@yemi33/minions 0.1.1883 → 0.1.1884

package/agents/lambert/charter.md

@@ -39,8 +39,7 @@
 
 ## How I Work
 
-- Read Ripley's exploration findings from `{{team_root}}/notes/inbox/ripley-findings-*.md`
-- Read Dallas's build summary from `{{team_root}}/notes/inbox/dallas-build-*.md`
+- Read recent teammate findings under `{{team_root}}/notes/inbox/` — filenames follow the engine-injected "Write Learnings" contract in each agent's dispatch prompt, so defer to that contract rather than matching ad-hoc filename globs here
 - Cross-reference against all `docs/`, agent `CLAUDE.md` files, and prototype instructions
 - Be exhaustive on missing features — better to over-document than under-document
 - Output the JSON to `{{team_root}}/prd/<plan-slug>.json` (the engine's `materializePlansAsWorkItems()` reads from that directory)

package/agents/ripley/charter.md

@@ -22,7 +22,7 @@
 - Always read `CLAUDE.md` files (root + per-agent) before anything else
 - Map the repo structure: `agents/`, `modules/`, `.devtools/`, `docs/`, `eval/`
 - Look for prototype instructions in: `docs/`, `agents/*/CLAUDE.md`, `README.md`, inline comments
-- Document findings in `notes/inbox/ripley-findings-{timestamp}.md` (relative to squad team root)
+- Document findings in the inbox file the dispatch prompt assigns under "Write Learnings" — that section is the single source of truth for the path and filename; do not re-derive it here
 - Never guess — if something is unclear, note it explicitly for human review
 
 ## Boundaries

package/docs/command-center.md

@@ -1,159 +1,7 @@
 # Command Center
 
-The Command Center (CC) is the minions's conversational AI brain. It powers the dashboard's chat panel, document editing modals, and plan steering — all through a single persistent Sonnet session with full minions awareness.
+The Command Center (CC) is the dashboard's conversational chat panel. It opens from the **CC** button in the top-right header and lets you drive the engine — dispatching work items, saving notes, approving plans, and asking questions about minions state — through a persistent Claude/Copilot session with full repo awareness.
 
-## Access
+CC is intentionally a thin wrapper around the runtime CLI: state changes happen via `Bash`-tool `curl` calls to the dashboard's own REST API, not via parsed delimiter blocks. The end-to-end flow is `dashboard/js/command-center.js` `_ccDoSend()` → `POST /api/command-center` (or `/api/command-center/stream`) in `dashboard.js` (`handleCommandCenter`) → `engine/llm.js` `callLLM({ direct: true })` → claude/copilot CLI session persisted in `engine/cc-sessions.json`. Per-turn API mutations are correlated via the `X-CC-Turn-Id` header and surfaced as standalone `role='action'` chips rendered outside the assistant bubble (`_ccActionResultLine` + `addMsg('action', ...)`).
 
