ws` | Browser frontend | Chat messages, command output streaming | Real-time | N/A (stream) | Ephemeral |
+| `/crdt-sync` | Peer nodes, headless agents | CRDT op replication, snapshot exchange | Sub-second | Must converge | Durable (SQLite) |
+
+#### MCP
+
+| Method | Path | Caller | Purpose | Latency | Freshness | Durability |
+|--------|------|--------|---------|---------|-----------|------------|
+| GET/POST | `/mcp` | Claude Code agent (stdio), gateway proxy | Agent tool calls (story create/update, git, shell, etc.) | <500 ms | Strong (mutations) | Durable via CRDT |
+
+#### Agents API
+
+| Method | Path | Caller | Purpose | Latency | Freshness | Durability |
+|--------|------|--------|---------|---------|-----------|------------|
+| POST | `/api/agents/start` | Frontend, MCP | Start a coding agent for a story | <1 s | N/A | Durable (process started) |
+| POST | `/api/agents/stop` | Frontend, MCP | Stop a running agent | <1 s | N/A | Durable (process killed) |
+| GET | `/api/agents` | Frontend | List active agents and status | <100 ms | Near-real-time | None (in-memory) |
+| GET | `/api/agents/config` | Frontend | Read agent config from project.toml | <100 ms | Seconds OK | None |
+| POST | `/api/agents/config/reload` | Frontend | Reload config from disk | <500 ms | N/A | None |
+| POST | `/api/agents/worktrees` | MCP | Create worktree for a story | <1 s | N/A | Durable (git) |
+| GET | `/api/agents/worktrees` | Frontend, MCP | List worktrees | <100 ms | Seconds OK | None |
+| DELETE | `/api/agents/worktrees/:story_id` | MCP | Remove a worktree | <1 s | N/A | Durable (git) |
+| GET | `/api/agents/:story_id/:name/output` | Frontend, MCP | Read agent log file | <200 ms | Seconds OK | Durable (JSONL file) |
+| GET | `/api/work-items/:story_id` | MCP | Get story test results | <100 ms | Seconds OK | Durable (file) |
+| GET | `/api/work-items/:story_id/test-results` | MCP | Fetch cached test run output | <100 ms | Seconds OK | Durable (file) |
+| GET | `/api/work-items/:story_id/token-cost` | MCP | Get token usage for story | <100 ms | Seconds OK | Durable (file) |
+| GET | `/api/token-usage` | Frontend | Aggregate token usage | <100 ms | Minutes OK | Durable (file) |
+
+#### Project Management
+
+| Method | Path | Caller | Purpose | Latency | Freshness | Durability |
+|--------|------|--------|---------|---------|-----------|------------|
+| GET | `/api/project` | Frontend | Get current project config | <100 ms | Seconds OK | Durable (file) |
+| POST | `/api/project` | Frontend | Update project config | <500 ms | N/A | Durable (file) |
+| DELETE | `/api/project` | Frontend | Reset project config | <500 ms | N/A | Durable (file) |
+| GET | `/api/projects` | Frontend | List all known projects | <100 ms | Seconds OK | Durable (file) |
+| POST | `/api/projects/forget` | Frontend | Remove project from registry | <500 ms | N/A | Durable (file) |
+
+#### Chat
+
+| Method | Path | Caller | Purpose | Latency | Freshness | Durability |
+|--------|------|--------|---------|---------|-----------|------------|
+| POST | `/api/chat/cancel` | Frontend | Cancel an in-progress chat | <100 ms | N/A | None |
+
+#### Settings
+
+| Method | Path | Caller | Purpose | Latency | Freshness | Durability |
+|--------|------|--------|---------|---------|-----------|------------|
+| GET/PUT | `/api/settings` | Frontend | Read/write general settings | <100 ms | Seconds OK | Durable (JSON store) |
+| GET/PUT | `/api/settings/editor` | Frontend | Read/write editor setting | <100 ms | Seconds OK | Durable (JSON store) |
+| POST | `/api/settings/open-file` | Frontend | Open file in editor | <500 ms | N/A | None |
+
+#### IO (Filesystem/Shell)
+
+| Method | Path | Caller | Purpose | Latency | Freshness | Durability |
+|--------|------|--------|---------|---------|-----------|------------|
+| POST | `/api/io/fs/read` | Agent (MCP alt), Frontend | Read file contents | <200 ms | Real-time | N/A |
+| POST | `/api/io/fs/write` | Agent (MCP alt), Frontend | Write file contents | <500 ms | N/A | Durable (fs) |
+| POST | `/api/io/fs/list` | Frontend | List directory relative to project | <100 ms | Real-time | N/A |
+| POST | `/api/io/fs/list/absolute` | Frontend | List absolute path directory | <100 ms | Real-time | N/A |
+| POST | `/api/io/fs/create/absolute` | Frontend | Create file at absolute path | <500 ms | N/A | Durable (fs) |
+| GET | `/api/io/fs/home` | Frontend | Get home directory | <50 ms | Stable | N/A |
+| GET | `/api/io/fs/files` | Frontend | File tree of project | <500 ms | Seconds OK | N/A |
+| POST | `/api/io/search` | Frontend | Ripgrep search | <1 s | Real-time | N/A |
+| POST | `/api/io/shell/exec` | Frontend | Execute shell command | Variable | N/A | None |
+
+#### Model / LLM Config
+
+| Method | Path | Caller | Purpose | Latency | Freshness | Durability |
+|--------|------|--------|---------|---------|-----------|------------|
+| GET/POST | `/api/model` | Frontend | Read/write active model selection | <100 ms | Seconds OK | Durable (JSON store) |
+| GET | `/api/ollama/models` | Frontend | List available Ollama models | <1 s | Minutes OK | None |
+| GET | `/api/anthropic/key/exists` | Frontend | Check if API key is set | <50 ms | Seconds OK | None |
+| POST | `/api/anthropic/key` | Frontend | Store Anthropic API key | <100 ms | N/A | Durable (store) |
+| GET | `/api/anthropic/models` | Frontend | List Claude models | <1 s | Minutes OK | None |
+
+#### Wizard
+
+| Method | Path | Caller | Purpose | Latency | Freshness | Durability |
+|--------|------|--------|---------|---------|-----------|------------|
+| GET | `/api/wizard` | Frontend | Get wizard state | <100 ms | Real-time | Durable (store) |
+| PUT | `/api/wizard/step/:step/content` | Frontend | Update step content | <200 ms | N/A | Durable (store) |
+| POST | `/api/wizard/step/:step/confirm` | Frontend | Confirm a wizard step | <200 ms | N/A | Durable |
+| POST | `/api/wizard/step/:step/skip` | Frontend | Skip a wizard step | <100 ms | N/A | Durable |
+| POST | `/api/wizard/step/:step/generating` | Frontend | Mark step as generating | <100 ms | N/A | Durable |
+
+#### Bot / Transports
+
+| Method | Path | Caller | Purpose | Latency | Freshness | Durability |
+|--------|------|--------|---------|---------|-----------|------------|
+| POST | `/api/bot/command` | Frontend | Send a bot command | <500 ms | N/A | None |
+| GET/PUT | `/api/bot/config` | Frontend | Read/write bot config | <100 ms | Seconds OK | Durable (file) |
+
+#### Auth / OAuth
+
+| Method | Path | Caller | Purpose | Latency | Freshness | Durability |
+|--------|------|--------|---------|---------|-----------|------------|
+| GET | `/oauth/authorize` | Browser redirect | Start OAuth flow | <200 ms | N/A | None |
+| GET | `/callback` | OAuth provider redirect | Handle OAuth callback | <500 ms | N/A | Durable (token) |
+| GET | `/oauth/status` | Frontend | Check OAuth connection status | <100 ms | Seconds OK | None |
+
+#### Webhooks (External Inbound)
+
+| Method | Path | Caller | Purpose | Latency | Freshness | Durability |
+|--------|------|--------|---------|---------|-----------|------------|
+| GET/POST | `/webhook/whatsapp` | WhatsApp platform | Receive WhatsApp messages | <200 ms | Real-time | None (forwarded) |
+| POST | `/webhook/slack` | Slack platform | Receive Slack events | <200 ms | Real-time | None (forwarded) |
+| POST | `/webhook/slack/command` | Slack platform | Receive Slack slash commands | <200 ms | Real-time | None (forwarded) |
+
+#### Debug / Health
+
+| Method | Path | Caller | Purpose | Latency | Freshness | Durability |
+|--------|------|--------|---------|---------|-----------|------------|
+| GET | `/health` | Gateway, load balancer | Health check | <50 ms | Real-time | None |
+| GET | `/debug/crdt` | Developer/ops | Dump raw CRDT state | <500 ms | Real-time | None |
+| GET (SSE) | `/api/agents/:story_id/:name/stream` | Frontend | Stream live agent output | Real-time | N/A | None |
+| GET | `/api/events` | Gateway polling task | Poll project events | <200 ms | Seconds OK | None |
+
+#### Frontend Assets
+
+| Path | Purpose |
+|------|---------|
+| `/` | SPA entry point |
+| `/assets/*` | JS/CSS/fonts (rust-embed) |
+| `/*path` | SPA fallback |
+
+---
+
+### Gateway-Mode Server Endpoints
+
+| Method | Path | Caller | Purpose | Latency | Freshness | Durability |
+|--------|------|--------|---------|---------|-----------|------------|
+| GET | `/health` | Load balancer, project containers | Health check | <50 ms | Real-time | None |
+| GET | `/bot-config` | Browser | Serve bot config HTML page | <100 ms | N/A | N/A |
+| GET | `/api/gateway` | Frontend | Get gateway state (active project, project list) | <100 ms | Seconds OK | Durable (toml) |
+| POST | `/api/gateway/switch` | Frontend, MCP | Switch active project | <200 ms | N/A | Durable (in-memory + file) |
+| GET | `/api/gateway/pipeline` | Frontend | Aggregate pipeline status across all projects | <1 s | Seconds OK | None (aggregated) |
+| POST | `/api/gateway/projects` | Frontend, init_project MCP | Register a new project in projects.toml | <500 ms | N/A | Durable (file) |
+| DELETE | `/api/gateway/projects/:name` | Frontend | Remove a registered project | <500 ms | N/A | Durable (file) |
+| GET/PUT | `/api/gateway/bot-config` | Frontend | Read/write bot config file | <100 ms | Seconds OK | Durable (file) |
+| GET/POST | `/mcp` | Claude Code agent | MCP proxy to active project | <500 ms | Strong | Durable via upstream |
+| GET | `/gateway/mode` | Frontend | Check whether gateway mode is active | <50 ms | Stable | None |
+| POST | `/gateway/tokens` | Ops/admin | Generate a headless-agent join token | <100 ms | N/A | Durable (in-memory HashMap) |
+| POST | `/gateway/register` | Headless build agent at startup | Register agent with token, supply address | <200 ms | N/A | In-memory Vec |
+| GET | `/gateway/agents` | Frontend, ops | List all registered headless agents | <100 ms | Seconds OK | In-memory Vec |
+| DELETE | `/gateway/agents/:id` | Frontend, ops | Deregister an agent | <200 ms | N/A | In-memory Vec |
+| POST | `/gateway/agents/:id/assign` | Frontend, ops | Assign agent to a project | <200 ms | N/A | In-memory Vec |
+| POST | `/gateway/agents/:id/heartbeat` | Headless agent (periodic) | Signal agent is alive | <100 ms | Real-time | In-memory Vec |
+
+---
+
+## 2. Classification
+
+| Endpoint Group | Classification |
+|---------------|----------------|
+| `/webhook/whatsapp`, `/webhook/slack`, `/webhook/slack/command` | **external-webhook** |
+| `/`, `/assets/*`, `/*path`, `/bot-config` (HTML) | **frontend-asset** |
+| `POST /api/agents/start`, `POST /api/agents/stop`, `POST /api/agents/worktrees`, `DELETE /api/agents/worktrees/:id` | **write** |
+| `POST /api/project`, `DELETE /api/project`, `POST /api/projects/forget` | **write** |
+| `PUT /api/settings`, `PUT /api/settings/editor`, `POST /api/settings/open-file` | **write** |
+| `POST /api/model`, `POST /api/anthropic/key` | **write** |
+| `POST /api/wizard/step/*`, `PUT /api/wizard/step/*` | **write** |
+| `POST /api/bot/command`, `PUT /api/bot/config` | **write** |
+| `POST /api/io/fs/write`, `POST /api/io/fs/create/absolute`, `POST /api/io/shell/exec` | **write** |
+| `POST /api/gateway/switch`, `POST /api/gateway/projects`, `DELETE /api/gateway/projects/:name` | **write** |
+| `POST /gateway/tokens`, `POST /gateway/register`, `DELETE /gateway/agents/:id`, `POST /gateway/agents/:id/assign` | **write** |
+| `POST /gateway/agents/:id/heartbeat` | **write** |
+| `POST /mcp`, `GET /mcp` | **write** (mutations dominate; reads via CRDT subscription eventually) |
+| All remaining `GET` endpoints | **read** |
+| `POST /api/chat/cancel`, `POST /api/agents/config/reload` | **write** (side-effect only, stateless result) |
+
+---
+
+## 3. Write Endpoints → Target CRDT Collections
+
+| Endpoint | Current Storage | Target CRDT Collection | Notes |
+|----------|----------------|----------------------|-------|
+| `POST /gateway/tokens` | `GatewayState.pending_tokens: HashMap<String, PendingToken>` | `tokens` — LWW map keyed by token UUID | TTL field; garbage-collect expired entries |
+| `POST /gateway/register` | `GatewayState.joined_agents: Vec<JoinedAgent>` | `nodes` — existing CRDT node collection (extend with agent metadata) | Already partially exists for CRDT mesh peers |
+| `POST /gateway/agents/:id/assign` | `joined_agents` Vec mutation | `nodes` — LWW field `assigned_project` per node entry | |
+| `DELETE /gateway/agents/:id` | `joined_agents` Vec mutation | `nodes` — tombstone / remove entry | Add-wins or explicit remove flag |
+| `POST /gateway/agents/:id/heartbeat` | `joined_agents` Vec `last_seen` field | `nodes` — LWW `last_seen_ms` field per node | Low-cost: just a timestamp LWW |
+| `POST /api/agents/start` | `AgentPool.agents: HashMap` | No new CRDT; agent process is local. Side-effect only. Assign record if cross-node visibility needed → `active_agents` LWW map | |
+| `POST /api/agents/stop` | `AgentPool.agents` mutation | Same as above | |
+| `POST /api/agents/worktrees` | git filesystem | No CRDT needed; git worktrees are local | |
+| `POST /api/gateway/switch` | `GatewayState.active_project` in-memory | `gateway_config` — LWW field `active_project` | |
+| `POST /api/gateway/projects` | `projects.toml` file | `gateway_config.projects` — LWW map by project name | |
+| `DELETE /api/gateway/projects/:name` | `projects.toml` file | `gateway_config.projects` — tombstone entry | |
+| `PUT /api/settings`, `PUT /api/settings/editor` | `JsonFileStore` | `settings` — LWW map per key | Low priority; settings are single-node today |
+| `POST /api/model` | `JsonFileStore` | `settings` — same LWW map | |
+| `POST /api/anthropic/key` | Encrypted file/env | Stay out of CRDT (secrets) | |
+| `PUT /api/bot/config` | `.huskies/bot.toml` file | Stay out of CRDT (credentials) | |
+| `POST /mcp` | CRDT (already) | Already replicated via CRDT WebSocket bus | Story/pipeline mutations are CRDT-native |
+| Merge job tracking | `AgentPool.merge_jobs: HashMap<String, MergeJob>` | `merge_jobs` — LWW map by story_id, or append-only log | Needed for cross-node merge visibility |
+| Test job tracking | `AppContext.test_job_registry: HashMap<WorkPath, TestJob>` | `test_jobs` — LWW map by story_id | Needed so any node can query test status |
+
+---
+
+## 4. Read Endpoints → Proposed RPC Frame Shapes
+
+| Endpoint | Request Fields | Response Fields |
+|----------|---------------|-----------------|
+| `GET /health` | _(none)_ | `{status: "ok", version: string, node_id: string}` |
+| `GET /api/gateway` | _(none)_ | `{active_project: string, projects: {name, url, healthy}[]}` |
+| `GET /api/gateway/pipeline` | _(none)_ | `{projects: {name: string, pipeline: PipelineStages}[]}` |
+| `GET /gateway/agents` | _(none)_ | `{agents: {id, label, address, assigned_project, last_seen_ms, alive: bool}[]}` |
+| `GET /api/agents` | _(none)_ | `{agents: {story_id, agent_name, pid, status, started_at}[]}` |
+| `GET /api/agents/worktrees` | _(none)_ | `{worktrees: {story_id, path, branch}[]}` |
+| `GET /api/agents/:id/:name/output` | _(path params)_ | `{lines: AgentLogLine[]}` |
+| `GET /api/work-items/:story_id/test-results` | _(path param)_ | `{passed: bool, output: string, ran_at: timestamp}` |
+| `GET /api/work-items/:story_id/token-cost` | _(path param)_ | `{input_tokens: u64, output_tokens: u64, cost_usd: f64}` |
+| `GET /api/token-usage` | _(none)_ | `{total_input: u64, total_output: u64, per_agent: {...}[]}` |
+| `GET /api/settings` | _(none)_ | `{settings: Record<string, JsonValue>}` |
+| `GET /api/model` | _(none)_ | `{provider: string, model: string}` |
+| `GET /api/events` | `{since: unix_ms}` | `{events: {type, payload, ts}[], next_since: unix_ms}` |
+| `GET /debug/crdt` | _(none)_ | `{crdt_doc: json}` |
+| `GET /api/wizard` | _(none)_ | `{steps: WizardStep[], current_step: string}` |
+| `GET /api/anthropic/models` | _(none)_ | `{models: {id, name}[]}` |
+| `GET /api/ollama/models` | _(none)_ | `{models: {name, size}[]}` |
+
+---
+
+## 5. Draft: Unsigned Read-RPC Protocol
+
+### Rationale
+
+Write mutations already flow through the CRDT bus (signed ops). Read endpoints are the remaining HTTP surface that could be migrated to the same WebSocket channel. This section drafts the envelope format so read RPCs can share the bus without requiring Ed25519 auth (unsigned reads are fine; only writes need authenticity guarantees).
+
+### Frame Envelope (JSON over WebSocket)
+
+```json
+// Request (caller → peer)
+{
+  "version": 1,
+  "kind": "rpc_request",
+  "correlation_id": "uuid-v4",
+  "ttl_ms": 5000,
+  "method": "get_pipeline_status",
+  "params": {}
+}
+
+// Success response (peer → caller)
+{
+  "version": 1,
+  "kind": "rpc_response",
+  "correlation_id": "uuid-v4",
+  "ok": true,
+  "result": { ... }
+}
+
+// Error response
+{
+  "version": 1,
+  "kind": "rpc_response",
+  "correlation_id": "uuid-v4",
+  "ok": false,
+  "error": "human-readable message",
+  "code": "NOT_FOUND | TIMEOUT | PEER_OFFLINE | INTERNAL"
+}
+```
+
+### Correlation IDs
+
+Each request carries a UUID v4 `correlation_id`. The responder echoes it verbatim. Callers maintain a `HashMap<String, oneshot::Sender>` to route responses back to waiting futures. On TTL expiry the entry is removed and the caller receives `Err(Timeout)`.
+
+### TTL Semantics
+
+- Caller specifies `ttl_ms` (default 5000, max 30000).
+- If the responding peer does not answer within the TTL, the caller synthesises a `TIMEOUT` error response locally.
+- Responders do not need to track TTLs; they answer as fast as they can.
+- Callers may use stale cached results if `ttl_ms == 0` is supplied and a cache entry exists (opt-in freshness trade-off).
+
+### Error Codes
+
+| Code | Meaning |
+|------|---------|
+| `NOT_FOUND` | Resource does not exist |
+| `TIMEOUT` | Peer did not respond within TTL |
+| `PEER_OFFLINE` | No live peer with the requested capability is connected |
+| `UNAUTHORIZED` | Caller lacks permission (future, when auth lands) |
+| `INTERNAL` | Unexpected server-side error |
+
+### Peer-Offline Handling
+
+- Before sending a request the caller checks whether any peer that can serve the method is currently connected.
+- If no peer is online, the caller immediately returns `PEER_OFFLINE` without queuing (fail-fast).
+- For idempotent reads, callers may fall back to a local CRDT-materialized view if `PEER_OFFLINE` or `TIMEOUT` is received.
+- Non-idempotent reads (e.g., `exec_shell`) must not be retried automatically.
+
+### Method Naming Convention
+
+`<noun>.<verb>` — e.g. `pipeline.get`, `agents.list`, `health.check`, `events.poll`.
+
+---
+
+## 6. In-Memory State → CRDT Collection Migration
+
+| Location | Field | Current Type | Proposed CRDT Type | Rationale |
+|----------|-------|-------------|-------------------|-----------|
+| `gateway.rs::GatewayState` | `pending_tokens` | `HashMap<String, PendingToken>` | **LWW-map** keyed by token UUID, with `expires_at` TTL field | Tokens are short-lived; LWW is fine; GC by TTL |
+| `gateway.rs::GatewayState` | `joined_agents` | `Vec<JoinedAgent>` | Extend existing **`nodes` CRDT collection** with agent metadata fields (label, address, assigned_project, last_seen_ms) | Nodes collection already exists for CRDT mesh peers |
+| `agents/pool/mod.rs::AgentPool` | `merge_jobs` | `HashMap<String, MergeJob>` | **LWW-map** keyed by story_id; fields: node_id, status, started_at, error | Required for cross-node merge visibility |
+| `agents/pool/mod.rs::AgentPool` | `agents` (running agent handles) | `HashMap<String, StoryAgent>` | **LWW-map** `active_agents` keyed by story_id; fields: node_id, agent_name, pid(optional), started_at, status | Process handles stay local; only metadata replicated |
+| `http/context.rs::AppContext` | `test_job_registry` | `HashMap<WorkPath, TestJob>` (TestJobRegistry) | **LWW-map** `test_jobs` keyed by story_id; fields: node_id, status, started_at, finished_at | Needed so any node can query test run status |
+| `agents/pool/auto_assign` | agent throttle / last-seen timestamps | Local variables / in-memory | **LWW-map** `agent_throttle` keyed by agent_name; field: last_dispatched_at | Prevents double-dispatch on multi-node |
+| `gateway.rs::GatewayState` | `active_project` | `Arc<RwLock<String>>` | **LWW register** in `gateway_config` collection, field `active_project` | Single-value; LWW is correct |
+| `gateway.rs::GatewayState` | `projects` (BTreeMap) | `Arc<RwLock<BTreeMap<String, ProjectEntry>>>` | **LWW-map** in `gateway_config.projects` keyed by project name | Infrequently mutated; LWW correct |
+
+### Summary of Proposed New CRDT Collections
+
+| Collection | Type | Notes |
+|-----------|------|-------|
+| `tokens` | LWW-map | Join tokens with TTL; garbage-collect on expiry |
+| `nodes` | LWW-map (extend existing) | Already exists; add agent metadata fields |
+| `merge_jobs` | LWW-map | One entry per story; overwritten on each merge attempt |
+| `active_agents` | LWW-map | One entry per story; metadata only (not process handles) |
+| `test_jobs` | LWW-map | One entry per story; test run status |
+| `agent_throttle` | LWW-map | One entry per agent name; last-dispatched timestamp |
+| `gateway_config` | LWW-map (or flat LWW fields) | `active_project`, `projects` map |
+
+---
+
+## 7. Migration Order and Dependencies
+
+### Blocking Dependency
+
+**Story 665 (Ed25519 auth)** must land before any write operation is migrated to the CRDT bus. Unsigned writes on a shared bus would allow any connected peer to forge mutations. Read RPCs do not require auth.
+
+### Wave 0 — Foundation (no story 665 needed)
+
+These can land in parallel with or before story 665:
+
+1. **Extend `nodes` CRDT collection** with `label`, `address`, `assigned_project`, `last_seen_ms` fields. This is a pure schema addition.
+2. **Add `merge_jobs` and `active_agents` LWW-maps** to the CRDT document schema (additive; existing nodes ignore unknown fields via `serde(default)`).
+3. **Implement unsigned read-RPC multiplexer** on the existing `/crdt-sync` WebSocket channel (new `kind: "rpc_request"/"rpc_response"` frame types, ignored by old peers).
+
+### Wave 1 — Migrate Heartbeat + Agent Registration (after `nodes` schema extended)
+
+- Replace `POST /gateway/agents/:id/heartbeat` HTTP call with a CRDT LWW write to `nodes[id].last_seen_ms`.
+- Replace `POST /gateway/register` with a CRDT insert into `nodes` collection.
+- Replace `POST /gateway/tokens` / token validation with CRDT `tokens` map read/write.
+- **Blocks on story 665** for the write side; read queries (list agents, check token) can migrate via read-RPC first.
+
+### Wave 2 — Migrate Read Endpoints to Read-RPC (no auth required)
+
+Can land in parallel with Wave 1 write migration:
+
+- `GET /health` → `health.check` RPC (gateway reads from CRDT `nodes` liveness)
+- `GET /gateway/agents` → `agents.list` RPC reading from CRDT `nodes`
+- `GET /api/events` polling loop → subscribe to CRDT op stream directly (eliminate polling)
+- `GET /api/gateway/pipeline` → `pipeline.get` RPC or direct CRDT materialisation (already replicated)
+- `GET /api/agents` → `active_agents.list` RPC reading from CRDT `active_agents`
+
+### Wave 3 — Migrate Merge and Test Job Tracking (after waves 0–1)
+
+- Replace `merge_jobs` HashMap with CRDT `merge_jobs` map writes on merge start/completion.
+- Replace `test_job_registry` HashMap with CRDT `test_jobs` map writes on test start/completion.
+- Enables: any node can query merge or test status without HTTP call to the node that started the job.
+
+### Wave 4 — Migrate Gateway Config Writes (after story 665)
+
+- `POST /api/gateway/switch`, `POST /api/gateway/projects`, `DELETE /api/gateway/projects/:name` → CRDT `gateway_config` LWW writes.
+- Low urgency; these are infrequent admin operations. Can keep HTTP as a thin wrapper that writes to CRDT.
+
+### Endpoints That Stay HTTP
+
+| Endpoint | Reason |
+|----------|--------|
+| `/webhook/whatsapp`, `/webhook/slack` | External platform callbacks; must remain HTTP |
+| `/oauth/authorize`, `/callback` | OAuth redirect flow; must remain HTTP |
+| `/api/io/*`, `/api/io/shell/exec` | Local filesystem/shell; process-local, not cross-node |
+| `/api/io/fs/*` | Same — local I/O only |
+| `/mcp` | External MCP clients (Claude Code CLI) speak HTTP/SSE; gateway proxy stays HTTP |
+| `/assets/*`, `/`, `/*path` | Static frontend assets |
+| `/api/anthropic/key`, `PUT /api/bot/config` | Credentials — must stay local, never in CRDT |
+| `GET /debug/crdt` | Debug only; HTTP fine |
+
+### Dependency Graph Summary
+
+```
+story 665 (Ed25519 auth)
+    └── Wave 1 write migrations (heartbeat, register, assign, tokens)
+        └── Wave 4 gateway config writes
+
+Wave 0 (schema extensions + read-RPC multiplexer)  [can start now, parallel]
+    └── Wave 2 read endpoint migrations            [can start now, parallel]
+    └── Wave 3 merge/test job tracking             [after Wave 0 schema]
+```
+
+**Critical path:** Story 665 → Wave 1 → Wave 4. Everything else is parallel.

