let-them-talk 3.6.2 → 3.8.0

package/CHANGELOG.md

@@ -1,5 +1,76 @@
 # Changelog
 
+## [3.8.0] - 2026-03-16
+
+### Changed — Group Conversation Overhaul
+
+Redesigned from the ground up based on 3-agent collaborative testing and design session.
+
+**Single-write group messages (O(1) instead of O(N)):**
+- `send_message` in group mode now writes ONE message with `to: "__group__"` instead of N copies per agent
+- `broadcast` in group mode also uses single `__group__` write
+- Old O(N) auto-broadcast loop completely removed
+- Result: with 6 agents, a message now creates 1 write instead of 6. A broadcast round that previously created 30 writes now creates 6.
+
+**`addressed_to` field + `should_respond` hints:**
+- `send_message(to="AgentName")` in group mode stores `addressed_to: ["AgentName"]` on the `__group__` message
+- `listen_group` response includes `addressed_to_you: true/false` and `should_respond: true/false` per message
+- Hint-based, not enforced — agents can still respond when they have valuable input
+- No `addressed_to` = everyone should respond (backwards compatible)
+
+**Adaptive cooldown:**
+- Cooldown now scales with team size: `max(500ms, N * 500ms)` where N = alive agent count
+- 2 agents = 1s, 3 agents = 1.5s, 6 agents = 3s, 10 agents = 5s
+- Explicit `group_cooldown` config still respected if set
+
+**Shorter stagger:**
+- Deterministic stagger reduced from 0-3000ms to 500-1500ms
+- Same agent always gets the same delay (hash-based)
+
+**Alive-only garbage collection:**
+- `autoCompact` for `__group__` messages only checks alive agents for consumed tracking
+- Dead agents no longer block message compaction forever
+- Dead agents catch up via `get_compressed_history()` which reads history.jsonl (never compacted)
+
+**Own-message filtering:**
+- Agents no longer see their own `__group__` messages in `listen_group` batches
+- Own messages are auto-consumed on sight
+- Own messages still visible in `context` array for reference
+
+### Added — 3D World: Player Mode & Improvements
+- **Player character** — users can spawn as a controllable character in the 3D Hub
+- **Spectator camera improvements** — refined controls and speed
+- **Environment updates** — campus environment refinements
+
+## [3.7.0] - 2026-03-16
+
+### Added — Agent Ecosystem (20 new tools, 52 total)
+
+**Tier 1 — Critical Infrastructure:**
+- **`get_briefing()`** — full project onboarding in one call: agents, tasks, decisions, KB, locked files, progress, project file tree
+- **`lock_file(path)` / `unlock_file(path?)`** — exclusive file editing with auto-release on agent death
+- **`log_decision(decision, reasoning?, topic?)` / `get_decisions(topic?)`** — persistent decision log, prevents re-debating
+- **Agent recovery on rejoin** — `register()` returns active tasks, workspace keys, recent messages for returning agents
+
+**Tier 2 — Quality of Life:**
+- **`kb_write(key, content)` / `kb_read(key?)` / `kb_list()`** — shared team knowledge base (any agent reads/writes)
+- **Event hooks** — auto-fires system messages on `agent_join`, `task_complete`, `all_tasks_done`, `dependency_met`
+- **`update_progress(feature, percent, notes)` / `get_progress()`** — feature-level progress tracking with overall %
+- **`get_compressed_history()`** — auto-compresses old messages into summary segments, keeps recent verbatim
+- **`listen_group()` now blocks indefinitely** — no more timeout, agents never drop out
+
+**Tier 3 — Advanced Collaboration:**
+- **`call_vote(question, options)` / `cast_vote(vote_id, choice)` / `vote_status(vote_id?)`** — team voting with auto-resolve when all vote
+- **`request_review(file, desc)` / `submit_review(review_id, status, feedback)`** — code review pipeline with approve/changes_requested
+- **`declare_dependency(task_id, depends_on)` / `check_dependencies(task_id?)`** — task dependency tracking with auto-notify on resolve
+- **`get_reputation(agent?)` / `suggest_task()`** — agent reputation tracking (auto-detects strengths), task suggestions based on skills
+- **Auto-reputation tracking** — global hook tracks every action (messages, tasks, reviews, decisions, KB writes) without manual calls
+
+### Fixed
+- **Monitor screens stay red** when agent stops listening — persistent color state instead of 300ms flash
+- **"NOT LISTENING" warning** shown prominently on desk monitor canvas
+- **Status color logic** — green = listening, red = active but not listening, yellow = sleeping, dim = dead
+
 ## [3.6.2] - 2026-03-16
 
 ### Added — Message Awareness System

package/README.md

@@ -86,9 +86,9 @@ Each terminal spawns its own MCP server process. All processes share a `.agent-b
 
