5df8ece040
feat(companion): export platform shell templates for app starters
2026-02-26 19:03:22 -08:00
f10c896a75
docs(companion): add release bundle install and verification runbook
2026-02-26 19:00:46 -08:00
bbec292434
feat(companion): include checksums in release bundle artifacts
2026-02-26 18:59:44 -08:00
484247e1c1
feat(companion): export release bundle artifacts for shell packaging
2026-02-26 18:58:21 -08:00
ee93061496
feat(companion): add shell bootstrap status location push controls
2026-02-26 18:55:29 -08:00
6620afcf1f
feat(companion): add bootstrap manifest export for app packaging
2026-02-26 18:40:55 -08:00
62c427da4a
feat(setup): add onboarding live checks and first-success guidance
2026-02-26 18:18:12 -08:00
03926a81eb
docs: sync voice reliability updates and phase state
2026-02-26 17:29:29 -08:00
2a9bed8c91
Document companion reconnect/handoff reliability progress
2026-02-26 17:01:22 -08:00
e9873ad22b
Document browser reliability layer and roadmap progress
2026-02-26 14:06:53 -08:00
3cc9e16ef5
feat(subagents): complete queue, budgets, audit, and inspection controls
2026-02-26 13:28:10 -08:00
b679261683
feat(subagents): add idle ttl cleanup and summary tool
2026-02-26 13:12:53 -08:00
2171346116
feat(subagents): add multi-turn subagent session runtime
2026-02-26 13:07:34 -08:00
e887c3c964
docs(plans): add personal assistant productization roadmap
2026-02-26 12:45:06 -08:00
d07e05d4cc
fix(config): change no_tools_mode default to false for pi_embedded
...
The previous default of true was overly restrictive. false is the correct
default — tool-like prompts fall through to native handling only when
explicitly enabled.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-02-26 11:52:43 -08:00
6e63e00b84
docs: Anthropic OAuth browser flow implementation plan
2026-02-26 10:30:22 -08:00
8d41d14266
docs: design Anthropic OAuth browser flow (PKCE + local callback server)
2026-02-26 10:26:15 -08:00
01e4e43a88
docs(state): bump test count after prompt injection test
2026-02-25 18:29:56 -08:00
0a354a597a
docs(memory): document session-start memory and config defaults
2026-02-25 13:02:30 -08:00
ed53d6d215
docs(memory): revise pi personal assistant memory plan after code review
...
Key changes from review:
- Use separate _sessionContext field instead of mutating _systemPromptBase
- Parameterize compaction prompt via buildCompactionPrompt() instead of duplicating
- Fix flaky TTL=0 test to use hardcoded past expiry date
- Route memory extraction to {userNamespace}/facts when namespace is set
- Document future considerations (config refactor, concurrent writes, token counting)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-25 12:50:24 -08:00
40828d424f
docs(memory): add pi personal assistant memory implementation plan
...
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-02-25 12:29:44 -08:00
cc70c3e524
docs(design): Pi-inspired personal assistant memory design
...
Two-tier memory model (working memory + long-term store) with a unified
user namespace across all channels. Addresses four gaps: cross-session
forgetting, compaction context loss, no proactive recall, and channel
fragmentation.
Key design decisions:
- user/working namespace written on every compaction (TTL-based expiry)
- user/profile + user/patterns as shared identity across channels
- Session-start injection before first turn (one-time, idempotent)
- Opt-in via memory.user_namespace config; default is unchanged behavior
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-02-25 12:23:49 -08:00
b5b4cb0a84
docs(state): fix feature gap scorecard and add missing phase entries
...
The scorecard claimed 128/128 (100%) which was never accurate — the
2026-02-06 gap analysis listed 16 MISSING features that remain
deferred. Updated to ~114/130 (~88%) with explicit list of deferred
items: channel adapters (Matrix/Zalo/LINE/Feishu/Mattermost), providers
(MiniMax/Moonshot/Vercel AI/OAuth), native companion apps, ClawHub,
Bonjour/mDNS, skill safety scanner, and elevated mode.