.huskies/specs/tech/SPIKE_GATEWAY_UPDATE_COMMAND.md

@@ -0,0 +1,241 @@
+# Spike 814: Chat-Driven Update Command for Multi-Project Gateway
+
+## 1. Problem Statement
+
+In a multi-project gateway deployment (Docker Compose or similar), each project runs as its own container.
+Today, updating a project container requires direct operator access to the host — `docker pull`, `docker compose up -d <project>`, or equivalent.
+There is no way to trigger an update from chat.
+
+This spike designs a `update` bot command that:
+- Can be typed in the Matrix/Slack/Discord chat room.
+- Pulls the latest image (or rebuilds from source) for one or all project containers managed by the gateway.
+- Reports progress and outcome back to the room.
+- Supports rollback when a container fails to start cleanly.
+
+---
+
+## 2. Command Surface
+
+### Basic syntax
+
+```
+update [<project>|all] [--rollback]
+```
+
+| Invocation | Effect |
+|-----------|--------|
+| `update huskies` | Update and restart the `huskies` container. |
+| `update all` | Update every registered project container, one at a time. |
+| `update` (no args) | Same as `update all`. |
+| `update huskies --rollback` | Roll back `huskies` to its previous image tag. |
+
+### Progress feedback
+
+The bot posts incremental updates to the room (editing the same message where the platform supports it):
+
+```
+[huskies] Pulling image…  ⏳
+[huskies] Image pulled (sha256:abc123). Stopping container…
+[huskies] Container stopped. Starting new container…
+[huskies] Health check passed ✅ (2 s)
+```
+
+On failure:
+```
+[huskies] Health check failed after 30 s ❌
+[huskies] Rolling back to previous image (sha256:def456)…
+[huskies] Rollback complete ✅
+```
+
+### Error cases
+
+| Condition | Response |
+|-----------|----------|
+| Unknown project name | `Unknown project 'foo'. Known projects: huskies, robot-studio` |
+| No Docker socket access | `Update not available: Docker socket not mounted` |
+| Rollback with no previous image | `No previous image recorded for 'huskies'; cannot roll back` |
+| Project container not managed by Docker | `'huskies' is not a container-managed project; rebuild it manually` |
+
+---
+
+## 3. Auth
+
+### 3.1 Threat model
+
+The update command triggers container replacement — a privileged operation equivalent to `docker compose up -d`.
+An unauthenticated attacker who can send a message to the bot room could force a rolling restart or roll back a working container.
+
+### 3.2 Proposed approach: room + role guard
+
+**Layer 1 — Room restriction.**
+The update command is only accepted in a designated *ops room*, configured in `bot.toml` (or `projects.toml`):
+
+```toml
+[gateway.ops_room]
+room_id = "!abc123:homeserver.example.com"
+```
+
+Messages from other rooms are rejected with: `The update command is only available in the ops room.`
+
+**Layer 2 — Sender role check (Matrix/Slack).**
+The bot checks the sender's power level (Matrix) or admin status (Slack/Discord).
+Only users with power level ≥ 50 (moderator) on Matrix, or workspace admin on Slack, may issue `update`.
+Unapproved senders receive: `You do not have permission to issue update commands.`
+
+**Layer 3 — Confirmation prompt for destructive operations.**
+`update all` affects every project.
+The bot responds with a confirmation challenge:
+
+```
+This will restart all 3 project containers. Reply `yes` within 60 s to confirm, or `no` to cancel.
+```
+
+Single-project updates (`update huskies`) do **not** require confirmation — they are already scoped.
+
+### 3.3 Future: Ed25519 operator token
+
+When story 665 (Ed25519 auth) lands, the gateway's node identity keypair can sign an operator token.
+The bot verifies the token against the node's public key before acting.
+This removes the room/role dependency and allows the command to be issued programmatically
+(e.g. from a CI pipeline via MCP).
+
+For now the room + role guard is sufficient.
+
+---
+
+## 4. Rollout Approach
+
+### 4.1 Docker-managed containers (primary path)
+
+The gateway process has access to the Docker socket (mounted as a volume at `/var/run/docker.sock`).
+The update sequence for a single project:
+
+1. **Record current image** — read the running container's image digest (store in gateway's `update_history` LWW-map in CRDT, keyed by project name).
+2. **Pull new image** — `docker pull <image>` (or the compose-file equivalent tag).
+3. **Drain connections** — gateway marks the project as `updating`; new proxy requests return 503 with a `Retry-After: 5` header; in-flight requests are allowed to complete (30 s grace window).
+4. **Stop old container** — `docker stop --time=30 <container_name>`.
+5. **Start new container** — `docker start <container_name>` (or `docker compose up -d <service>`).
+6. **Health check** — poll the project's `/health` endpoint until 200 OK or 30 s timeout.
+7. **Restore routing** — remove the `updating` flag; proxy resumes normal operation.
+
+Steps 1–7 are serialised per project. When `update all` is used, projects are updated **one at a time** (not in parallel) to limit blast radius.
+
+### 4.2 Source-rebuild path (non-Docker / dev mode)
+
+When Docker is not available (the gateway binary is running directly on the host, not in a container),
+the update command falls back to the existing `rebuild_and_restart` flow (`server/src/rebuild.rs`):
+`cargo build` → re-exec.
+This path cannot update individual projects independently — it rebuilds the gateway itself.
+
+### 4.3 Gateway state during update
+
+```
+normal → updating → (success) normal
+                  → (failure) rolling_back → normal
+```
+
+The CRDT `gateway_config` collection gains two new LWW fields per project:
+
+| Field | Type | Purpose |
+|-------|------|---------|
+| `update_state` | `"idle" \| "updating" \| "rolling_back"` | Current update lifecycle stage |
+| `update_started_at` | `u64` (unix ms) | When the update was triggered |
+| `previous_image` | `string` | Image digest before the most recent update |
+| `current_image` | `string` | Image digest currently running |
+
+These fields are replicated to all nodes so that other gateway instances and headless agents
+can observe update progress without polling HTTP.
+
+---
+
+## 5. Rollback Approach
+
+### 5.1 Automatic rollback
+
+If the health check in step 6 (§4.1) times out or returns a non-200 status, the gateway automatically:
+
+1. Logs the failure: `[update] health check failed for huskies after 30 s`.
+2. Posts to the ops room: `Health check failed. Rolling back…`.
+3. Runs `docker stop` on the new container.
+4. Pulls and starts the previous image digest (stored in `previous_image`).
+5. Re-runs the health check on the rolled-back container.
+6. Reports outcome to the room.
+
+If the rollback health check also fails, the bot reports:
+```
+Rollback failed. Manual intervention required. Previous image: sha256:def456
+```
+and sets `update_state = "error"` in the CRDT. The ops room is notified; no further automatic action is taken.
+
+### 5.2 Manual rollback
+
+An operator can issue `update huskies --rollback` at any time when the project is in `idle` state.
+The command replays steps 3–7 of §4.1 with `previous_image` substituted for the target image.
+`previous_image` is overwritten with the image that was displaced, so repeated rollbacks alternate between two images.
+
+### 5.3 Rollback unavailability
+
+Rollback is unavailable when:
+- No `previous_image` is recorded (first-ever update on this installation).
+- `update_state` is already `"updating"` or `"rolling_back"` (only one concurrent update per project).
+
+---
+
+## 6. Implementation Sketch
+
+### 6.1 New files
+
+| Path | Purpose |
+|------|---------|
+| `server/src/chat/commands/update.rs` | Synchronous `handle_update` stub (returns `None` — async, like `rebuild`) |
+| `server/src/service/gateway/update.rs` | Core update/rollback logic; calls Docker API or falls back to `rebuild.rs` |
+| `server/src/service/gateway/docker.rs` | Thin wrapper around Docker socket HTTP API (`/containers/:id/start` etc.) |
+
+### 6.2 New CRDT fields
+
+Extend the `gateway_config` CRDT document (already exists per Spike 679 §6) with:
+- `projects.<name>.update_state` (LWW string)
+- `projects.<name>.update_started_at` (LWW u64)
+- `projects.<name>.previous_image` (LWW string)
+- `projects.<name>.current_image` (LWW string)
+
+### 6.3 Gateway HTTP changes
+
+Add one endpoint for the Docker-fallback check:
+
+```
+GET /gateway/update/available
+→ {"available": true, "mode": "docker"} | {"available": true, "mode": "rebuild"} | {"available": false}
+```
+
+The frontend can use this to show/hide an "Update" button in the gateway project list.
+
+### 6.4 Async dispatch
+
+`update` is an async command (like `rebuild`, `htop`, `start`).
+The command keyword is detected in `on_room_message` before `try_handle_command` is invoked.
+The handler spawns a `tokio::spawn` task, posts incremental updates via the existing transport's `send_message` / `edit_message` API, and returns.
+
+---
+
+## 7. Open Questions
+
+| # | Question | Notes |
+|---|----------|-------|
+| 1 | Should the Docker socket be mounted in the gateway container by default? | Security trade-off: socket access = container escape risk. Alternative: `docker exec` via a sidecar. |
+| 2 | Should `update all` use a sequential or rolling strategy? | Sequential is safer; rolling is faster. Sequential chosen for v1. |
+| 3 | How do we handle projects not managed by Docker (e.g. running on bare metal)? | Fallback to `rebuild` covers the gateway itself; project-specific fallback is out of scope for v1. |
+| 4 | Should the confirmation challenge expire? | Yes — 60 s timeout, configurable in `bot.toml`. |
+| 5 | Should update history be persisted beyond CRDT (i.e. across full gateway restarts)? | CRDT persists to SQLite, so yes, as long as the CRDT DB survives the restart. |
+| 6 | Multi-gateway HA: which node triggers the actual Docker call? | The node that owns the Docker socket. CRDT `update_state` prevents double-triggering. |
+
+---
+
+## 8. Dependencies
+
+| Story / Spike | Dependency type |
+|--------------|----------------|
+| Spike 679 (HTTP → CRDT bus) | Soft — `gateway_config` LWW collection needed for update state; can stub without it |
+| Story 665 (Ed25519 auth) | Soft — operator token auth is a future hardening step; room+role guard suffices for v1 |
+| `server/src/rebuild.rs` | Direct — reuse `rebuild_and_restart` for the non-Docker path |
+| `server/src/gateway_relay.rs` | Indirect — update state changes should trigger relay events to connected frontends |

