feat(ai): F009 chat UI, session continuity & project picker

[nimat-dev]

Summary

This PR implements F009: Chat UI (streaming) + session continuity (reconnect resumes) + project picker, completing Phase 03 (AI — Claude Code bridge).

Changes Included:

1. Wire Protocol (@shellmind/protocol):
   • ChatTurn schema & types (id, role, text, toolEvents, timestamp, status).
   • chat.history.req: Client history query ({ projectCwd?: string; limit?: number }).
   • chat.history.resp: Agent history response ({ currentCwd: string; turns: ChatTurn[] }).
   • Registered in KnownMessage union, registry, and codec.
2. Pure Core Interfaces (@shellmind/agent):
   • ITranscriptStore, TranscriptFilter in src/core/transcript.ts (0 Node builtins or I/O imports).
   • Manages chronological turns, ID updates, size cap pruning, and project isolation.
3. Storage Adapter & Daemon Integration (@shellmind/agent):
   • FileTranscriptStore in src/adapters/storage/file-transcript.ts:
     • Local JSON persistence under ~/.shellmind/transcripts/ with file mode 0600 and dir mode 0700.
     • Bounded storage capped at max N turns (default 100).
     • Isolated per project working directory path via sanitized slug + SHA-256 hash.
     • Resilient error recovery: gracefully recovers with empty transcript on corrupt JSON files.
   • AgentDaemon:
     • Records user turns on agent.prompt.
     • Accumulates assistant text deltas and tool events into completed assistant turn in transcript.
     • Handles chat.history.req and replies with chat.history.resp.
     • Automatically switches transcript context when project.set changes cwd.
4. Mobile Client, Tool Renderers & UI (@shellmind/mobile):
   • AgentClient methods: requestChatHistory(projectCwd?, limit?) and onChatHistory().
   • Tool Renderer Registry (packages/mobile/src/renderers/registry.ts):
     • BashRenderer: terminal execution card with command, running/success/error status pill, and collapsible output.
     • FileRenderer: file modification card showing path, READ/WRITE/EDIT action badges, diffs, and results.
     • SearchRenderer: search query card with pattern, directory, and matches preview.
     • DefaultRenderer: safe fallback card for unrecognized tools.
   • ChatScreen.tsx:
     • Interactive project picker dropdown driving project.list and project.set.
     • Live streaming feed showing user bubbles, assistant streaming text, tool cards, and embedded PermissionCard.
     • Prompt input field with Send and Abort buttons.
     • Seamless session continuity: requests transcript on connect/reconnect and deduplicates by turn ID.
5. E2E & Verification:
   • Maestro flow specification .maestro/chat_flow.yaml and trace in .harness/evidence/F009/e2e-trace.txt.
   • 113/113 tests passing monorepo-wide (29 protocol, 52 agent, 32 mobile).
   • Clean architecture verified with dependency-cruiser (70 modules, 209 dependencies cruised, 0 violations).
   • Full suite passing (pnpm verify).

[nimat-dev]

Maker-Checker Review: F009 (Chat UI + session continuity + project picker)

1. Acceptance Criteria Verification

• Wire protocol messages (chat.history.req, chat.history.resp, ChatTurn) defined and registered in @shellmind/protocol.
• Pure core interface ITranscriptStore in @shellmind/agent/src/core/transcript.ts has 0 Node builtins or I/O imports.
• Concrete adapter FileTranscriptStore persists turns with file mode 0600, project isolation, maxTurns pruning, and corrupt JSON resilience.
• AgentDaemon records turns upon prompt/completion, serves chat.history.req, and respects project.set.
• Mobile AgentClient implements requestChatHistory and onChatHistory.
• ToolRenderer registry handles Bash, File, Search, and safely falls back to DefaultRenderer.
• ChatScreen.tsx provides streaming message timeline, project picker dropdown, abort button, permission card embed, and deduplication on reconnect.
• Clean architecture verified via dependency-cruiser (0 violations across 70 modules).
• 113/113 tests passing monorepo-wide across all packages.
• Maestro E2E specification in .maestro/chat_flow.yaml.

2. Evaluation Scores

• Acceptance: 5/5
• Correctness: 5/5
• Boundaries: 5/5
• Modularity: 5/5
• Evidence: 5/5
• Average: 5.0 (PASS)

3. Decision

APPROVE. Ready for squash merge to main.