 - **3D virtual office** — chibi characters at desks, spectator camera (WASD+mouse), 11 hairstyles, 6 outfits, gestures, furniture, TV dashboard
 - **Managed conversation mode** — structured turn-taking with floor control for 3+ agents, prevents broadcast storms
-- **32 MCP tools** — messaging, tasks, workflows, profiles, workspaces, branching, managed mode
+- **53 MCP tools** — messaging, tasks, workflows, profiles, workspaces, branching, managed mode, briefing, file locking, decisions, KB, voting, reviews, dependencies, reputation
 - **8-tab dashboard** — 3D Hub (default), messages, tasks, workspaces, workflows, launch, stats, docs
-- **Group conversation mode** — free multi-agent collaboration with auto-broadcast and cooldown
+- **Group conversation mode** — single-write `__group__` messages, adaptive cooldown, `addressed_to` hints, alive-only GC
 - **5 agent templates** — pair, team, review, debate, managed — with ready-to-paste prompts
 - **5 conversation templates** — Code Review, Debug Squad, Feature Dev, Research & Write, Managed Team
 - **Stats & analytics** — per-agent scores, response times, hourly charts, conversation velocity
@@ -175,7 +175,7 @@ The dashboard's default view is a **real-time 3D virtual office** (the "3D Hub")
 
 **Animations:** walk, sit, type, raise hand, sleep (ZZZ), wave, think, point, celebrate, stretch, idle gestures. Agents turn toward speakers during conversations.
 
-## MCP Tools (32)
+## MCP Tools (53)
 
 <details>
 <summary><strong>Messaging (13 tools)</strong></summary>
@@ -249,6 +249,90 @@ The dashboard's default view is a **real-time 3D virtual office** (the "3D Hub")
 
 </details>
 
+<details>
+<summary><strong>Briefing & Recovery (1 tool)</strong></summary>
+
+| Tool | Description |
+|------|-------------|
+| `get_briefing` | Full project onboarding — agents, tasks, decisions, KB, locks, progress, files |
+
+</details>
+
+<details>
+<summary><strong>File Locking (2 tools)</strong></summary>
+
+| Tool | Description |
+|------|-------------|
+| `lock_file` | Lock a file for exclusive editing. Auto-releases on death |
+| `unlock_file` | Unlock a file or all your locked files |
+
+</details>
+
+<details>
+<summary><strong>Decision Log (2 tools)</strong></summary>
+
+| Tool | Description |
+|------|-------------|
+| `log_decision` | Log a team decision with reasoning and topic |
+| `get_decisions` | Get all decisions, optionally filtered by topic |
+
+</details>
+
+<details>
+<summary><strong>Knowledge Base (3 tools)</strong></summary>
+
+| Tool | Description |
+|------|-------------|
+| `kb_write` | Write to shared team knowledge base |
+| `kb_read` | Read KB entries (one or all) |
+| `kb_list` | List all KB keys with metadata |
+
+</details>
+
+<details>
+<summary><strong>Progress & Compression (3 tools)</strong></summary>
+
+| Tool | Description |
+|------|-------------|
+| `update_progress` | Update feature-level completion percentage |
+| `get_progress` | Get all feature progress with overall % |
+| `get_compressed_history` | Compressed old messages + recent verbatim |
+
+</details>
+
+<details>
+<summary><strong>Voting (3 tools)</strong></summary>
+
+| Tool | Description |
+|------|-------------|
+| `call_vote` | Start a team vote with options |
+| `cast_vote` | Cast your vote (auto-resolves when all vote) |
+| `vote_status` | Check vote results |
+
+</details>
+
+<details>
+<summary><strong>Code Review (2 tools)</strong></summary>
+
+| Tool | Description |
+|------|-------------|
+| `request_review` | Request a code review from the team |
+| `submit_review` | Approve or request changes with feedback |
+
+</details>
+
+<details>
+<summary><strong>Dependencies & Reputation (4 tools)</strong></summary>
+
+| Tool | Description |
+|------|-------------|
+| `declare_dependency` | Declare task dependency (auto-notifies on resolve) |
+| `check_dependencies` | Check blocked/resolved dependencies |
+| `get_reputation` | Agent leaderboard with strengths |
+| `suggest_task` | Get next task suggestion based on your skills |
+
+</details>
+
 ## CLI Reference
 
 ```bash

package/cli.js

@@ -9,7 +9,7 @@ const command = process.argv[2];
 
 function printUsage() {
   console.log(`
-  Let Them Talk — Agent Bridge v3.6.2
+  Let Them Talk — Agent Bridge v3.8.0
   MCP message broker for inter-agent communication
   Supports: Claude Code, Gemini CLI, Codex CLI, Ollama