.huskies/specs/tech/STACK.md

@@ -0,0 +1,177 @@
+# Tech Stack
+
+## Backend
+- **Language:** Rust
+- **Framework:** Poem (HTTP + WebSocket + OpenAPI)
+- **Database:** SQLite via sqlx + rusqlite
+- **State:** BFT CRDT replicated document backed by SQLite
+- **Agents:** Claude Code CLI spawned in PTY pseudo-terminals
+- **Package manager:** cargo
+
+## Frontend
+- **Language:** TypeScript + React
+- **Build:** Vite
+- **Package manager:** npm
+- **Testing:** Vitest (unit), Playwright (e2e)
+
+## Deployment
+- Single Rust binary with embedded React frontend (rust-embed)
+- Three modes: standard server, headless build agent (`--rendezvous`), multi-project gateway (`--gateway`)
+- Docker container with OrbStack recommended on macOS
+
+## Project Layout
+```
+server/src/          — Rust backend
+frontend/src/        — React frontend
+crates/bft-json-crdt/ — CRDT library
+.huskies/            — Pipeline config, agent config, specs
+script/              — test, build, lint scripts
+docker/              — Dockerfile and docker-compose
+website/             — Static marketing/docs site
+```
+
+## Source Map
+
+One row per directory or top-level file. Descriptions are pulled from the module's `//!` doc-comment where present. **Use this to know where to look — do not re-discover the codebase via grep.**
+
+### Top-level backend files (`server/src/`)
+
+| File | Purpose |
+|------|---------|
+| `server/src/agent_log.rs` | Agent log persistence — reads and writes JSONL agent event logs to disk. |
+| `server/src/agent_mode.rs` | Headless build-agent mode for distributed, rendezvous-based story processing. |
+| `server/src/cli.rs` | Command-line argument parsing for the huskies binary. |
+| `server/src/crdt_wire.rs` | CRDT wire codec — serialization format for `SignedOp` sync messages between nodes. |
+| `server/src/gateway.rs` | Multi-project gateway — entrypoint wiring and route tree.  When `huskies --gateway` is used, the server starts in gateway mode. B… |
+| `server/src/gateway_relay.rs` | Gateway relay task — pushes project status events to the gateway via WebSocket.  When `gateway_url` is configured in `project.tom… |
+| `server/src/log_buffer.rs` | Bounded in-memory ring buffer for server log output.  Use the [`slog!`] macro (INFO), [`slog_warn!`] (WARN), or [`slog_error!`] (… |
+| `server/src/main.rs` | Huskies server — entry point, CLI argument parsing, and server startup. |
+| `server/src/mesh.rs` | Peer mesh discovery — supplementary CRDT sync connections between build agents.  When mesh discovery is enabled, a build agent pe… |
+| `server/src/node_identity.rs` | Node identity — Ed25519 keypair foundation for distributed huskies.  Each huskies node has a stable identity derived from an Ed25… |
+| `server/src/rebuild.rs` | Server rebuild and restart logic shared between the MCP tool and Matrix bot command. |
+| `server/src/services.rs` | Shared services bundle — common state threaded through HTTP handlers and chat transports.  `Services` bundles the fields that eve… |
+| `server/src/state.rs` | Session state — global mutable state shared across the server (project root, cancellation). |
+| `server/src/store.rs` | Key-value store — JSON-backed persistent storage for user settings and preferences. |
+| `server/src/workflow.rs` | Workflow module: test result tracking and acceptance evaluation. |
+
+### Backend modules (`server/src/`)
+
+| Path | Purpose |
+|------|---------|
+| `server/src/` |  |
+| `server/src/agents/` | Agent subsystem — types, configuration, and orchestration for coding agents. |
+| `server/src/agents/merge/` | Merge operations — rebases agent work onto master and runs post-merge validation. |
+| `server/src/agents/merge/squash/` | Squash-merge orchestration: rebase agent work onto master and run post-merge gates. |
+| `server/src/agents/pool/` | Agent pool — manages the set of active agents across all pipeline stages. |
+| `server/src/agents/pool/auto_assign/` | Auto-assign submodules: wires focused sub-files and re-exports public items. |
+| `server/src/agents/pool/auto_assign/watchdog/` | Watchdog task: detects orphaned agents, enforces turn/budget limits, and triggers auto-assign. |
+| `server/src/agents/pool/auto_assign/watchdog/tests/` | Shared test helpers for the watchdog module. |
+| `server/src/agents/pool/pipeline/` | Pipeline operations — stage advancement, completion handling, and merge orchestration. |
+| `server/src/agents/pool/pipeline/advance/` | Pipeline advance — moves stories forward through pipeline stages after agent completion. |
+| `server/src/agents/pool/pipeline/completion/` | Agent completion handling — processes exit results and triggers pipeline advancement. |
+| `server/src/agents/pool/start/` | Agent start — spawns a new agent process in a worktree for a given story. |
+| `server/src/agents/runtime/` | Agent runtimes — pluggable backends (Claude Code, Gemini, OpenAI) for running agents. |
+| `server/src/chat/` | Transport abstraction for chat platforms.  The [`ChatTransport`] trait defines a platform-agnostic interface for sending and edit… |
+| `server/src/chat/commands/` | Bot-level command registry shared by all chat transports.  Commands registered here are handled directly by the bot without invok… |
+| `server/src/chat/transport/` | Chat transports — pluggable backends (Matrix, Slack, WhatsApp, Discord) for bot messaging. |
+| `server/src/chat/transport/discord/` | Discord Bot integration.  Provides: - [`DiscordTransport`] — a [`ChatTransport`] that sends messages via the Discord REST API (`/… |
+| `server/src/chat/transport/matrix/` | Matrix bot integration for Story Kit.  When a `.huskies/bot.toml` file is present with `enabled = true`, the server spawns a Matr… |
+| `server/src/chat/transport/matrix/bot/` | Matrix bot — sub-modules for the Matrix chat bot implementation. |
+| `server/src/chat/transport/matrix/bot/messages/` | Matrix message handler — processes incoming room messages and dispatches commands. |
+| `server/src/chat/transport/matrix/config/` | Matrix transport configuration — deserialization of `bot.toml` Matrix settings. |
+| `server/src/chat/transport/slack/` | Slack Bot API integration.  Provides: - [`SlackTransport`] — a [`ChatTransport`] that sends messages via the Slack Web API (`api.… |
+| `server/src/chat/transport/slack/commands/` | Slack incoming message dispatch and slash command handling. |
+| `server/src/chat/transport/whatsapp/` | WhatsApp Business API integration.  Provides: - [`WhatsAppTransport`] — a [`ChatTransport`] that sends messages via the Meta Grap… |
+| `server/src/chat/transport/whatsapp/commands/` | WhatsApp command handling — processes incoming WhatsApp messages as bot commands. |
+| `server/src/config/` | Project configuration — parses `project.toml` for agents, components, and server settings. |
+| `server/src/crdt_snapshot/` | CRDT snapshot compaction with cross-node coordination.  This module implements full CRDT state snapshots for compacting the op jo… |
+| `server/src/crdt_state/` | CRDT state layer — manages pipeline state as a conflict-free replicated document backed by SQLite.  The CRDT document is the prim… |
+| `server/src/crdt_sync/` | CRDT sync — WebSocket-based replication of pipeline state between huskies nodes. WebSocket-based CRDT sync layer for replicating… |
+| `server/src/crdt_sync/server/` | Server-side `/crdt-sync` WebSocket handler. |
+| `server/src/db/` | SQLite storage layer — content store, shadow writes, and CRDT op persistence. |
+| `server/src/http/` | HTTP server — module declarations for all REST, MCP, WebSocket, and SSE endpoints. |
+| `server/src/http/agents/` | HTTP agent endpoints — thin adapters over `service::agents`.  Each handler: extracts payload → calls `service::agents::X` → shape… |
+| `server/src/http/gateway/` | Gateway HTTP handlers — thin transport shells for the gateway service.  Each handler calls `service::gateway::*` for business log… |
+| `server/src/http/mcp/` | HTTP MCP server module. |
+| `server/src/http/mcp/agent_tools/` | MCP agent tools — start, stop, wait, list, and inspect agents via MCP. |
+| `server/src/http/mcp/diagnostics/` | MCP diagnostic tools — server logs, CRDT dump, version, line counting, story movement. |
+| `server/src/http/mcp/shell_tools/` | MCP shell tools — run commands, execute tests, and stream output via MCP.  This file is a thin adapter: it deserialises MCP paylo… |
+| `server/src/http/mcp/story_tools/` | MCP story tools — create, update, move, and manage stories, bugs, refactors, and spikes via MCP.  This module is a thin adapter:… |
+| `server/src/http/mcp/story_tools/story/` | Story creation, listing, update, and lifecycle MCP tools. |
+| `server/src/http/mcp/tools_list/` | `tools/list` MCP method — returns the static schema for every tool the server exposes. |
+| `server/src/http/workflow/` | Workflow helpers — shared story/bug file operations used by HTTP and MCP handlers. |
+| `server/src/http/workflow/story_ops/` | Story operations — creates, updates, and manages acceptance criteria in story files. |
+| `server/src/io/` | I/O subsystem — filesystem, shell, search, onboarding, and story metadata operations. |
+| `server/src/io/fs/` | Filesystem I/O — module declarations and re-exports for file operations. |
+| `server/src/io/fs/scaffold/` | Project scaffolding — creates the `.huskies/` directory structure and default files. |
+| `server/src/io/fs/scaffold/detect/` | Stack detection — inspect the project root for marker files and emit TOML `[[component]]` entries plus `script/build\|lint\|test`… |
+| `server/src/io/watcher/` | Filesystem watcher for `.huskies/project.toml` and `.huskies/agents.toml`.  Watches config files for changes and broadcasts a [`W… |
+| `server/src/llm/` | LLM subsystem — chat orchestration, prompts, OAuth, and provider integrations. |
+| `server/src/llm/chat/` | LLM chat — orchestrates multi-turn conversations with tool-calling LLM providers. |
+| `server/src/llm/providers/` | LLM providers — module declarations for Anthropic, Claude Code, and Ollama backends. |
+| `server/src/llm/providers/claude_code/` | Claude Code provider — runs Claude Code CLI in a PTY and parses structured output. |
+| `server/src/pipeline_state/` | Typed pipeline state machine (story 520).  Replaces the stringly-typed CRDT views with strict Rust enums so that impossible state… |
+| `server/src/service/` | Service layer — domain logic extracted from HTTP handlers.  Each sub-module follows the conventions documented in `docs/architect… |
+| `server/src/service/agents/` | Agent service — public API for the agent domain.  This module orchestrates calls to `io.rs` (side effects) and the pure topic mod… |
+| `server/src/service/anthropic/` | Anthropic service — public API for Anthropic API-key management and model listing.  Exposes functions to check, store, and use th… |
+| `server/src/service/bot_command/` | Bot command service — domain logic for dispatching slash commands.  Extracted from `http/bot_command.rs` so that argument parsing… |
+| `server/src/service/common/` | Shared pure helpers used by multiple service modules.  All sub-modules here are pure (no I/O, no side effects). Any helper that d… |
+| `server/src/service/diagnostics/` | Diagnostics service — server logs, CRDT dump, permission management, and story movement.  Extracted from `http/mcp/diagnostics.rs… |
+| `server/src/service/events/` | Events service — public API for the events domain.  This module re-exports the pure buffer types from `buffer.rs` and the side-ef… |
+| `server/src/service/file_io/` | File I/O service — public API for filesystem and shell operations.  Exposes functions for reading, writing, and listing files sco… |
+| `server/src/service/gateway/` | Gateway service — domain logic for the multi-project gateway.  Follows the conventions in `docs/architecture/service-modules.md`:… |
+| `server/src/service/git_ops/` | Git operations service — worktree path validation and git command execution.  Extracted from `http/mcp/git_tools.rs` following th… |
+| `server/src/service/merge/` | Merge service — domain logic for merging agent work to master.  Extracted from `http/mcp/merge_tools.rs` following the convention… |
+| `server/src/service/notifications/` | Notifications service — pipeline-event fan-out to chat transports.  Subscribes to [`WatcherEvent`] broadcasts and posts human-rea… |
+| `server/src/service/notifications/io/` | I/O side of the notifications service.  This is the **only** file inside `service/notifications/` that may perform side effects:… |
+| `server/src/service/oauth/` | OAuth service — domain logic for the Anthropic OAuth 2.0 PKCE flow.  Extracts business logic from `http/oauth.rs` following the c… |
+| `server/src/service/pipeline/` | Pipeline service — shared pipeline-domain logic.  Contains pure functions for parsing and aggregating pipeline status data. Used… |
+| `server/src/service/project/` | Project service — public API for the project domain.  Exposes functions to open, close, query, and manage known projects. HTTP ha… |
+| `server/src/service/qa/` | QA service — domain logic for requesting, approving, and rejecting QA reviews.  Extracted from `http/mcp/qa_tools.rs` following t… |
+| `server/src/service/settings/` | Settings service — domain logic for project settings and editor configuration.  Extracts business logic from `http/settings.rs` f… |
+| `server/src/service/shell/` | Shell service — command safety, path sandboxing, and output helpers.  Extracted from `http/mcp/shell_tools.rs` following the conv… |
+| `server/src/service/status/` | Status broadcaster — unified pipeline-event fan-out for all consumers.  [`StatusBroadcaster`] lives on the [`crate::services::Ser… |
+| `server/src/service/story/` | Story service — domain logic for creating, updating, and managing pipeline work items.  Extracted from `http/mcp/story_tools.rs`… |
+| `server/src/service/timer/` | Timer service — deferred agent start via one-shot timers.  Provides [`TimerStore`] for persisting timers to `.huskies/timers.json… |
+| `server/src/service/wizard/` | Wizard service — domain logic for the multi-step project setup wizard.  Follows the conventions from `docs/architecture/service-m… |
+| `server/src/service/ws/` | WebSocket service — domain logic for real-time pipeline updates, chat, and permission prompts.  This module extracts the business… |
+| `server/src/worktree/` | Git worktree management — creates, lists, and removes worktrees for agent isolation. |
+
+### Crates
+
+| Path | Purpose |
+|------|---------|
+| `crates/bft-json-crdt/benches/` |  |
+| `crates/bft-json-crdt/bft-crdt-derive/src/` |  |
+| `crates/bft-json-crdt/src/` |  |
+| `crates/bft-json-crdt/tests/` |  |
+
+### Frontend (`frontend/src/`)
+
+| Path | Purpose |
+|------|---------|
+| `frontend/src/` |  |
+| `frontend/src/api/` |  |
+| `frontend/src/components/` |  |
+| `frontend/src/components/selection/` |  |
+| `frontend/src/hooks/` |  |
+| `frontend/src/utils/` |  |
+
+### Canonical patterns (copy these when adding new things)
+- **New CRDT LWW-map collection:** see `server/src/crdt_state/lww_maps.rs`
+- **New read-RPC handler:** register in `server/src/crdt_sync/rpc.rs`; call from frontend via `rpcCall<T>("method.name")` from `frontend/src/api/rpc.ts`
+- **Migrate HTTP route → CRDT:** delete from `gateway.rs` / `http/*`, add op to `service/<area>/`, write through `crdt_state/`
+- **New front-matter field:** add to `StoryMetadata` and `FrontMatter` in `io/story_metadata.rs` plus a `write_<name>_in_content` helper
+- **New service module:** copy `service/agents/` structure (`mod.rs` + `io.rs` + `selection.rs`)
+- **New chat command:** add a file under `chat/commands/` and register in `chat/commands/mod.rs::dispatch_command`
+- **New auto-assigner predicate:** add to `agents/pool/auto_assign/story_checks.rs`, wire in `auto_assign/auto_assign.rs`
+- **CRDT-seeding test helper:** `crate::db::write_item_with_content(story_id, stage, content)` — do not `fs::write` to `.huskies/work/{stage}/`
+
+
+## Quality Gates
+All enforced by `script/test`:
+1. Frontend build (`npm run build`)
+2. Rust formatting (`cargo fmt --all --check`)
+3. Rust linting (`cargo clippy -- -D warnings`)
+4. Rust tests (`cargo test`)
+5. Frontend tests (`npm test`)