Also added missing progress entries for Phase 3 (companion/canvas/voice
deepening), Phase 4 (rollout/operator readiness), and the post-phase
test fixes.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-02-25 12:02:07 -08:00
787dd61a6d
docs(rollout): add phase 4 readiness plan
2026-02-25 11:23:47 -08:00
eec54ace9d
test(voice): cover tts fallback
2026-02-25 11:21:49 -08:00
e3e98058b0
feat(canvas): persist artifacts and surface UI
2026-02-25 11:18:53 -08:00
ac60fa5be3
feat(companion): add reconnect resilience
2026-02-25 11:12:21 -08:00
7b170cff4d
Phase 2 reactions v2 priority and cooldown
2026-02-25 10:36:56 -08:00
e4ee6acce8
Phase 1 run-control semantics and run_state events
2026-02-25 10:22:44 -08:00
ae21681958
docs(observability): seed phase-0 baseline probe artifacts
2026-02-25 09:42:48 -08:00
8b5266c66c
docs(observability): document phase-0 telemetry and baseline workflow
2026-02-25 09:22:56 -08:00
0b8f7c7299
feat(audit): add phase-0 baseline summary tooling
...
Diagrams reviewed: docs/architecture/AGENT_DIAGRAM.md, docs/architecture/GATEWAY_SESSIONS_AND_QUEUE.md, docs/api/PROTOCOL.md (no changes required).
2026-02-25 09:14:38 -08:00
2311826092
feat(metrics): add phase-0 baseline counters
...
Diagrams reviewed: docs/architecture/AGENT_DIAGRAM.md, docs/architecture/GATEWAY_SESSIONS_AND_QUEUE.md, docs/api/PROTOCOL.md (no changes required).
2026-02-25 09:05:31 -08:00
6bcdb13bf4
feat(observability): emit run and reaction baseline audit events
...
Diagrams reviewed: docs/architecture/AGENT_DIAGRAM.md, docs/architecture/GATEWAY_SESSIONS_AND_QUEUE.md, docs/api/PROTOCOL.md (no changes required).
2026-02-25 08:54:19 -08:00
23b813a92f
feat(audit): add phase0 run/reaction baseline audit events
2026-02-25 00:12:31 -08:00
37be391a40
Unify TUI runtime commands with gateway and harden gateway restart
2026-02-24 13:14:53 -08:00
db2f697741
docs(plan): add OpenClaw gateway-first TUI runtime unification plan
2026-02-24 10:43:01 -08:00
d4d3000656
docs(runtime): document /runtime command path and status semantics
2026-02-24 10:41:38 -08:00
4188c68130
feat: add persisted manual pi backend mode controls
2026-02-23 23:06:40 -08:00
3e5e82c76e
docs(eval): record applied runtime rollback in decision log
2026-02-23 22:48:32 -08:00
8b1f2d9a67
docs(eval): close pi canary phase with rollback decision and probe evidence
2026-02-23 22:44:30 -08:00
7b80c1e7a4
docs(eval): record guard-coverage preprobe window and updated gates
2026-02-23 22:38:18 -08:00
2d42f65b9f
docs(eval): enforce min-sample gates in canary artifacts and decision log
2026-02-23 22:34:54 -08:00
2d31f85c75
docs(eval): add window B telemetry slice and maintain hold decision
2026-02-23 22:31:06 -08:00
9156adb2a8
docs(eval): record pi canary window A results and hold decision
2026-02-23 22:29:08 -08:00
4f88e047fd
docs(plan): add pi canary evaluation gate and tracking (diagram review no topology change)
2026-02-23 22:26:35 -08:00
722f0837f5
docs: document pi_embedded canary path and update state
2026-02-23 21:13:06 -08:00
b6c345eb14
docs(diagrams): refresh ai-optimized mermaid flows after audit
2026-02-23 18:48:10 -08:00
d8188b5425
docs(audit): add report, google auth runbook, and agent repo map
2026-02-23 17:12:41 -08:00
49fd2b5327
fix(daily-briefing): add calendar/tasks scope re-auth guidance
2026-02-23 16:07:12 -08:00
William Valentin