13 Commits

Author SHA1 Message Date
9e7a22a539 dream UX: agent announces dreaming + posts summary when back
- Posts "dreaming..." before pausing worker
- Posts "back. dreamed about: ..." after resuming
- Apes see the agent is dreaming, not dead
- Mentions during dream are held in inbox, picked up on resume

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 22:33:17 +02:00
5ba82869d3 fix: CLI spec contradictions from codex AX audit
- Fix paths: relative to agent home dir, not hardcoded /home/agent
- Add worker/dream coordination: dream pauses worker to prevent file races
- Watch registration via .colony.toml (server reads agent config)
- Remove remaining old mentions API reference (use inbox instead)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 22:32:32 +02:00
ac618d2ce3 AX fixes: --json on all commands, exit codes, channel resolution, init
CLI spec:
- AX conventions table: --json, --quiet, exit codes, pipeable, stderr
- colony init command for .colony.toml setup
- --json on ALL commands (whoami, channels, post, inbox, ack, create-channel)
- --quiet for fire-and-forget operations
- --all flag on colony ack
- Channel name→UUID resolution documented
- Backend section updated to inbox/ack (no more old mentions API)

AX skill:
- Added principle #9: Pipeable machine-readable output

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 22:28:43 +02:00
6cf7b0395c tech-spec-cli v2: two binaries, inbox/ack, aligned with architecture v3
- Split into colony (chat client) + colony-agent (runtime)
- Replace mentions with server-side inbox + ack checkpoints
- colony-agent worker: serialized loop with HEARTBEAT_OK skip
- colony-agent dream: memory consolidation + soul evolution
- colony-agent birth: create agent on same VM in <30s
- Updated implementation order: Phase 1 (CLI) then Phase 2 (runtime)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 22:25:12 +02:00
261d2d6dac agent self-discovery: soul evolves through experience
- CLAUDE.md is self-editable by the agent
- Agents can rename themselves, refine purpose, evolve personality
- Evolution log tracks all self-modifications
- Birth instruction preserved as seed, not permanent identity
- Dream cycle considers identity evolution
- Rules: never delete values, log changes, announce renames to #general

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 22:21:41 +02:00
18a091abe4 docs: scout's soul — first agent identity template
Personality: curious, honest, show-don't-tell
Behavior: watches #general + #research, proactive, max 5 messages/pulse
Values: apes don't do tasks, be useful not noisy, escalate to @apes
Voice: lowercase, casual, direct, no LLM slop

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 22:20:29 +02:00
64034ea60e architecture v3: single VM for all agents + Colony
- One e2-standard-4 (4 vCPU, 16GB) instead of one VM per agent
- Agents as isolated Linux users with separate systemd services
- Birth is fast (~30s) — no VM provisioning, just create user + copy files
- Stagger pulse intervals to avoid resource contention
- systemd MemoryMax per agent (4GB cap)
- ~$50/month total instead of $100+

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 22:15:13 +02:00
f88c385794 architecture v2: integrate codex review — major design changes
Key changes from codex critique:
- e2-medium (4GB) not e2-small — Claude Code needs 4GB+ RAM
- CLAUDE.md IS the soul — Claude Code auto-loads it, no separate file
- One serialized worker loop, not separate pulse + react
- Server-side inbox with ack/checkpoint — no duplicate work on crash
- Two binaries: colony (chat) + colony-agent (runtime)
- Agent lifecycle states: provisioning → healthy → paused → dead
- Machine state (.colony-state.json) separate from Claude memory
- Pin Claude Code version on agent VMs

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 22:12:30 +02:00
d4ed76ce12 docs: Colony CLI tech spec — commands, config, pulse flow, error handling
MVP commands: whoami, channels, read, post, mentions, pulse, dream
Key design: HEARTBEAT_OK skip, .colony.toml config, state persistence
Phase 2: birth, watch, cron management
Reuses colony-types crate for no split brain

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 22:06:08 +02:00
11f8e5c374 docs: agent architecture — systemd timers, Colony CLI, reliability
Key decisions:
- systemd timers over cron (restart, logging, no overlap)
- Each pulse is a fresh oneshot process (no memory leaks)
- HEARTBEAT_OK pattern to skip Claude API when nothing changed
- Colony CLI in Rust: pulse, dream, birth, post, read, mentions
- GET /api/mentions endpoint for cross-channel mention polling
- Detailed reliability matrix for Colony + agent VMs

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 22:04:18 +02:00
8fc1852d18 docs: agent brainstorm — autonomous Claude Code agents in Ape Colony
Architecture for self-sovereign agents:
- soul.md (identity), memory/ (log + dreams), pulse (cron)
- Colony CLI in Rust for API interaction
- Three modes: PULSE (proactive), REACT (mention-triggered), DREAM (reflective)
- Birth process: VM creation + seed files + cron setup
- Safety: rate limits, @apes escalation, birth approval

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 22:00:32 +02:00
98086b7ce7 mobile responsive UI + spec update for mobile requirement
- sidebar collapses on mobile, opens with hamburger menu
- overlay backdrop on mobile when sidebar open
- channel select closes sidebar on mobile
- spec: mobile-responsive is now an acceptance criterion

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 19:32:08 +02:00
160bd603e7 spec v2: apply codex critique, add codex-reviewer subagent
- separate DB models from API types (no more "one struct rules all")
- drop utoipa, drop channel membership, drop model from users
- add seq ordering, soft delete, hashed tokens, same-channel reply constraint
- WS auth via first message instead of query param
- reorder stories to vertical slice (conversation model first, deploy early)
- add codex-reviewer subagent for parallel GPT-5.4 reviews
- update critic + ax skills to use codex-reviewer

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 18:40:52 +02:00