.huskies/specs/tech/STATE_MACHINE.md

@@ -0,0 +1,350 @@
+# Pipeline State Machine
+
+This document describes the huskies pipeline state machine in two halves:
+**(a)** the model that runs in production today, and **(b)** transitions, refinements,
+and corrections we have identified as needed but not yet implemented.
+
+The codebase is in a deliberate transitional state: a typed CRDT state machine
+exists at `server/src/pipeline_state.rs` (introduced by story 520) with strict Rust
+enums for every stage, archive reason, execution state, and event. It is fully
+defined and tested but **not yet called from non-test code** (`#![allow(dead_code)]`
+at the top of the module). Consumers will migrate incrementally.
+
+The model that is actually doing work is the older **filesystem-stage-string +
+front-matter-flag** model. Section (a) below documents both representations and
+the migration intent.
+
+---
+
+## (a) The current state machine
+
+### Stages (production: filesystem string; future: typed enum)
+
+| Filesystem (production) | Typed (future) | Meaning |
+|---|---|---|
+| `work/1_backlog/` | `Stage::Backlog` | Story exists, waiting for dependencies or auto-assign promotion |
+| `work/2_current/` | `Stage::Coding` | Coder agent is running (or about to) |
+| `work/3_qa/` | `Stage::Qa` | Coder finished; gates / human review running |
+| `work/4_merge/` | `Stage::Merge { feature_branch, commits_ahead: NonZeroU32 }` | Gates passed, mergemaster ready to squash |
+| `work/5_done/` | `Stage::Done { merged_at, merge_commit }` | Mergemaster squashed to master |
+| `work/6_archived/` | `Stage::Archived { archived_at, reason: ArchiveReason }` | Out of the active flow |
+
+`5_done` auto-sweeps to `6_archived` after four hours. The typed `Stage::Done`
+variant always carries the merge SHA and timestamp; `Stage::Merge`'s
+`commits_ahead: NonZeroU32` makes "Merge with nothing to merge" structurally
+impossible (eliminates bug 519).
+
+### Archive reasons (`pipeline_state.rs::ArchiveReason`)
+
+The typed model already enumerates the reasons a story can leave the active flow
+(subsumes the legacy `blocked`, `merge_failure`, and `review_hold` front-matter
+fields per story 436):
+
+- `Completed` — happy-path
+- `Abandoned` — user explicitly abandoned
+- `Superseded { by: StoryId }` — replaced by another story
+- `Blocked { reason: String }` — manually blocked, awaiting human resolution
+- `MergeFailed { reason: String }` — mergemaster gave up after retry budget
+- `ReviewHeld { reason: String }` — held for human review at user request
+
+### Per-node execution state (`pipeline_state.rs::ExecutionState`)
+
+Stage is shared/CRDT-replicated. Execution state is per-node and lives under
+each node's pubkey in the CRDT, so there are no inter-author merge conflicts:
+
+- `Idle`
+- `Pending { agent, since }` — worktree being created, agent about to start
+- `Running { agent, started_at, last_heartbeat }`
+- `RateLimited { agent, resume_at }`
+- `Completed { agent, exit_code, completed_at }`
+
+### Pipeline events (`pipeline_state.rs::PipelineEvent`)
+
+The typed model defines every event that drives a Stage transition. Each variant
+carries the data needed to construct the destination state, so a transition
+function can never accidentally land in an underspecified state:
+
+- `DepsMet` — dependencies met; promote from backlog
+- `GatesStarted` — coder starting gates
+- `GatesPassed { feature_branch, commits_ahead }`
+- `GatesFailed { reason }`
+- `QaSkipped { feature_branch, commits_ahead }` — qa-mode = "server"; skip QA, go to merge
+- `MergeSucceeded { merge_commit }`
+- `MergeFailedFinal { reason }`
+- `Accepted` — Done → Archived(Completed)
+
+### Transitions (current production = MCP verb shape)
+
+#### Backlog → Coding (a.k.a. backlog → 2_current)
+
+- **Auto path**: `AgentPool::auto_assign_available_work` calls
+  `promote_ready_backlog_stories`. A backlog story is promoted iff (a) it has
+  an explicit non-empty `depends_on` AND (b) every dep is in `5_done` or
+  `6_archived`. Stories with no `depends_on` are NOT auto-promoted — they wait
+  for human scheduling.
+  - Implemented in `server/src/agents/pool/auto_assign/auto_assign.rs::promote_ready_backlog_stories`.
+- **Manual path**: `mcp__huskies__move_story story_id=X target_stage=current`,
+  or `mcp__huskies__start_agent` (which moves the story to current as a
+  side-effect of starting an agent).
+- **Archived-dep warning**: if a dep was satisfied via `6_archived` rather than
+  `5_done` (e.g. abandoned/superseded), the auto-assigner logs a prominent
+  warning so the user can see the promotion was triggered by an archived dep.
+
+#### Coding → Qa (current → 3_qa)
+
+- Triggered when the coder agent finishes (gates start running).
+- `mcp__huskies__request_qa` is the manual verb.
+
+#### Qa → Coding (qa → current — rejection path)
+
+- `mcp__huskies__reject_qa story_id=X notes="..."` moves qa → current,
+  **clears `review_hold`**, and writes the rejection notes
+  (`agents/lifecycle.rs:210`).
+- Used when a qa agent fails or a human reviewer rejects the work.
+
+#### Qa → Merge (qa → 4_merge)
+
+- Triggered when QA gates pass. `mcp__huskies__move_story_to_merge` is the
+  dedicated verb.
+- For server-mode QA: typed-side `PipelineEvent::QaSkipped` allows going from
+  Coding → Merge directly without entering Qa.
+
+#### Merge → Done (merge → 5_done)
+
+- Mergemaster picks up a story in `4_merge/`, squashes the feature branch onto
+  master, then transitions to `5_done`.
+- `mcp__huskies__move_story_to_merge` queues; mergemaster does the actual work.
+
+#### Done → Archived(Completed) (5_done → 6_archived)
+
+- Auto-sweep after four hours, OR
+- `mcp__huskies__accept_story` (immediate manual archive).
+
+#### Any-stage → Archived(other reasons)
+
+- **Abandoned / Superseded**: today done by `mcp__huskies__move_story
+  target_stage=done` (no first-class verbs for these reasons; see (b) below).
+- **Blocked**: `blocked: true` flag in front matter is set on retry-limit
+  exceedance. `mcp__huskies__unblock_story` clears the flag and resets
+  retry_count.
+- **MergeFailed**: written to front matter when mergemaster fails; auto-assign
+  skips these stories (`has_merge_failure` check).
+- **ReviewHeld**: `review_hold: true` flag is set automatically on spike
+  completion; auto-assign skips these stories until the flag is cleared.
+
+#### Tombstone / purge
+
+- `mcp__huskies__delete_story` and `mcp__huskies__purge_story` permanently
+  remove. Purge writes a CRDT tombstone.
+
+### Auto-assign skip conditions (current production)
+
+`auto_assign_available_work` walks `2_current/`, `3_qa/`, `4_merge/` in order
+and attempts to dispatch a free agent to each unassigned story. It **skips**
+any story that:
+
+1. Has `review_hold: true` in front matter (spikes after QA, manual hold).
+2. Is `frozen` (`is_story_frozen` — pipeline advancement suspended for this story).
+3. Has `blocked: true` (retry limit exceeded; cleared via `unblock_story`).
+4. Has unmet `depends_on` dependencies.
+5. (Merge stage only) Has a recorded merge failure (`has_merge_failure`).
+6. (Merge stage only) Has an empty diff on the feature branch — auto-writes
+   `merge_failure` and blocks immediately rather than wasting a mergemaster turn.
+
+### Front-matter fields that gate transitions
+
+| Field | Type | Effect |
+|---|---|---|
+| `depends_on` | list of story IDs | Blocks backlog → current promotion until all deps are in 5_done or 6_archived |
+| `agent` | string (e.g. `coder-opus`) | Pins the preferred agent for next assignment |
+| `review_hold` | bool | Auto-assign skips this story; cleared by `reject_qa` or manual unblock |
+| `blocked` | bool | Auto-assign skips this story; cleared by `unblock_story` |
+| `frozen` | bool | Auto-assign skips this story; manual unfreeze required |
+| `merge_failure` | string | Auto-assign skips merge-stage agents on this story |
+| `retry_count` | int | Local-only (not in CRDT); incremented by orchestrator |
+
+### Spike-specific behavior
+
+Per the typical lifecycle, a spike runs through `current → qa` like any work
+item, then **stops** in qa awaiting human review (`spikes skip merge`). This
+is implemented via `review_hold: true` being written automatically when a
+spike's qa gates pass. The user accepts (move qa → done) or rejects (move
+qa → current). Spikes do NOT auto-promote to merge.
+
+### Mergemaster lifecycle
+
+The mergemaster agent only runs against stories in `4_merge/`. It:
+
+1. Verifies the feature branch has commits (or the story is auto-blocked).
+2. Squashes the feature branch onto master with a deterministic commit message.
+3. Transitions the story to `5_done` with `merged_at` and `merge_commit`.
+4. On failure beyond the retry budget, writes `merge_failure` and blocks the
+   story (auto-assign then skips it).
+
+### Agent terminated with committed work (bug 645 recovery path)
+
+When a coder agent terminates abnormally (e.g. the Claude Code CLI's
+`output.write(&bytes).is_ok()` PTY write assertion fires mid-session), the
+server-owned completion path detects the crash and checks for surviving work:
+
+1. If the worktree is dirty but has commits ahead of master, reset the
+   uncommitted files (`git checkout . && git clean -fd`) and run gates
+   against the committed code.
+2. If gates still fail but `git log master..HEAD` shows commits and
+   `cargo check` passes, **advance to QA** instead of entering the
+   retry/block path.  This is the "work survived" check, implemented in
+   `server/src/agents/pool/pipeline/advance.rs`.
+3. Agents that die WITHOUT committed work (no commits ahead of master)
+   still follow the existing retry → block path unchanged.
+
+This prevents false-positive blocking of stories where the agent completed
+meaningful work before crashing.
+
+### Watchdog (current production)
+
+The "watchdog" at `server/src/agents/pool/auto_assign/watchdog.rs` runs every
+30 ticks of the unified background loop. Today it does **one** thing: detect
+orphaned agents whose tokio task is `is_finished()` but whose status is still
+`Running` or `Pending`, and mark them `Failed` with an `AgentEvent::Error`
+emission. Bug 624 (now merged) extends it to also enforce `max_turns` and
+`max_budget_usd` limits — an agent over either limit is killed via the
+existing `kill_child_for_key` path and recorded with a typed termination
+reason.
+
+---
+
+## (b) Transitions and behaviors that don't yet exist (or are only partially wired)
+
+### Migration of consumers off legacy strings to typed `Stage` enum
+
+The biggest outstanding piece. `pipeline_state.rs` is `#![allow(dead_code)]`.
+Every consumer (auto-assign, mergemaster, MCP tools, chat commands) still
+works with stage strings (`"2_current"`, `"4_merge"`) and front-matter flags.
+The projection layer (`TryFrom<PipelineItemView> for PipelineItem` and
+friends) exists but isn't called outside tests. Migration is intentionally
+incremental.
+
+**Opportunity**: pick a leaf consumer (e.g. one MCP tool that reads the stage
+string) and migrate it to read `Stage` instead. Pattern repeats outward until
+all consumers go through the typed projection and the legacy stage-string
+code can be deleted.
+
+### First-class verbs for archive reasons
+
+`ArchiveReason` already has six variants but only `Completed` (via
+`accept_story`) and `Blocked` (via the `blocked: true` flag) have dedicated
+MCP verbs. Today, `Abandoned`, `Superseded`, `MergeFailed`, and `ReviewHeld`
+are reached either via `move_story target_stage=done` (which doesn't carry
+the reason) or via setting front-matter flags on the live story.
+
+**Missing transitions**:
+
+- `mcp__huskies__supersede_story story_id=X by=Y` — sets stage to
+  `Archived { reason: Superseded { by: Y } }`. Today we use
+  `move_story → done`, losing the `by` reference. (Came up 2026-04-25 with
+  spike 621 → refactor 623.)
+- `mcp__huskies__abandon_story story_id=X reason="..."` — sets
+  `Archived { reason: Abandoned }`. Today done via `move_story → done` or
+  `purge_story`.
+- `mcp__huskies__hold_for_review story_id=X reason="..."` — explicitly puts
+  a story in `Archived { reason: ReviewHeld }` rather than relying on the
+  auto-set `review_hold` flag.
+
+### Type-conversion transitions
+
+Spike → story conversion is a real workflow (we do it when a spike's scope
+grows into an implementation story). Today, converting type via `update_story
+front_matter={"type": "story"}` does not bootstrap the
+`## Acceptance Criteria` section, and `add_criterion` then permanently fails
+on that story (see **bug 625** filed 2026-04-25). The `type` field passed via
+front_matter is also silently dropped — same silent-drop bug class as
+`acceptance_criteria`. The state machine should treat type conversion as a
+transition with side effects — at minimum, ensuring the AC section exists
+when transitioning to a type that requires it, and the displayed type
+reflects the new value (today the display chip is parsed from the immutable
+story_id prefix; story 578 in backlog will fix this by switching to
+numeric-only IDs).
+
+### Limit-based agent termination (turn / budget)
+
+Pre-624 master: `max_turns` and `max_budget_usd` per-agent config were read
+by the metric tool (`tool_get_agent_remaining_turns_and_budget`) but **not
+enforced** anywhere. Observed `coder-1` running 282/50 turns and $10.05/$5.00
+USD on story 623 before a human stopped it (bug 624, now merged).
+
+The bug 624 fix adds enforcement to the watchdog. The state-machine impact:
+introduces a new agent-termination path distinct from "Failed (orphan)" —
+something like `Failed(LimitExceeded { kind: Turns | Budget })`. The
+`ExecutionState` enum may want a corresponding terminal variant so it can be
+distinguished from generic `Failed`.
+
+### Pinned-agent honoring under contention
+
+When a story has `agent: coder-opus` pinned but `coder-opus` is busy, today's
+auto-assign behavior is to leave the story unassigned — but if a human stops
+the running attempt and the story sits in `current/`, auto-assign **re-grabs
+it with the default coder** rather than waiting for the pinned agent.
+Observed multiple times on 2026-04-25 with story 623: pinning `coder-opus`
+did not prevent `coder-1` (sonnet) from being auto-assigned during opus's
+busy window.
+
+**Missing behavior**: auto-assign should treat a pinned agent as a hard
+filter ("only this agent can take this story"), not a preference. Today the
+workaround is to also set `depends_on` on a phantom story, or move the story
+back to backlog and let the dependency system gate it.
+
+### Honoring the `blocked` flag (bug 559)
+
+`559_bug_mergemaster_ignores_blocked_flag_and_keeps_respawning_on_blocked_stories`
+is in backlog. Even though `blocked: true` is documented as a skip condition
+in `auto_assign_available_work`, mergemaster's spawn path apparently checks
+something different (or earlier) and respawns on blocked merge-stage stories.
+The state machine should make `Stage::Archived { reason: Blocked }` a single
+authoritative source so no consumer can incidentally bypass it.
+
+### Formal "ghost story recovery" transition
+
+The `move_story` MCP tool description mentions "recovering a ghost story by
+moving it back to current" as a valid use. Ghost stories are CRDT entries
+with no corresponding filesystem stage directory (or the inverse). Today this
+is an `update_story + move_story` ad-hoc dance. A first-class
+`recover_ghost_story` verb that reconciles the CRDT and filesystem would
+formalize the recovery path.
+
+### Operator-level visibility / observability
+
+There is no UI, CLI, or doc that shows "the state machine as a diagram." The
+typed enums are the closest thing to a canonical specification, but they
+aren't rendered anywhere a human can see at a glance: which stages exist,
+which transitions are valid, which events trigger them. A generated state
+diagram (graphviz or mermaid, dumped into this doc on each release) would
+help both new contributors and operators triaging stuck pipelines.
+
+### Review-hold cleanup verb
+
+`review_hold: true` is set automatically on spike completion. Clearing it is
+done as a side effect of `reject_qa` (which also moves the story qa →
+current) or by manually editing front matter. There is no clean "I have
+reviewed this, release the hold" verb that doesn't also move the story.
+
+### Cross-node concurrency for execution state
+
+`ExecutionState` is per-node (keyed by pubkey) so two nodes can't fight over
+who's running an agent. But there is no formal transition that says "node A
+hands the story to node B" if node A goes offline. The state machine's
+distributed semantics for this case are not yet specified.
+
+---
+
+## How to update this document
+
+Whenever you discover a transition that doesn't yet exist, or a flag that
+behaves surprisingly, add it to **section (b)** with:
+
+- A short description of the desired behavior
+- Citation of the work item or incident that surfaced it
+- Pointer to the place in `pipeline_state.rs` where it should be modeled (or
+  note "needs a new variant" if it doesn't fit any existing enum yet)
+
+When a transition from (b) ships, move it to (a) with the relevant file:line
+citations.