-Click the **CC** button in the top-right header of the dashboard. A slide-out chat drawer opens on the right side.
-
-## Persistent Sessions
-
-CC maintains a true multi-turn session using Claude CLI's `--resume` flag. Unlike a typical stateless API call, each message resumes the same conversation — Claude retains full history including tool calls, intermediate reasoning, and file contents from prior turns.
-
-**Session lifecycle:**
-- **Created** on first message (or after the system prompt changes, or when you click **New Session**)
-- **Resumed** on subsequent messages via `--resume <sessionId>`
-- **Invalidated** only when the CC system prompt changes — detected by hashing `CC_STATIC_SYSTEM_PROMPT` into `_ccPromptHash` and comparing on each call. CC chat sessions do **not** auto-expire by TTL or turn count; `ENGINE_DEFAULTS.ccMaxTurns` (default 50) is a per-call tool-use cap inside the Claude CLI, not a session lifetime cap.
-- **Persisted** to `engine/cc-session.json` (legacy global session) and `engine/cc-sessions.json` (per-tab sessions) — both survive dashboard restarts and engine cleanup ticks
-- **Frontend messages** saved to `localStorage` — survive page refresh
-- **Removed** only when the user explicitly closes a tab via the **×** button on the tab strip — that fires `DELETE /api/cc-sessions/:id` to evict the persisted session
-
-Click **New Session** in the drawer header to start fresh; click the **×** on a tab to remove it permanently.
-
-### Fresh State Each Turn
-
-The system prompt is baked into the session at creation (persona, rules, action format, tool access). Dynamic minions state is injected as a preamble in each user message, so CC always sees current data even in a resumed session.
-
-```
-Turn 1: system prompt (static) + [Current Minions State] + user message
-Turn 2+: [Updated Minions State] + user message  (system prompt already in session)
-```
-
-## What It Knows
-
-Full minions context is injected every turn:
-
-| Context | Details |
-|---------|---------|
-| Agents | Statuses, current tasks, full charters (expertise/roles) |
-| Routing | Who's preferred/fallback for each work type |
-| Config | Tick interval, max concurrent, timeouts, max turns |
-| Work items | Active, pending, failed across all projects with failure reasons |
-| Pull requests | Status, review status, build status, branch, URL |
-| Plans | Full `.md` plan contents + PRD JSON summaries + archived plans |
-| PRD items | All items with status, priority, dependencies |
-| Dispatch | Active agents + last 15 completions with result summaries |
-| Skills | All reusable agent workflows with triggers |
-| Knowledge base | Recent entries (architecture, conventions, build reports, reviews) |
-| Team notes | Recent consolidated notes |
-
-## Tool Access
-
-CC can use tools to look beyond the pre-loaded context:
-
-- **Bash** — Run shell commands (git, build tools, scripts)
-- **Read** — Open any file (agent output logs, code, config, plans)
-- **Write** — Create or overwrite files
-- **Edit** — Make targeted edits to existing files
-- **Glob** — Find files by pattern (e.g., `agents/*/output.log`)
-- **Grep** — Search file contents (find functions, search agent outputs)
-- **WebFetch/WebSearch** — Look up external resources
-
-## Unified Brain
-
-All LLM-powered features in the dashboard route through the same CC session:
-
-| Feature | Endpoint | How It Works |
-|---------|----------|-------------|
-| **CC chat panel** | `POST /api/command-center` | Direct CC interaction |
-| **Doc chat modal** | `POST /api/doc-chat` | Routes through CC via `ccDocCall()` |
-| **Doc steer** | `POST /api/steer-document` | Routes through CC via `ccDocCall()` |
-| **Plan revision** | `POST /api/plans/revise` | Routes through CC via `ccDocCall()` |
-
-This means:
-- A question in the doc chat modal shares context with the CC panel
-- CC remembers what you discussed in a document editing session
-- Doc modals can cross-reference other minions knowledge, PRs, work items
-- All turns accumulate in the same session
-
-## Actions
-
-When you ask CC to *do* something, it includes structured action blocks in its response.
-
-| Action | What It Does | Example Prompt |
-|--------|-------------|----------------|
-| `dispatch` | Create a work item | "Have dallas fix the login bug" |
-| `note` | Save a decision/reminder | "Remember we need to migrate to v3" |
-| `plan` | Create an implementation plan | "Plan the GitHub integration feature" |