.huskies/work/1_backlog/408_spike_fly_io_machines_api_integration_for_multi_tenant_storkit_saas.md

@@ -1,8 +1,8 @@
 ---
-name: "Fly.io Machines API integration for multi-tenant storkit SaaS"
+name: "Fly.io Machines API integration for multi-tenant huskies SaaS"
 ---
 
-# Spike 408: Fly.io Machines API integration for multi-tenant storkit SaaS
+# Spike 408: Fly.io Machines API integration for multi-tenant huskies SaaS
 
 ## Question
 
@@ -28,7 +28,7 @@ A thin Rust service using `reqwest` for the Machines API and `axum` for the reve
 - [ ] Test attaching a persistent volume to a machine and verify it persists across stop/start
 - [ ] Test secret injection — pass a dummy `credentials.json` as a Fly secret and verify it's readable inside the machine
 - [ ] Sketch the auth proxy: JWT validation → machine lookup → reverse proxy to machine's private IP; verify WebSocket proxying works
-- [ ] Measure actual cold start time for a minimal storkit container image
+- [ ] Measure actual cold start time for a minimal huskies container image
 - [ ] Document any API quirks, rate limits, or sharp edges discovered during testing
 
 ## Findings

.huskies/work/1_backlog/411_story_multi_account_oauth_token_rotation_on_rate_limit.md

@@ -6,13 +6,13 @@ name: "Multi-account OAuth token rotation on rate limit"
 
 ## User Story
 
-As a storkit user with multiple Claude Max subscriptions, I want the system to automatically rotate to a different account when one gets rate limited, so that agents and chat don't stall out waiting for limits to reset.
+As a huskies user with multiple Claude Max subscriptions, I want the system to automatically rotate to a different account when one gets rate limited, so that agents and chat don't stall out waiting for limits to reset.
 
 ## Acceptance Criteria
 
 - [ ] OAuth login flow stores credentials per-account (keyed by email), not overwriting previous accounts
 - [ ] GET /oauth/status returns all stored accounts and their status (active, rate-limited, expired)
-- [ ] When the active account hits a rate limit, storkit automatically swaps to the next available account's refresh token, refreshes, and retries
+- [ ] When the active account hits a rate limit, huskies automatically swaps to the next available account's refresh token, refreshes, and retries
 - [ ] The bot sends a notification in Matrix/WhatsApp when it swaps accounts
 - [ ] If all accounts are rate limited, the bot surfaces a clear message with the time until the earliest reset
 - [ ] A new /oauth/authorize login adds to the account pool rather than replacing the current credentials

.huskies/work/1_backlog/436_refactor_unify_story_stuck_states_into_a_single_status_field.md

@@ -1,5 +1,7 @@
 ---
 name: "Unify story stuck states into a single status field"
+status: "superseded"
+superseded_by: 520
 ---
 
 # Refactor 436: Unify story stuck states into a single status field

.huskies/work/1_backlog/479_story_build_agent_mode_with_crdt_based_work_claiming.md

@@ -0,0 +1,24 @@
+---
+name: "Build agent mode with CRDT-based work claiming"
+agent: coder-opus
+depends_on: [478]
+---
+
+# Story 479: Build agent mode with CRDT-based work claiming
+
+## User Story
+
+As a user with multiple laptops, I want to run huskies in build agent mode so it connects to the mesh, syncs state, and autonomously picks up and runs coding work.
+
+## Acceptance Criteria
+
+- [ ] New CLI mode: huskies agent --rendezvous ws://host:3001
+- [ ] Agent mode: syncs CRDT state, runs coders, no web UI or chat interface
+- [ ] Work claiming via CRDT: node writes claim (node ID) to CRDT doc, merge resolves conflicts deterministically, losing node stops work
+- [ ] Agent picks up stories in current stage and runs Claude Code locally
+- [ ] Agent pushes feature branch to Gitea when done, reports completion via CRDT
+- [ ] Handles offline/reconnect: CRDT merges on reconnect, interrupted work is reclaimed after timeout
+
+## Out of Scope
+
+- TBD

.huskies/work/1_backlog/480_story_cryptographic_node_auth_for_distributed_mesh.md

@@ -0,0 +1,23 @@
+---
+name: "Cryptographic node auth for distributed mesh"
+agent: coder-opus
+depends_on: [479]
+---
+
+# Story 480: Cryptographic node auth for distributed mesh
+
+## User Story
+
+As a user running a distributed huskies mesh, I want nodes authenticated by Ed25519 keypairs so only trusted machines can join and see pipeline state.
+
+## Acceptance Criteria
+
+- [ ] Each node has an Ed25519 keypair (generated on first run or via CLI command)
+- [ ] Trusted nodes defined by a list of known public keys in config
+- [ ] Nodes authenticate on WebSocket connect by signing a challenge
+- [ ] CRDT node ID derived from public key (already built into bft-json-crdt crate)
+- [ ] Unauthorised nodes rejected on connect
+
+## Out of Scope
+
+- TBD

.huskies/work/1_backlog/486_bug_create_worktree_deletes_all_files_from_main_branch_git_index.md

@@ -0,0 +1,25 @@
+---
+name: "create_worktree deletes all files from main branch git index"
+---
+
+# Bug 486: create_worktree deletes all files from main branch git index
+
+## Description
+
+On the reclaimer project, the create_worktree operation for story 34 produced a commit (cea0c48) with message "huskies: create 34_story_drawer_open_pushes_main_view_aside_with_animation" that removed 76 files (9853 deletions) from the main branch git index. All files remained on disk — nothing was lost — but every tracked file became untracked. Static analysis of the watcher code (watcher.rs:152-185) shows git add -A .huskies/work/ with correct current_dir, which should only affect files under .huskies/work/. No other code path in the server runs git add without a pathspec on the main branch. Root cause is unknown — may be related to the storkit→huskies migration leaving the git index in an inconsistent state, or a race condition during first-time scaffold on a project that previously used .storkit/.
+
+## How to Reproduce
+
+1. Uncertain — may require fresh huskies setup on a project that previously used storkit. 2. Create a story via the bot or MCP tool. 3. Observe that the auto-commit for story creation removes all tracked files from the git index.
+
+## Actual Result
+
+The commit for story creation deleted 76 files (9853 deletions) from the git index while leaving them on disk.
+
+## Expected Result
+
+The commit for story creation should only add the new story markdown file under .huskies/work/1_backlog/. No other files should be affected.
+
+## Acceptance Criteria
+
+- [ ] Bug is fixed and verified

.huskies/work/1_backlog/498_bug_stale_merge_job_lock_prevents_new_merges_after_agent_dies.md

@@ -0,0 +1,32 @@
+---
+name: "Stale merge job lock prevents new merges after agent dies"
+---
+
+# Bug 498: Stale merge job lock prevents new merges after agent dies
+
+## Description
+
+When the mergemaster agent is killed or stops while a merge is in progress, the in-memory `merge_jobs` map retains a `Running` status entry for that story. Subsequent attempts to call `merge_agent_work` get "Merge already in progress" and fail. The lock is never cleaned up.
+
+This causes the mergemaster to loop: spawn, try merge, get "already in progress", waste turns, exit, respawn. The merge never completes.
+
+The fix: clear the merge job entry when the mergemaster agent exits (whether cleanly or via kill/stop).
+
+## How to Reproduce
+
+1. Start mergemaster on a story in merge
+2. Kill/stop the mergemaster agent before merge completes
+3. Try to merge_agent_work again for the same story
+4. Get "Merge already in progress" error
+
+## Actual Result
+
+Stale Running entry in merge_jobs map blocks all future merge attempts until server restart.
+
+## Expected Result
+
+Merge job lock is cleaned up when the agent exits, allowing retry.
+
+## Acceptance Criteria
+
+- [ ] Bug is fixed and verified

.huskies/work/1_backlog/511_bug_crdt_lamport_clock_inner_seq_resets_to_1_on_server_restart_instead_of_resuming_from_max_own_author_seq_1.md

@@ -0,0 +1,72 @@
+---
+name: "CRDT lamport clock (inner.seq) resets to 1 on server restart instead of resuming from max(own_author_seq) + 1"
+---
+
+# Bug 511: CRDT lamport clock (inner.seq) resets to 1 on server restart instead of resuming from max(own_author_seq) + 1
+
+## Description
+
+When the huskies server restarts (e.g. via `rebuild_and_restart`), the local node's CRDT lamport clock — `inner.seq` on each `SignedOp` — appears to reset to 1 instead of resuming from `MAX(seq) + 1` for the local author's own previously-persisted ops.
+
+**Discovered live on 2026-04-09** while inspecting the `crdt_ops` table after a `rebuild_and_restart`. Pre-restart ops were at seqs 485-492 (creation ops for stories 503-510). Post-restart ops were being persisted at seqs 1, 2, 3, 4, 5, 6, 7 — visible by sorting `crdt_ops` by `created_at DESC`:
+
+```
+created_at                              | seq
+2026-04-09T18:49:56  → seq 7      ← post-restart
+2026-04-09T18:38:22  → seq 6      ← post-restart
+2026-04-09T18:37:45  → seq 492    ← pre-restart, last write before restart
+2026-04-09T18:31:32  → seq 4      ← post-restart
+2026-04-09T18:27:04  → seq 3      ← post-restart
+```
+
+So the local node, which had reached seq=492 before the restart, started writing new ops at seq=1 after the restart and is now climbing from there. This means **new ops have lower seqs than existing ops from the same author**.
+
+## Why this matters
+
+In a BFT JSON CRDT, `inner.seq` is the local lamport clock used for causality tracking. The library assumes per-author seqs are monotonically increasing — newer ops from the same author have higher seqs than older ops. Several things break when this invariant is violated:
+
+1. **Causality / ordering on remote replay.** When a peer (or this same node after another restart) replays the persisted ops in `seq` order, the post-restart ops will be applied *before* the pre-restart ops, even though they happened later. This can produce a non-deterministic state and can cause field updates to "go backwards" — e.g. a story that was moved current → done pre-restart, then nothing post-restart, would correctly end at "done"; but if you also did a post-restart action, the seq ordering would re-play it in the wrong order.
+
+2. **Op ID collisions.** The op id is a hash of the op contents (including author, seq, content). If a post-restart op happens to be structurally identical to a pre-restart op (e.g. "set stage to 1_backlog" with the same author and same seq=3), the op ids could collide. The persistence path uses `INSERT INTO crdt_ops ... ON CONFLICT(op_id) DO NOTHING`, which would *silently drop* the new op. (We have not yet observed this happen, but it's a latent risk.)
+
+3. **Sync between nodes will desync.** Once the WebSocket sync layer (story 478, just merged) is exchanging ops between nodes, a restart on one node will produce ops with seqs that look "old" to the other node, and the receiving node may de-dupe or mis-order them. This will manifest as silent state divergence in multi-node deployments, which is exactly what the sync layer is supposed to prevent.
+
+4. **Today's pipeline state confusion.** The 8 stories I created in this session (503-510) are at seqs 485-492 in the persisted CRDT. Their post-restart lifecycle moves are at seqs 1-15. If we replay the CRDT from disk in seq order, the lifecycle moves will be applied to *empty* state before the creation ops have run, and will silently no-op (because they reference content indexes that don't exist yet). On the next restart after this state, the in-memory view will show the stories in their *creation* state, not their post-restart-lifecycle state — i.e. all 8 stories will appear "stuck at 1_backlog" again. **This may well be the cause of bug 510's split-brain symptom**.
+
+## Where the bug lives
+
+`server/src/crdt_state.rs::init()` (around lines 80-115) replays persisted ops to reconstruct state, then constructs a fresh `CrdtState { crdt, keypair, index, persist_tx }`. The `BaseCrdt::new(&keypair)` call constructs a fresh CRDT with a fresh internal seq counter. The replay re-applies ops via `crdt.apply(signed_op)` which presumably updates the doc but does NOT advance the local seq counter (because `apply()` is for *remote* ops).
+
+After replay, the local seq counter is at 0 (or wherever the BFT CRDT library defaults). The next call to `apply_and_persist` produces an op with `inner.seq = 1` (or whatever the next-counter value is) — even though there are already ops at seq 485+ from this author in the persisted state.
+
+The fix is to inspect `MAX(inner.seq)` for ops where `author == local_keypair.public()` after the replay, and seed the BFT CRDT's local seq counter from `max + 1`. The exact API for "seed the seq counter" depends on the bft-json-crdt library — may need a small upstream change if not already exposed.
+
+## How to Reproduce
+
+1. Start a fresh huskies server with an empty database. Verify `crdt_ops` is empty.
+2. Create several stories via `create_story` or similar — observe ops being persisted at incrementing seqs (1, 2, 3, ...).
+3. Note the highest seq via `sqlite3 .huskies/pipeline.db "SELECT MAX(seq) FROM crdt_ops;"` — call this N.
+4. Stop the server and start it again (or `rebuild_and_restart`).
+5. Create another story via `create_story`.
+6. Query `SELECT seq, created_at FROM crdt_ops ORDER BY created_at DESC LIMIT 5;`
+
+## Actual Result
+
+The new op (just created in step 5) is persisted with `seq = 1` (or some small value), NOT `seq = N + 1`. The lamport clock has been reset.
+
+Concretely on 2026-04-09 we observed seqs in `crdt_ops` ordered by `created_at` DESC of: 7, 6, 492, 4, 3 — i.e. post-restart writes were at seqs 3, 4, 6, 7 even though the highest pre-restart seq was 492.
+
+## Expected Result
+
+After restart, the local node's seq counter must resume from `MAX(inner.seq)` across all persisted ops where `author == local_keypair.public()`, plus 1. The next op written by the local node should have `seq = N + 1` where N is the previous local high-water mark.
+
+Equivalent stated: `inner.seq` on the local author's ops must be monotonically increasing across the entire lifetime of the local node's keypair, not just within a single process invocation.
+
+## Acceptance Criteria
+
+- [ ] After a server restart, the next CRDT op written by the local node has seq = MAX(local_author_seq from crdt_ops) + 1, not 1
+- [ ] Regression test: seed crdt_ops with an op at seq=100 by the local author, restart the CRDT subsystem (or call init() in a test harness), trigger a write_item, assert the new op has seq=101
+- [ ] Regression test: a brand-new node (no pre-existing ops) still starts at seq=1 (no off-by-one introduced by the fix)
+- [ ] Inter-node test: simulate two nodes A and B, A writes ops up to seq=50, A restarts, A writes a new op which should be seq=51, broadcast to B, assert B applies it in the correct causal position
+- [ ] If the fix requires changes to bft-json-crdt itself (to expose a way to seed the local seq), the upstream change is documented in the bug body and either landed or vendored
+- [ ] After this fix is in place, replay-on-restart for the existing data (8 stories in pipeline_items at seqs 485-492 with lifecycle moves at seqs 1-15) is verified to produce the correct in-memory state — OR the existing broken-seq data is migrated as part of the fix

.huskies/work/1_backlog/512_story_migrate_chat_commands_from_filesystem_lookup_to_crdt_db.md

@@ -0,0 +1,58 @@
+---
+name: "Migrate chat commands from filesystem lookup to CRDT/DB"
+---
+
+# Story 512: Migrate chat commands from filesystem lookup to CRDT/DB
+
+## User Story
+
+**Depends on story 520** (typed pipeline state machine). This story is best implemented as a *consumer* of the typed transition API, not against the loose `PipelineItemView`. Wait for 520 to land first, then migrate the chat command lookups to use the typed `find_story_by_number → Result<PipelineItem, _>` helper from the new module.
+
+---
+
+**Note:** content stuffed into user_story per bug 509 workaround.
+
+## Context
+
+All the slash-style chat commands in `server/src/chat/commands/{move_story,show,depends,unblock}.rs` and `server/src/chat/transport/matrix/{start,assign,delete}.rs` look up stories by **searching for `.huskies/work/*/N_*.md` filesystem files**. After the 491/492 migration moved story content out of the filesystem and into `pipeline_items` + CRDT, these commands silently fail with `"No story, bug, or spike with number {N} found"` for any story whose filesystem shadow doesn't exist — *even when the story is fully present in the DB and CRDT*.
+
+## Real user story
+
+As a user typing chat commands in the web UI or the matrix bot, I want move/show/depends/unblock/start/assign/delete to find any story that's in the pipeline regardless of whether its filesystem shadow exists, so the chat workflow stays usable post-migration.
+
+## Observed 2026-04-09
+
+Master commit `41515e3b` had 503's code, the in-memory CRDT view had 503 at stage='merge', the `pipeline_items` row existed (post my-sqlite-update at `5_done`), but `move 503 done` in the web UI returned **`No story, bug, or spike with number 503 found`** because no `.huskies/work/4_merge/503_*.md` file existed.
+
+## Implementation note
+
+The MCP `move_story` tool already does this correctly: it goes through `lifecycle::move_item` which checks `crdt_state::read_item(story_id)` first. The chat commands need to use the same lookup helper. The fix should consolidate all "find story by number" logic into one shared function used by every command.
+
+## Context
+
+All the slash-style chat commands in `server/src/chat/commands/{move_story,show,depends,unblock}.rs` and `server/src/chat/transport/matrix/{start,assign,delete}.rs` look up stories by **searching for `.huskies/work/*/N_*.md` filesystem files**. After the 491/492 migration moved story content out of the filesystem and into `pipeline_items` + CRDT, these commands silently fail with `"No story, bug, or spike with number {N} found"` for any story whose filesystem shadow doesn't exist — *even when the story is fully present in the DB and CRDT*.
+
+## Real user story
+
+As a user typing chat commands in the web UI or the matrix bot, I want move/show/depends/unblock/start/assign/delete to find any story that's in the pipeline regardless of whether its filesystem shadow exists, so the chat workflow stays usable post-migration.
+
+## Observed 2026-04-09
+
+Master commit `41515e3b` had 503's code, the in-memory CRDT view had 503 at stage='merge', the `pipeline_items` row existed (post my-sqlite-update at `5_done`), but `move 503 done` in the web UI returned **`No story, bug, or spike with number 503 found`** because no `.huskies/work/4_merge/503_*.md` file existed.
+
+## Implementation note
+
+The MCP `move_story` tool already does this correctly: it goes through `lifecycle::move_item` which checks `crdt_state::read_item(story_id)` first. The chat commands need to use the same lookup helper. The fix should consolidate all "find story by number" logic into one shared function used by every command.
+
+## Acceptance Criteria
+
+- [ ] All seven chat commands (move_story, show, depends, unblock, start, assign, delete) successfully find stories that exist in CRDT but have no filesystem shadow
+- [ ] Backward compat: commands still work for stories with only filesystem shadows (during the migration window)
+- [ ] A single shared `find_story_by_number` helper is introduced and used by every chat command
+- [ ] Lookup priority order is documented and consistent: CRDT first, then pipeline_items, then filesystem fallback
+- [ ] Regression test per command covering CRDT-only, filesystem-only, both-present, and not-found cases
+- [ ] Observed repro from 2026-04-09 (move 503 done failing even though 503 was fully present in CRDT and pipeline_items) is the canonical regression case
+
+## Out of Scope
+
+- TBD

.huskies/work/1_backlog/513_story_startup_reconcile_pass_that_detects_drift_between_crdt_pipeline_items_and_filesystem_shadows.md

@@ -0,0 +1,55 @@
+---
+name: "Startup reconcile pass that detects drift between CRDT, pipeline_items, and filesystem shadows"
+---
+
+# Story 513: Startup reconcile pass that detects drift between CRDT, pipeline_items, and filesystem shadows
+
+## User Story
+
+**Note:** content stuffed into user_story per bug 509 workaround.
+
+---
+
+## Context
+
+Post-491/492, huskies has **four places state lives** that can drift apart:
+
+1. `crdt_ops` table — the persisted CRDT operation log (intended source of truth)
+2. In-memory CRDT view — `state.crdt.doc.items` reconstructed from `crdt_ops` on startup, mutated by `apply_and_persist` during runtime
+3. `pipeline_items` table — a shadow / materialised view, written to as a shadow alongside CRDT writes
+4. Filesystem shadows in `.huskies/work/N_stage/*.md` — legacy rendering, still written by some paths and read by others
+
+There is currently **no reconcile pass** that detects drift between them. We've watched this drift bite repeatedly today: stories appear in some views and not others, lifecycle moves happen in one but not another, my direct sqlite UPDATE was invisible to the API, etc. Each individual view looks "fine" in isolation, but the drift only becomes visible when a user notices a story behaving inconsistently.
+
+## Real user story
+
+As a developer or operator running huskies, I want a startup reconcile pass that compares all four state sources and either reconciles them automatically (preferred) or logs structured warnings about the drift, so I can detect and diagnose state corruption before it causes user-visible bugs.
+
+## Observed 2026-04-09
+
+Throughout this session we observed: 478 in pipeline_items but missing from CRDT (after a direct sqlite insert), 503 in CRDT at stage=merge but pipeline_items at stage=5_done (after my UPDATE), filesystem shadows in `1_backlog/` for stories that were already in 5_done in the DB (bug 510), etc. None of these were detected by huskies itself — they were all only found by running ad-hoc `SELECT` queries during incident response.
+
+## Scope
+
+This is the *detection* story, not the *fix-the-drift* story. The reconcile pass should:
+
+- Run at startup (after CRDT replay, before serving requests)
+- Compare each story's stage across all four sources
+- Emit structured log lines for each drift type (CRDT-only, FS-only, DB-only, stage mismatch, etc.)
+- Optionally surface a count to the matrix bot startup announcement (e.g. "⚠️ 3 stories have CRDT/DB drift — see logs")
+
+The actual *fix-the-drift* logic (what to do when drift is detected) is a separate, larger story.
+
+## Acceptance Criteria
+
+- [ ] At server startup, after CRDT replay, a reconcile_state() function runs that walks all four state sources and detects drift
+- [ ] Each drift type is logged with a structured line: e.g. `[reconcile] DRIFT story=X crdt_stage=Y db_stage=Z fs_stage=W` (or `MISSING` for absent)
+- [ ] If any drift is detected, the matrix bot startup announcement includes a count and a suggestion to check the server logs
+- [ ] The reconcile pass completes in < 1 second for a typical pipeline (~100 stories) so it doesn't slow startup meaningfully
+- [ ] Tests cover: no drift (clean state), CRDT-only story, DB-only story, FS-only story, stage mismatch between CRDT and DB
+- [ ] Documentation in README.md explains the reconcile pass and what each drift type means
+- [ ] The pass is opt-out via a config flag in case it produces noise during the migration window
+
+## Out of Scope
+
+- TBD

.huskies/work/1_backlog/514_story_delete_story_should_do_a_full_cleanup_crdt_op_db_row_filesystem_shadow_worktree_pending_timers.md

@@ -0,0 +1,94 @@
+---
+name: "delete_story should do a full cleanup (CRDT op + DB row + filesystem shadow + worktree + pending timers)"
+---
+
+# Story 514: delete_story should do a full cleanup (CRDT op + DB row + filesystem shadow + worktree + pending timers)
+
+## User Story
+
+**Depends on story 520** (typed pipeline state machine). With 520 in place, `delete_story` becomes a single typed transition (`* → Archived(Abandoned)` or a hard-delete CRDT op) followed by event subscribers that handle the worktree, timers, and filesystem cleanup. This story should be re-shaped as the consumer migration once 520 lands.
+
+---
+
+**Note:** content stuffed into user_story per bug 509 workaround.
+
+## Context
+
+The MCP `delete_story` tool currently only **removes the filesystem markdown** from `.huskies/work/N_stage/`. It does NOT:
+
+- Remove the row from `pipeline_items`
+- Write a CRDT delete op to `crdt_ops`
+- Tear down the in-memory CRDT entry
+- Remove the `.huskies/worktrees/N_…/` worktree
+- Cancel any pending rate-limit retry timers in `.huskies/timers.json`
+
+So after `delete_story`, the story keeps appearing in `get_pipeline_status` (because the in-memory CRDT still has it), the timer fires and re-spawns an agent, the agent runs in the still-existing worktree, and the user has no idea why the "deleted" story keeps coming back.
+
+## Real user story
+
+As a user calling `delete_story` (via MCP, web UI, or chat command), I want a complete tear-down of all state associated with that story across every layer, so the story is actually gone — no in-memory cache entries, no pending agents, no timers, no worktree, no shadow files, no future spawns.
+
+## Observed 2026-04-09
+
+Repeatedly throughout the session. The most concrete example was around 17:20: I called `delete_story 478_…`, the tool returned success, the markdown file at `.huskies/work/1_backlog/478_…md` was removed, but at 17:25:17 the rate-limit retry timer fired and **re-spawned a coder-1 on the deleted story** because the worktree still existed, the pipeline_items row still existed, and the timer entry still existed in `.huskies/timers.json`. We then had to do sqlite surgery + manual worktree removal + manual timers.json edit to actually kill 478.
+
+## Implementation note
+
+The current `delete_story` is on the legacy filesystem path. The fix needs to wrap it in a transaction that touches every layer:
+
+1. Cancel any pending timers for this story_id (read timers.json, filter, write back)
+2. Stop any running/pending agents for this story_id (call `agent_pool.stop_agent` for each)
+3. Remove the worktree if it exists (`git worktree remove`)
+4. Write a CRDT delete op (`apply_and_persist` with a delete op)
+5. Wait for the persist task to confirm
+6. Delete the row from `pipeline_items` directly (or trust the materialiser to drop it)
+7. Remove the filesystem shadow
+
+Each step should be best-effort with logging — partial failures should be visible, not silent.
+
+## Context
+
+The MCP `delete_story` tool currently only **removes the filesystem markdown** from `.huskies/work/N_stage/`. It does NOT:
+
+- Remove the row from `pipeline_items`
+- Write a CRDT delete op to `crdt_ops`
+- Tear down the in-memory CRDT entry
+- Remove the `.huskies/worktrees/N_…/` worktree
+- Cancel any pending rate-limit retry timers in `.huskies/timers.json`
+
+So after `delete_story`, the story keeps appearing in `get_pipeline_status` (because the in-memory CRDT still has it), the timer fires and re-spawns an agent, the agent runs in the still-existing worktree, and the user has no idea why the "deleted" story keeps coming back.
+
+## Real user story
+
+As a user calling `delete_story` (via MCP, web UI, or chat command), I want a complete tear-down of all state associated with that story across every layer, so the story is actually gone — no in-memory cache entries, no pending agents, no timers, no worktree, no shadow files, no future spawns.
+
+## Observed 2026-04-09
+
+Repeatedly throughout the session. The most concrete example was around 17:20: I called `delete_story 478_…`, the tool returned success, the markdown file at `.huskies/work/1_backlog/478_…md` was removed, but at 17:25:17 the rate-limit retry timer fired and **re-spawned a coder-1 on the deleted story** because the worktree still existed, the pipeline_items row still existed, and the timer entry still existed in `.huskies/timers.json`. We then had to do sqlite surgery + manual worktree removal + manual timers.json edit to actually kill 478.
+
+## Implementation note
+
+The current `delete_story` is on the legacy filesystem path. The fix needs to wrap it in a transaction that touches every layer:
+
+1. Cancel any pending timers for this story_id (read timers.json, filter, write back)
+2. Stop any running/pending agents for this story_id (call `agent_pool.stop_agent` for each)
+3. Remove the worktree if it exists (`git worktree remove`)
+4. Write a CRDT delete op (`apply_and_persist` with a delete op)
+5. Wait for the persist task to confirm
+6. Delete the row from `pipeline_items` directly (or trust the materialiser to drop it)
+7. Remove the filesystem shadow
+
+Each step should be best-effort with logging — partial failures should be visible, not silent.
+
+## Acceptance Criteria
+
+- [ ] delete_story returns success only when ALL of the following are true: no row in pipeline_items, no op in crdt_ops referencing the story_id (or a delete op present), no in-memory CRDT entry, no worktree directory, no timer entries, no filesystem shadow
+- [ ] Each tear-down step has its own log line so partial failures are diagnosable
+- [ ] If any tear-down step fails, the tool returns an error with which step failed and what was already torn down (so the user can finish the cleanup manually)
+- [ ] After delete_story, the story does NOT appear in get_pipeline_status, the web UI, or list_agents
+- [ ] After delete_story, no rate-limit retry timer can re-spawn an agent on the deleted story
+- [ ] Regression test using the 2026-04-09 repro: schedule a rate-limit timer for the story, call delete_story, fast-forward 5 minutes, assert no agent spawned
+
+## Out of Scope
+
+- TBD

.huskies/work/1_backlog/515_story_add_a_debug_mcp_tool_to_dump_the_in_memory_crdt_state_for_inspection.md

@@ -0,0 +1,54 @@
+---
+name: "Add a debug MCP tool to dump the in-memory CRDT state for inspection"
+---
+
+# Story 515: Add a debug MCP tool to dump the in-memory CRDT state for inspection
+
+## User Story
+
+**Note:** content stuffed into user_story per bug 509 workaround.
+
+---
+
+## Context
+
+When diagnosing CRDT/state issues today, we had no way to look at the **in-memory** CRDT state directly. The closest available views were:
+
+- `get_pipeline_status` — gives a summarised pipeline-shaped view (active/backlog/done) but hides the raw item structure, the index map, the lamport clock state, etc.
+- Querying `crdt_ops` directly via sqlite — gives the *persisted* state, which can diverge from the in-memory state (we saw this with bug 511, where post-restart writes use reset seq counters)
+- `read_item(story_id)` in `crdt_state.rs` — exists, returns a `PipelineItemView`, but is not exposed via MCP or HTTP
+
+The result: every time I needed to check the CRDT state, I was either inferring it from `get_pipeline_status` (lossy) or querying the persisted ops (lagging the in-memory state). Neither gave me the ground truth.
+
+## Real user story
+
+As a developer debugging huskies state issues, I want an MCP tool (or HTTP debug endpoint) that returns a structured dump of the in-memory CRDT state, so I can see exactly what the running server thinks is true without inferring from summaries.
+
+## Suggested API
+
+- Tool name: `mcp__huskies__dump_crdt`
+- Args: optional `story_id` filter (single story) or no args (dump everything)
+- Returns: JSON with one entry per item containing: `story_id`, all field values (`stage`, `name`, `agent`, `retry_count`, `blocked`, `depends_on`), the CRDT path/index bytes (for cross-referencing with `crdt_ops`), the local lamport seq counter, and a flag indicating whether the item is `is_deleted`
+- Returns metadata: total item count, current local seq counter value, count of pending ops in `persist_tx` channel (if observable)
+
+## Observed 2026-04-09
+
+This story would have saved us significant debugging time. Specific examples:
+
+- When 478 was missing from `get_pipeline_status` after the manual sqlite insert, we had to infer "the API reads from in-memory CRDT, not from pipeline_items" by looking at source code. A `dump_crdt 478_…` call would have returned "not found" immediately, confirming the same conclusion.
+- When 503 was showing at stage=merge in the API but only had a creation op at stage=1_backlog in `crdt_ops`, we had to manually search for content-indexed update ops to figure out where the post-restart updates went. A dump tool showing the current in-memory state vs the persisted op count would have made the divergence obvious.
+
+## Acceptance Criteria
+
+- [ ] New MCP tool `dump_crdt` is registered and callable
+- [ ] With no args, returns all items in the in-memory CRDT as a structured JSON list
+- [ ] With a story_id arg, returns just that one item (or null if not found)
+- [ ] Each item entry includes: story_id, stage, name, agent, retry_count, blocked, depends_on, content_index (hex), is_deleted
+- [ ] Returns top-level metadata: total_items, max_local_seq, pending_persist_ops_count (if available), in_memory_state_loaded (bool)
+- [ ] Tool description is clear that this is a debug tool, not for normal pipeline introspection (those should use get_pipeline_status)
+- [ ] Optional: also expose via HTTP at `/debug/crdt` for browser inspection
+- [ ] Documented in README.md under a 'debugging' section
+
+## Out of Scope
+
+- TBD

.huskies/work/1_backlog/516_story_update_story_description_should_create_the_description_section_if_it_doesn_t_exist_instead_of_erroring.md

@@ -0,0 +1,53 @@
+---
+name: "update_story.description should create the ## Description section if it doesn't exist (instead of erroring)"
+---
+
+# Story 516: update_story.description should create the ## Description section if it doesn't exist (instead of erroring)
+
+## User Story
+
+**Note:** content stuffed into user_story per bug 509 workaround.
+
+---
+
+## Context
+
+The MCP `update_story` tool's `description` parameter "replaces the `## Description` section content". If the section doesn't exist in the story file, the call **errors out** with `Section '## Description' not found in story file.`
+
+This becomes a real problem when:
+
+1. A story was created via `create_story` (which is buggy per 509 and writes a stub template with no `## Description` section)
+2. The user later wants to add a description via `update_story`
+3. The update fails with the cryptic "section not found" error
+
+We hit this exact scenario today: after bug 509 dropped the descriptions of 6 stories (500, 504, 505, 506, 507, 508), I tried to recover them by calling `update_story` with `description=...` — and the call errored out because the stub template the buggy `create_story` had written had no `## Description` section. We had to fall back to stuffing everything into the `user_story` field.
+
+## Real user story
+
+As a user calling `update_story.description` on any story (regardless of how it was originally created), I want the call to either replace the existing `## Description` section OR create one if it doesn't exist, so I never have to think about the template structure.
+
+## Implementation note
+
+The simplest fix is in the `update_story_in_file` (or equivalent) function: when looking for the `## Description` section, if not found, **insert it** at a sensible location — probably between `## User Story` and `## Acceptance Criteria` — and then write the description content there.
+
+Related: this story partially covers the workaround for bug 509 (create_story drops description). If 509 is fixed first, the templates would always have a `## Description` section and this wouldn't matter. But this fix is still valuable for older stories created before 509 lands, AND for stories created via legacy paths that don't use the canonical template.
+
+## Observed 2026-04-09
+
+```
+> update_story story_id=500_story_remove_duplicate_pty_debug_log_lines description="..."
+Error: Section '## Description' not found in story file.
+```
+
+## Acceptance Criteria
+
+- [ ] update_story.description succeeds whether or not the target story has a pre-existing ## Description section
+- [ ] When the section is missing, it is created at a consistent location (between ## User Story and ## Acceptance Criteria)
+- [ ] When the section exists, the existing replace-content behaviour is preserved (no regression)
+- [ ] Unit test covering both: section-exists path AND section-missing path
+- [ ] Symmetric fix for update_story.user_story (if it has the same brittleness)
+- [ ] Error messages for genuine failure modes (file not found, write failed) are still distinct from the now-silent missing-section case
+
+## Out of Scope
+
+- TBD