-| `cancel` | Stop a running agent | "Cancel whatever ripley is doing" |
-| `retry` | Retry failed work items | "Retry the three failed tasks" |
-| `pause-plan` | Pause a PRD | "Pause the officeagent PRD" |
-| `approve-plan` | Approve a PRD | "Approve the new plan" |
-| `edit-prd-item` | Edit a PRD item | "Change P003's priority to high" |
-| `remove-prd-item` | Remove a PRD item | "Remove P011 from the plan" |
-| `delete-work-item` | Delete a work item | "Delete work item W025" |
-
-For endpoints without a named action, CC may emit a local API fallback action with `endpoint`, `method`, and `params`. The server only invokes safe local `/api/...` paths, validates the requested method against the route index when available, sends GET params as query strings, and rejects streaming/recursive CC/doc-chat endpoints.
-
-## Error Handling
-
-- **Frontend timeout**: 10-minute `AbortSignal` on the fetch — prevents infinite "thinking" spinner
-- **Backend timeout**: 5-minute kill timer on the claude process
-- **Resume failure**: If `--resume` fails (corrupted/deleted session), automatically retries with a fresh session
-- **Concurrency guard**: Only one CC call at a time — concurrent requests get a 429 "CC is busy" response
-- **Phase indicators**: Thinking indicator shows progressive phases ("Thinking..." → "Analyzing..." → "Timing out soon...")
-
-## Architecture
-
-```
-User message (CC panel, doc modal, or steer)
-    │
-    ▼
-POST /api/command-center  (or /api/doc-chat, /api/steer-document)
-    │
-    ├── Validate session (prompt-hash check — invalidate if `_ccPromptHash` drifted)
-    ├── Build dynamic state preamble (buildCCStatePreamble)
-    ├── callLLM() with sessionId (resume) or without (new)
-    │     model: sonnet
-    │     maxTurns: 25 (CC) or 10 (doc-plan) or 1 (doc-other)
-    │     allowedTools: Bash, Read, Write, Edit, Glob, Grep, WebFetch, WebSearch
-    │     timeout: 600s (CC) or 300s (doc-plan) or 60s (doc-other)
-    │
-    ▼
-engine/llm.js callLLM({ direct: true })  (bypasses engine/spawn-agent.js — CC + doc-chat only)
-    │
-    ├── Resolves claude CLI binary path from engine/claude-caps.json
-    ├── If --resume: pass -p --resume <id> (no system prompt file)
-    ├── If new: pass -p --system-prompt-file <file>
-    │
-    ▼
-claude CLI (persistent session on disk)
-    │
-    ▼
-Parse response
-    ├── Extract sessionId from stream-json result
-    ├── Extract ===ACTIONS=== block (CC)
-    ├── Extract ---DOCUMENT--- block (doc chat/steer)
-    ├── Update cc-session.json
-    │
-    ▼
-Frontend
-    ├── Render chat message
-    ├── Execute actions / apply doc edits
-    ├── Save sessionId + messages to localStorage
-```
-
-## Key Files
-
-| File | Role |
-|------|------|
-| `engine/llm.js` | `callLLM()` / `callLLMStreaming()` — single LLM function with optional `sessionId` for resume; `direct: true` spawns claude CLI directly (used by CC + doc-chat) |
-| `engine/spawn-agent.js` | Agent dispatch wrapper — resolves claude CLI path and invokes it. **Not used by CC/doc-chat** (direct spawn path). |
-| `engine/shared.js` | `parseStreamJsonOutput()` extracts `sessionId` from result |
-| `engine/cc-session.json` | Persisted session state (sessionId, turnCount, timestamps) |
-| `dashboard.js` | CC endpoint, `buildCCStatePreamble()`, `ccDocCall()`, `parseCCActions()` |
-| `dashboard/js/` | Frontend: localStorage persistence, session indicator, New Session button |
-
-## Command Bar
-
-The command bar at the top of the dashboard routes all input to the CC panel. Typing in the command bar opens the CC drawer and sends the message as a CC turn.
+For canonical detail (system prompt, session lifecycle, turn-ID surfacing pipeline, doc-chat integration, and CC API contract), read [`CLAUDE.md`](../CLAUDE.md) — see the **CC API Contract** and **Sessions** sections — and the source in [`dashboard/js/command-center.js`](../dashboard/js/command-center.js), [`dashboard.js`](../dashboard.js) (`handleCommandCenter`), and [`prompts/cc-system.md`](../prompts/cc-system.md). This pointer file exists so the docs index has an entry for "Command Center"; the implementation details are deliberately not duplicated here because they drift.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@yemi33/minions",
-  "version": "0.1.1883",
+  "version": "0.1.1884",
   "description": "Multi-agent AI dev team that runs from ~/.minions/ — five autonomous agents share a single engine, dashboard, and knowledge base",
   "bin": {
     "minions": "bin/minions.js"