.huskies/work/1_backlog/517_story_remove_filesystem_shadow_fallback_paths_from_lifecycle_rs_finish_the_migration_to_crdt_only.md

@@ -0,0 +1,98 @@
+---
+name: "Remove filesystem-shadow fallback paths from lifecycle.rs (finish the migration to CRDT-only)"
+---
+
+# Story 517: Remove filesystem-shadow fallback paths from lifecycle.rs (finish the migration to CRDT-only)
+
+## User Story
+
+**Depends on story 520** (typed pipeline state machine). Once 520 lands and consumers are migrated to the typed transition API, the lifecycle module no longer needs filesystem fallbacks — all state changes go through the typed `transition` function and the event bus. This story becomes the natural cleanup pass after 520 + 512 + 514 land.
+
+---
+
+**Note:** content stuffed into user_story per bug 509 workaround.
+
+## Context
+
+`server/src/agents/lifecycle.rs::move_item` (the helper that backs `move_story_to_current`, `move_story_to_done`, `move_story_to_merge`, etc.) has **three execution paths**:
+
+1. **CRDT-first path** (the "happy" post-migration path) — calls `crdt_state::read_item(story_id)`, then `db::move_item_stage`, which writes a CRDT op and broadcasts events
+2. **Content-store fallback** — if the story isn't in CRDT but exists in the db's content store, import it via `db::write_item_with_content`
+3. **Filesystem fallback** — if neither, scan `.huskies/work/N_stage/` for a markdown file, import it to the DB
+
+Paths 2 and 3 are **migration scaffolding**. They were necessary while stories existed only on disk and the CRDT was empty, but post-491/492 they should be unnecessary. Worse, they actively *cause* drift today:
+
+- The filesystem fallback can re-import stale shadow files into the DB, undoing intentional deletes
+- The path 3 search is blind to which stage a story "should" be in per the DB — it picks whatever stage dir has the file, which can promote stale shadows
+- This is the mechanism that makes bug 510 (split-brain shadow promotion) possible
+
+`move_story_to_current` is hardcoded to read from `["1_backlog"]`, which is also part of the same legacy filesystem assumption.
+
+## Real user story
+
+As a developer maintaining huskies, I want the lifecycle code to operate exclusively on the CRDT/DB and never touch filesystem shadows, so state drift is eliminated and the post-migration architecture is consistent.
+
+## Implementation plan
+
+1. Inventory every code path in `lifecycle.rs` that touches the filesystem under `.huskies/work/`
+2. For each, determine whether it's a *read* (legacy fallback — can be removed if we're confident all stories are in CRDT now) or a *write* (legacy mirror — can be deferred to a separate filesystem-renderer task that derives state from CRDT)
+3. Remove the read fallbacks
+4. Move the writes to a downstream materialiser task that writes the filesystem shadows from CRDT events (so they're strictly read-only renderings)
+5. Run the bug-510 reconcile pass at startup (story TBD) before this lands, to ensure no story is stranded with only a filesystem shadow
+
+## Observed 2026-04-09
+
+We watched the filesystem fallback paths cause harm multiple times today:
+- Bug 510 split-brain: filesystem shadows in `1_backlog/` got re-promoted by timer fires after the DB had already moved the story to `5_done`
+- The 478 worktree's `move_story_to_current` no-op'd because there was no `1_backlog` shadow — even though 478 was in `4_merge` per the DB (this was actually correct behaviour given the function's narrow `from = ["1_backlog"]`, but it surfaces how filesystem-bound the function is)
+- Lifecycle moves were happening on the filesystem without writing CRDT ops (we initially mis-diagnosed this as "no transition ops in CRDT" before finding bug 511)
+
+## Context
+
+`server/src/agents/lifecycle.rs::move_item` (the helper that backs `move_story_to_current`, `move_story_to_done`, `move_story_to_merge`, etc.) has **three execution paths**:
+
+1. **CRDT-first path** (the "happy" post-migration path) — calls `crdt_state::read_item(story_id)`, then `db::move_item_stage`, which writes a CRDT op and broadcasts events
+2. **Content-store fallback** — if the story isn't in CRDT but exists in the db's content store, import it via `db::write_item_with_content`
+3. **Filesystem fallback** — if neither, scan `.huskies/work/N_stage/` for a markdown file, import it to the DB
+
+Paths 2 and 3 are **migration scaffolding**. They were necessary while stories existed only on disk and the CRDT was empty, but post-491/492 they should be unnecessary. Worse, they actively *cause* drift today:
+
+- The filesystem fallback can re-import stale shadow files into the DB, undoing intentional deletes
+- The path 3 search is blind to which stage a story "should" be in per the DB — it picks whatever stage dir has the file, which can promote stale shadows
+- This is the mechanism that makes bug 510 (split-brain shadow promotion) possible
+
+`move_story_to_current` is hardcoded to read from `["1_backlog"]`, which is also part of the same legacy filesystem assumption.
+
+## Real user story
+
+As a developer maintaining huskies, I want the lifecycle code to operate exclusively on the CRDT/DB and never touch filesystem shadows, so state drift is eliminated and the post-migration architecture is consistent.
+
+## Implementation plan
+
+1. Inventory every code path in `lifecycle.rs` that touches the filesystem under `.huskies/work/`
+2. For each, determine whether it's a *read* (legacy fallback — can be removed if we're confident all stories are in CRDT now) or a *write* (legacy mirror — can be deferred to a separate filesystem-renderer task that derives state from CRDT)
+3. Remove the read fallbacks
+4. Move the writes to a downstream materialiser task that writes the filesystem shadows from CRDT events (so they're strictly read-only renderings)
+5. Run the bug-510 reconcile pass at startup (story TBD) before this lands, to ensure no story is stranded with only a filesystem shadow
+
+## Observed 2026-04-09
+
+We watched the filesystem fallback paths cause harm multiple times today:
+- Bug 510 split-brain: filesystem shadows in `1_backlog/` got re-promoted by timer fires after the DB had already moved the story to `5_done`
+- The 478 worktree's `move_story_to_current` no-op'd because there was no `1_backlog` shadow — even though 478 was in `4_merge` per the DB (this was actually correct behaviour given the function's narrow `from = ["1_backlog"]`, but it surfaces how filesystem-bound the function is)
+- Lifecycle moves were happening on the filesystem without writing CRDT ops (we initially mis-diagnosed this as "no transition ops in CRDT" before finding bug 511)
+
+## Acceptance Criteria
+
+- [ ] Inventory of every filesystem touch in lifecycle.rs is documented in the story body or a follow-up comment
+- [ ] All read fallbacks in lifecycle.rs (paths 2 and 3 above) are removed
+- [ ] All write paths in lifecycle.rs that mirror to the filesystem are moved to a separate materialiser task driven by CRDT events
+- [ ] After the change, lifecycle.rs has zero direct std::fs:: calls under .huskies/work/
+- [ ] move_story_to_current no longer hardcodes from=['1_backlog'] — it reads the source stage from CRDT
+- [ ] Regression: the existing 'try filesystem fallback' tests are updated to test the new CRDT-only path instead of being deleted
+- [ ] A pre-flight script verifies all existing stories are in CRDT before this change lands (so nothing gets stranded)
+- [ ] Bug 510 (split-brain shadows) no longer reproduces after this change
+
+## Out of Scope
+
+- TBD

.huskies/work/1_backlog/518_story_apply_and_persist_should_log_when_persist_tx_send_fails_instead_of_silently_dropping_the_op.md

@@ -0,0 +1,62 @@
+---
+name: "apply_and_persist should log when persist_tx send fails instead of silently dropping the op"
+---
+
+# Story 518: apply_and_persist should log when persist_tx send fails instead of silently dropping the op
+
+## User Story
+
+**Note:** content stuffed into user_story per bug 509 workaround.
+
+---
+
+## Context
+
+`server/src/crdt_state.rs::apply_and_persist` updates the in-memory CRDT and then sends the signed op to the persistence task via a channel:
+
+```rust
+fn apply_and_persist<F>(state: &mut CrdtState, op_fn: F) {
+    let raw_op = op_fn(state);
+    let signed = raw_op.sign(&state.keypair);
+    state.crdt.apply(signed.clone());                  // in-memory update
+    let _ = state.persist_tx.send(signed.clone());     // ← fire-and-forget, error dropped
+    ...
+}
+```
+
+The `let _ = ...` discards the return value of `send()`. If the channel is closed (because the persistence task panicked, was shut down, or has dropped its receiver), the op is silently dropped from persistence — but the in-memory CRDT is already updated. The next restart will replay only the persisted ops, and the in-memory state will quietly diverge from the persisted state.
+
+This is also one of the candidate causes for some of the state drift we've been chasing. It's hard to rule out because there's no log line to confirm whether the persist task is still alive or whether sends are succeeding.
+
+## Real user story
+
+As a developer or operator, I want any failure of `persist_tx.send()` to be logged immediately at WARN or ERROR level, so silent persistence loss is detectable instead of invisible.
+
+## Observed 2026-04-09
+
+Spent significant time investigating whether persist sends were silently failing. Eventually ruled it out empirically (we found that ops WERE being persisted, just with reset seq counters per bug 511). But the diagnosis would have been minutes instead of an hour if there was a log line to check.
+
+## Fix (small)
+
+```rust
+if let Err(e) = state.persist_tx.send(signed.clone()) {
+    crate::slog_error!(
+        "[crdt] Failed to send op to persist task: {e}; persist task may be dead. \
+         In-memory state is now ahead of persisted state."
+    );
+}
+```
+
+Apply the same fix at every `let _ = state.persist_tx.send(...)` site in crdt_state.rs (there are at least 2 — one in apply_and_persist, one in apply_remote_op).
+
+## Acceptance Criteria
+
+- [ ] Every call site of `state.persist_tx.send(...)` in crdt_state.rs logs at ERROR level on send failure
+- [ ] The error message includes the channel error and a clear note that 'in-memory and persisted state may have diverged'
+- [ ] Unit test: shut down the persist receiver (drop the rx end), call write_item, assert an error is logged
+- [ ] No regression in the happy path (no extra log lines on success)
+- [ ] Consider: also expose a counter / metric for persist send failures so it can be monitored without grepping logs
+
+## Out of Scope
+
+- TBD

.huskies/work/1_backlog/519_story_mergemaster_should_detect_no_commits_ahead_of_master_and_fail_loudly_instead_of_exiting_silently.md

@@ -0,0 +1,107 @@
+---
+name: "mergemaster should detect no-commits-ahead-of-master and fail loudly instead of exiting silently"
+---
+
+# Story 519: mergemaster should detect no-commits-ahead-of-master and fail loudly instead of exiting silently
+
+## User Story
+
+**Depends on story 520** (typed pipeline state machine). Once 520 lands, this story largely *evaporates*: `Stage::Merge` is defined as `Merge { feature_branch: BranchName, commits_ahead: NonZeroU32 }`, so a merge state with zero commits ahead is **structurally unrepresentable**. The transition `Current → Merge` (or `Qa → Merge`) is required to provide a NonZeroU32 — the type system enforces it. This story remains useful as a *defensive runtime check* during the migration window before 520 lands; afterwards, it should be closed as redundant.
+
+---
+
+**Note:** content stuffed into user_story per bug 509 workaround.
+
+## Context
+
+When mergemaster runs on a story whose worktree has **zero commits ahead of master** (e.g. because `create_worktree` always creates from master and the original feature branch was never checked out into the worktree), it currently:
+
+1. Spawns its claude session
+2. Runs `merge_agent_work` MCP tool
+3. Finds nothing to merge
+4. Exits cleanly with `[agent:N:mergemaster] Done. Session: ...`
+5. **Does not log any error or warning**
+6. **Spends real money** on the empty session — we observed `cost=$0.82` for one such no-op run
+
+The user has no signal that the merge didn't actually happen. The matrix bot fires a "QA → Merge" stage notification (because the story did move stages internally), then nothing — no `🎉 Merge → Done` notification follows. Master is unchanged.
+
+## Real user story
+
+As a user watching the pipeline, I want mergemaster to detect "this worktree has no commits ahead of master" *before* spending money on a Claude session, and fail loudly with a clear error so I know to investigate the upstream cause (probably the worktree got reset to master).
+
+## Observed 2026-04-09
+
+Around 18:31:51, mergemaster spawned for 478 in a worktree that had been reset to master by the orphan cleanup logic at 18:29:54. By the time mergemaster ran, the worktree was on master with zero commits ahead. It ran a session, spent $0.82, exited "Done", and didn't merge anything. We didn't notice for several minutes because the failure was completely silent. We had to manually `git log master..feature/story-478_…` to confirm there was no merge commit on master.
+
+## Fix
+
+In mergemaster's startup sequence (probably in advance.rs or wherever the mergemaster session is spawned), add a pre-flight check:
+
+```rust
+let commits_ahead = git_commits_ahead(worktree_path, "master")?;
+if commits_ahead == 0 {
+    slog_error!(
+        "[mergemaster] worktree {worktree_path} has no commits ahead of master; \
+         refusing to spawn merge session. Likely cause: worktree was reset to \
+         master after the feature branch's commits were created. Investigate the \
+         worktree's git state before retrying."
+    );
+    return Err("no commits to merge".into());
+}
+```
+
+This costs ~milliseconds (one git command) and saves the cost of an entire Claude session per false-positive.
+
+## Context
+
+When mergemaster runs on a story whose worktree has **zero commits ahead of master** (e.g. because `create_worktree` always creates from master and the original feature branch was never checked out into the worktree), it currently:
+
+1. Spawns its claude session
+2. Runs `merge_agent_work` MCP tool
+3. Finds nothing to merge
+4. Exits cleanly with `[agent:N:mergemaster] Done. Session: ...`
+5. **Does not log any error or warning**
+6. **Spends real money** on the empty session — we observed `cost=$0.82` for one such no-op run
+
+The user has no signal that the merge didn't actually happen. The matrix bot fires a "QA → Merge" stage notification (because the story did move stages internally), then nothing — no `🎉 Merge → Done` notification follows. Master is unchanged.
+
+## Real user story
+
+As a user watching the pipeline, I want mergemaster to detect "this worktree has no commits ahead of master" *before* spending money on a Claude session, and fail loudly with a clear error so I know to investigate the upstream cause (probably the worktree got reset to master).
+
+## Observed 2026-04-09
+
+Around 18:31:51, mergemaster spawned for 478 in a worktree that had been reset to master by the orphan cleanup logic at 18:29:54. By the time mergemaster ran, the worktree was on master with zero commits ahead. It ran a session, spent $0.82, exited "Done", and didn't merge anything. We didn't notice for several minutes because the failure was completely silent. We had to manually `git log master..feature/story-478_…` to confirm there was no merge commit on master.
+
+## Fix
+
+In mergemaster's startup sequence (probably in advance.rs or wherever the mergemaster session is spawned), add a pre-flight check:
+
+```rust
+let commits_ahead = git_commits_ahead(worktree_path, "master")?;
+if commits_ahead == 0 {
+    slog_error!(
+        "[mergemaster] worktree {worktree_path} has no commits ahead of master; \
+         refusing to spawn merge session. Likely cause: worktree was reset to \
+         master after the feature branch's commits were created. Investigate the \
+         worktree's git state before retrying."
+    );
+    return Err("no commits to merge".into());
+}
+```
+
+This costs ~milliseconds (one git command) and saves the cost of an entire Claude session per false-positive.
+
+## Acceptance Criteria
+
+- [ ] Before mergemaster spawns its Claude session, it runs `git log master..HEAD --oneline` (or equivalent) on the worktree
+- [ ] If the result is empty (zero commits ahead), mergemaster exits early with an ERROR log line and does NOT spawn the session
+- [ ] The error message is specific enough that the user can diagnose the upstream cause (e.g. mentions 'worktree was reset' and suggests checking the worktree's branch)
+- [ ] The matrix bot sends a clear failure notification (NOT a successful 🎉 emoji) when this happens
+- [ ] The story does not advance to a 'done' state when mergemaster exits this way; it stays in 4_merge with a clear blocked status
+- [ ] Regression test: create a worktree on master (no feature commits), invoke mergemaster, assert the early exit happens and no Claude session is spawned
+- [ ] Cost saving observed in the 2026-04-09 incident ($0.82 per no-op session) is documented in the test as the motivation
+
+## Out of Scope
+
+- TBD

.huskies/work/1_backlog/520_story_typed_pipeline_state_machine_in_rust_foundation_replaces_stringly_typed_crdt_views_with_strict_enums_subsumes_436.md

@@ -0,0 +1,192 @@
+---
+name: "Typed pipeline state machine in Rust (foundation: replaces stringly-typed CRDT views with strict enums, subsumes 436)"
+---
+
+# Story 520: Typed pipeline state machine in Rust (foundation: replaces stringly-typed CRDT views with strict enums, subsumes 436)
+
+## User Story
+
+**Note:** content stuffed into user_story per bug 509 workaround.
+
+---
+
+## Context
+
+Today huskies represents pipeline state as a loose JSON document inside the BFT JSON CRDT. Each story has fields like `stage: String`, `agent: String`, `retry_count: f64`, `blocked: bool`, `depends_on: String` (JSON-encoded list, double-encoded). This stringly-typed representation allows **many impossible states** to be representable in the data model:
+
+- `stage = "9_invalid"` — typo, no compile error
+- `stage = "5_done"` + `blocked = true` — a done story is blocked? what does that mean?
+- `stage = "4_merge"` with no commits ahead of master — the silent mergemaster failure mode (today's story 478)
+- A coder agent assigned to a story in `4_merge` — bug 502, the loop we fought all day today
+- `retry_count = 3.7` — fractional retry counts (it's an f64 because that's what JSON CRDTs do)
+- `agent = "coder-1"` AND `stage = "1_backlog"` — backlog story has an agent? sentinel encoding via empty string
+
+Multiple bugs filed today (501, 502, 510, 511) exist *because* the type system can't enforce the pipeline invariants. **Patching individual symptoms forever is the wrong strategy.** The right strategy is to make impossible states unrepresentable at the Rust type level, using a typed state machine layered on top of the loose CRDT. The CRDT can stay loose at the persistence layer (it has to be — that's what makes it merge correctly across nodes), but every consumer above the CRDT operates on strict typed enums.
+
+## Real user story
+
+As a developer working on huskies, I want the pipeline state to be expressed as a strict Rust state machine where impossible states and impossible transitions are compile-time errors, so future bugs in this category become structural rather than runtime drift.
+
+## Design
+
+### Two enum hierarchies
+
+**Synced state (CRDT-backed, converges across nodes):**
+
+```rust
+enum Stage {
+    Backlog,
+    Current,
+    Qa,
+    Merge { feature_branch: BranchName, commits_ahead: NonZeroU32 },
+    Done { merged_at: DateTime<Utc>, merge_commit: GitSha },
+    Archived { archived_at: DateTime<Utc>, reason: ArchiveReason },
+}
+
+enum ArchiveReason {
+    Completed,                              // normal accept_story → archived
+    Abandoned,                              // user explicitly abandoned
+    Superseded { by: StoryId },
+    Blocked { reason: String },             // was bug 436's `blocked: true`
+    MergeFailed { reason: String },         // was bug 436's `merge_failure`
+    ReviewHeld { reason: String },          // was bug 436's `review_hold`
+}
+
+struct PipelineItem {
+    story_id: StoryId,                      // newtype, validated
+    name: String,
+    stage: Stage,                           // typed enum, all variants are valid by construction
+    depends_on: Vec<StoryId>,               // parsed, not stringified
+    retry_count: u32,                       // not f64
+    // No more separate `blocked`, `merge_failure`, `review_hold` — folded into Stage::Archived
+}
+```
+
+**Per-node execution state (CRDT-backed under node_id key, local-authored but globally-readable):**
+
+```rust
+enum ExecutionState {
+    Idle,
+    Pending     { agent: AgentName, since: DateTime<Utc> },
+    Running     { agent: AgentName, started_at: DateTime<Utc>, last_heartbeat: DateTime<Utc> },
+    RateLimited { agent: AgentName, resume_at: DateTime<Utc> },
+    Completed   { agent: AgentName, exit_code: i32, completed_at: DateTime<Utc> },
+}
+
+// In the CRDT document, ExecutionState is stored under each node's pubkey:
+//   crdt.execution_state: { node_pubkey → { story_id → ExecutionState } }
+```
+
+The execution state lives in the CRDT under **each node's pubkey**. Each node only writes to entries where `node_pubkey == self.pubkey`, so there's no merge conflict — concurrent writes from the same author follow LWW, concurrent writes from different authors target different entries entirely. All nodes can READ all execution states across the mesh.
+
+**This per-node-keyed CRDT pattern enables:**
+
+- **Cross-node observability** — matrix bot can show "node A is running coder-1 on story X, node B is rate-limited on story Y"
+- **Heartbeat detection** — if a node hasn't updated its execution_state in N minutes, the entry is "stale" (laptop closed, process crashed, oom kill, etc.)
+- **Foundation for story 479** (CRDT work claiming) — a node knows what other nodes are doing *before* claiming work
+- **Stuck job recovery** — if node A's heartbeat dies mid-run, node B can see the stuck state and decide whether to take over
+- **Crash forensics** — the last persisted ExecutionState before a crash is preserved in CRDT, accessible from any node
+
+### The transition function
+
+```rust
+fn transition(
+    state: PipelineItem,
+    event: PipelineEvent,
+) -> Result<PipelineItem, TransitionError>
+```
+
+Pure function. Takes the current state and an event, returns either the new state or a TransitionError. The compiler enforces that the result of every transition is structurally valid — you can't construct a `Stage::Merge` without `commits_ahead: NonZeroU32`, you can't construct a `Stage::Done` without a `merge_commit: GitSha`, etc.
+
+**The set of valid transitions is small** (roughly 10):
+
+- `Backlog → Current` — deps met, auto-assign promotes
+- `Current → Qa` — gates start
+- `Current → Merge` — qa: server, gates auto-pass
+- `Qa → Merge` — gates pass
+- `Qa → Current` — gates fail, retry
+- `Merge → Done` — mergemaster squash succeeds; *requires `Merge.commits_ahead > 0`*
+- `Done → Archived(Completed)` — accept_story
+- `* → Archived(Blocked / MergeFailed / ReviewHeld)` — stuck-state move
+- `Archived(Blocked) → Backlog` — unblock
+
+Anything else is a `TransitionError`. The compiler refuses to compile code that constructs invalid transitions.
+
+### The event subscriber pattern
+
+State changes fire events on a bus. Side-effect handlers subscribe independently:
+
+```rust
+type TransitionEvent = (PipelineItem /* before */, PipelineItem /* after */);
+
+bus.subscribe("matrix-bot",       |before, after| matrix_bot.notify_stage_change(before, after));
+bus.subscribe("filesystem",       |before, after| fs_renderer.update(after));
+bus.subscribe("pipeline-table",   |before, after| pipeline_items_table.upsert(after));
+bus.subscribe("auto-assign",      |before, after| auto_assign.poke_if_relevant(after));
+bus.subscribe("web-ui-broadcast", |before, after| ws_clients.broadcast(after));
+```
+
+Each subscriber is independent and concerns itself only with its own dispatch. Adding a new side effect = adding a new subscriber, not editing the transition function. **The "many things happen on state changes" complexity moves out of the state machine and into the bus consumers**, where each piece is testable in isolation.
+
+### Projection layer (loose CRDT ↔ typed Rust)
+
+The bft-json-crdt JSON document is the persistence layer. The typed enums are the application layer. A projection function bridges them at one carefully-controlled boundary:
+
+```rust
+impl TryFrom<&PipelineItemCrdt> for PipelineItem {
+    type Error = ProjectionError;
+    fn try_from(crdt: &PipelineItemCrdt) -> Result<Self, ProjectionError> { ... }
+}
+
+impl From<&PipelineItem> for PipelineItemCrdt {
+    fn from(item: &PipelineItem) -> Self { ... }
+}
+```
+
+When the CRDT contains data the typed layer can't parse (e.g. a stage value from a future huskies version, OR a merge that produces an inconsistent intermediate state), `try_from` returns a `ProjectionError`. The error surfaces to the caller — it doesn't silently propagate as garbage. The validation happens at exactly one point: the projection boundary.
+
+## What this subsumes
+
+**Story 436** ("Unify story stuck states into a single status field") is subsumed by the `Stage::Archived { reason: ArchiveReason }` variant. The unified status field IS the `ArchiveReason` enum. Story 436 is marked superseded by this story.
+
+## What this enables (concrete bug eliminations)
+
+- **Bug 502** becomes unrepresentable: there's no way to construct `Stage::Merge` with a Coder agent — Coder agents only attach to `Current` / `Qa` stages, and that constraint is in the type signature of the transition function.
+- **Bug 510** becomes irrelevant: there's no "stage='1_backlog' filesystem shadow vs stage='5_done' DB" drift, because Stage is a typed enum with a single source of truth (the CRDT), and projections are derived deterministically.
+- **Bug 519** (mergemaster silent on no-op merge) becomes unrepresentable: `Stage::Merge` requires `commits_ahead: NonZeroU32`. You can't construct a Merge state with zero commits.
+- **Bug 511** (lamport seq reset) becomes detectable: the projection layer notices when CRDT data fails to parse cleanly and surfaces a ProjectionError instead of silently producing garbage in-memory state.
+- **Story 479** (CRDT work claiming) has a clean foundation: ExecutionState gives every node visibility into what every other node is doing, including stale-heartbeat detection.
+- **Future state machine bugs become compile errors**, not runtime drift.
+
+## Implementation order
+
+1. Define the `Stage`, `ArchiveReason`, `ExecutionState`, `PipelineItem` types in a new module (e.g. `server/src/pipeline_state.rs`).
+2. Implement the projection layer (try_from / from for PipelineItemCrdt).
+3. Implement the `transition` function with exhaustive valid transitions.
+4. Implement the event bus.
+5. Migrate consumers ONE AT A TIME — chat commands, lifecycle, API, auto-assign, matrix bot. Each migration is isolated; the compiler tells you when you've missed something.
+6. Once nothing reads the loose `PipelineItemView` anymore, delete it.
+7. Story 436 closes when this lands.
+
+## Acceptance Criteria
+
+- [ ] A new module (e.g. server/src/pipeline_state.rs) defines the Stage, ArchiveReason, ExecutionState, and PipelineItem types with the variants described in the design
+- [ ] Stage::Merge has a NonZeroU32 commits_ahead field (so the bug 519 silent no-op merge is unrepresentable)
+- [ ] Stage::Done has GitSha merge_commit and DateTime merged_at fields (so a 'done' story always has merge metadata)
+- [ ] ArchiveReason enum subsumes the old blocked / merge_failure / review_hold front matter fields, with a sub-reason variant for each
+- [ ] PipelineItem.depends_on is Vec<StoryId>, not String (no more JSON-as-string)
+- [ ] ExecutionState lives in the CRDT under per-node-pubkey keys; each node only writes to its own subspace (validated by CRDT signature check)
+- [ ] Last_heartbeat field is updated periodically by the running node so other nodes can detect stale entries
+- [ ] A pure transition(state, event) -> Result<PipelineItem, TransitionError> function exists and is exhaustively pattern-matched
+- [ ] Every valid transition listed in the design (~10) is implemented and unit-tested with both success and error cases
+- [ ] The TryFrom<&PipelineItemCrdt> for PipelineItem projection function handles every currently-valid CRDT state and returns a structured ProjectionError for invalid ones (instead of silently propagating garbage)
+- [ ] An event bus pattern is in place where matrix bot, filesystem renderer, pipeline_items materialiser, auto-assign, and web UI broadcaster are independent subscribers
+- [ ] All call sites that previously read item.stage as a string or used the blocked / merge_failure / review_hold fields are migrated to the typed enum API
+- [ ] Story 436 is closed as superseded by this story
+- [ ] Bug 502 has a regression test that confirms the type system prevents the loop (the test should be a compile-fail test if possible)
+- [ ] Bug 510 (filesystem shadow split-brain) no longer reproduces after this lands, because the typed state machine has a single source of truth
+- [ ] Documentation in README.md or a new ARCHITECTURE.md explains the type hierarchy, the transition function, the event bus pattern, and the per-node ExecutionState convention
+
+## Out of Scope
+
+- TBD

.huskies/work/1_backlog/521_story_mcp_http_capability_to_write_a_crdt_tombstone_delete_op_for_a_story_to_clear_it_from_in_memory_state.md

@@ -0,0 +1,87 @@
+---
+name: "MCP/HTTP capability to write a CRDT tombstone (delete op) for a story, to clear it from in-memory state"
+---
+
+# Story 521: MCP/HTTP capability to write a CRDT tombstone (delete op) for a story, to clear it from in-memory state
+
+## User Story
+
+**Note:** content stuffed into user_story per bug 509 workaround.
+
+---
+
+## Context
+
+Today (2026-04-09) we discovered the hard way that **there is no way to remove a story from huskies's running in-memory state without restarting the server process**. The state machines that keep stories alive include:
+
+1. The persisted CRDT op log (`crdt_ops` table) — direct sqlite DELETE works
+2. The in-memory CRDT view (`CRDT_STATE` global in `server/src/crdt_state.rs`) — **no eviction API**
+3. The in-memory content store (`CONTENT_STORE` in `server/src/db/mod.rs:46`) — has `delete_content()` but no MCP / HTTP exposure
+4. The shadow `pipeline_items` table — direct sqlite DELETE works
+5. Filesystem shadows under `.huskies/work/` — `find -delete` works
+6. `timers.json` — direct file edit works
+
+If a story gets into a bad state (split-brain, ghost row, runaway timer respawning it), we can scrub all the *persistent* layers (1, 4, 5, 6) but the *in-memory* layers (2, 3) keep regenerating it because some periodic code reads in-memory state and writes new ops based on what it sees. The only way to clear in-memory state today is `docker restart huskies`, which is heavy and disrupts the matrix bot, web UI, and any in-flight agents.
+
+We need a **scoped, surgical capability** to write a CRDT tombstone op for a single story_id, which:
+- Marks the in-memory item as `is_deleted = true`
+- Persists the tombstone op to `crdt_ops` so future replays don't resurrect the story
+- Removes the story from `CONTENT_STORE` 
+- Cleans up any pending `timers.json` entries for the story
+- Cancels any running agents on the story
+
+…and exposes it as an MCP tool (e.g. `mcp__huskies__purge_story`) and ideally an HTTP endpoint, so an operator can "kill it with fire" without restarting the server.
+
+## Real user story
+
+As a huskies operator, I want a single MCP/HTTP call that completely removes a story from every layer of state — persistent AND in-memory — so I never have to restart the entire server just to clean up one stuck story.
+
+## Observed 2026-04-09
+
+We spent the last hour of this session whack-a-moling stories 503 and 478. Even after:
+- `DELETE FROM pipeline_items WHERE id LIKE '503%'` ✓
+- `DELETE FROM crdt_ops WHERE op_json LIKE '%503_bug_depends_on%'` ✓
+- `mcp stop_agent + remove_worktree` for the running coders ✓
+- `find .huskies/work -name '503_*' -delete` ✓
+- emptying `timers.json` (multiple times — kept getting re-populated) ✓
+
+…503 kept reappearing in `current` with new agents being spawned. The root cause: the in-memory `CRDT_STATE` (loaded from `crdt_ops` at startup at 18:19) still had 503 and 478 as live items, and a periodic code path was reading `crdt_state::read_all_items()`, seeing them as live, and triggering the auto-assign / rate-limit-retry chain.
+
+Final resolution: `docker restart huskies` to wipe the in-memory state. Worked, but it's a sledgehammer.
+
+## Implementation note
+
+The bft-json-crdt library appears to support per-item delete via the `is_deleted: bool` field on each CRDT item (visible in the persisted op JSON we inspected today). Writing a delete op should look something like:
+
+```rust
+crdt_state::apply_and_persist(&mut state, |s| {
+    s.crdt.doc.items[idx].delete()  // or whatever the BFT JSON CRDT delete API is
+})
+```
+
+The op gets signed, applied to the in-memory state (marking the item deleted), and persisted to crdt_ops via the existing channel. Then `read_all_items()` should filter out `is_deleted: true` entries (it may already do this — verify in `extract_item_view`).
+
+## Why this is distinct from bug 514 (delete_story full cleanup)
+
+Bug 514 is about making the existing `delete_story` MCP tool do a full cleanup across all the layers we know about. **This** story is specifically about acquiring the *capability* to write a CRDT tombstone — without that, bug 514 can't be implemented correctly because it has no way to clear in-memory state. So 521 is a prerequisite for 514.
+
+It's also a prerequisite for properly handling the fix for bug 510 (split-brain shadows) — when the reconcile pass detects a stale story, it needs a way to actually evict it. That eviction is what this story provides.
+
+## Acceptance Criteria
+
+- [ ] A new MCP tool (e.g. `mcp__huskies__purge_story`) is registered and callable
+- [ ] The tool takes a story_id and returns a structured result indicating which layers were cleared (CRDT op, content store, timers, agents, worktree, filesystem)
+- [ ] The tool writes a signed CRDT tombstone op (is_deleted: true) for the item, applies it to the in-memory CRDT, and persists it to crdt_ops
+- [ ] After the tool runs, `read_all_items()` does NOT return the purged story (verify the filter handles is_deleted)
+- [ ] After the tool runs, `read_content(story_id)` returns None (CONTENT_STORE entry is removed)
+- [ ] After the tool runs, `timers.json` has no entries for the story
+- [ ] After the tool runs, no agents are running on the story (stop_agent is called for any active ones)
+- [ ] After the tool runs, the worktree at `.huskies/worktrees/{story_id}/` is removed
+- [ ] After the tool runs, the filesystem shadow at `.huskies/work/*/{story_id}.md` is removed
+- [ ] Idempotent: calling purge_story twice on the same story_id is safe and doesn't error
+- [ ] Bug 514 (delete_story full cleanup) is updated to use this purge capability internally
+- [ ] Regression test: insert a story via the normal write path, call purge_story, restart the server, verify the story is still gone (i.e. the tombstone persisted correctly)
+
+## Out of Scope
+
+- TBD

.huskies/work/6_archived/130_bug_permission_approval_returns_wrong_format_tools_fail_after_user_approves.md

@@ -10,7 +10,7 @@ The `prompt_permission` MCP tool returns plain text ("Permission granted for '..
 
 ## How to Reproduce
 
-1. Start the storkit server and open the web UI
+1. Start the huskies server and open the web UI
 2. Chat with the claude-code-pty model
 3. Ask it to do something that requires a tool NOT in `.claude/settings.json` allow list (e.g. `wc -l /etc/hosts`, or WebFetch to a non-allowed domain)
 4. The permission dialog appears — click Approve