Failed to authenticate. API Error: 401 {"type":"error","error":{"type":"authentication_error","message":"Invalid authentication credentials"},"request_id":"req_011Cb1oFXSKe4iePHNc84shJ"}
[2026-05-14] vault sync
This commit is contained in:
Alexey Martemyanov
+7
-6
@@ -20,9 +20,10 @@ Activity log for the daily Eagle wiki-curation cron job.
|
||||
## 2026-05-14
|
||||
|
||||
- Orientation: read SCHEMA.md, index.md, log.md; scanned family/how-to/ and work/ for updates
|
||||
- Updated `personal-os-architecture.md`: expanded MCP Servers section — Eagle (Mac M4) uses obsidian-mcp-wrapper.js; Taiga (TrueNAS) + Kraken (RPi5) both use mcpvault with Tavily; Claude Code sessions clarified as Eagle-only. Bumped last_updated to 2026-05-14.
|
||||
- Updated `personal-os-agent-rules.md`: added wiki-curation cron (02:00 daily, Hermes, silent). Bumped last_updated to 2026-05-14.
|
||||
- Fixed `obsidian-mcp-wrapper.md`: added missing YAML frontmatter (namespace, tags, last_updated, confidence)
|
||||
- Updated `index.md`: bumped date to 2026-05-14, added Total pages: 15
|
||||
- Lint results: all 15 pages present in index ✅; no broken wikilinks found ✅; no orphan pages (all reachable from index) ✅; 1 frontmatter fix applied (obsidian-mcp-wrapper.md) ✅; `personal-os-agent-rules.md` and `personal-os-architecture.md` had stale `last_updated: 2026-04-28` — corrected ✅
|
||||
- No new pages needed (Taiga/Kraken already covered in architecture; wiki-curation now documented in agent-rules)
|
||||
- Updated `personal-os-architecture.md`: bumped last_updated to 2026-05-14, corrected Eagle cron list (removed old executor-autonomous, added wiki-curation), updated Executor section to reflect v2 (executor-runner.sh + executor-analyzer.sh replacing LLM cron, paused 2026-05-11)
|
||||
- Updated `personal-os-purpose.md`: fixed "Discord-facing" → "Zulip-facing" agent description; bumped last_updated to 2026-05-14
|
||||
- Updated `personal-os-self-modification.md`: fixed "show the diff in Discord" → "show the diff in Zulip"; bumped last_updated to 2026-05-14
|
||||
- Fixed `obsidian-mcp-wrapper.md`: added missing outbound wikilinks (`[[personal-os-architecture]] [[personal-os-agent-rules]]`) and restored История section
|
||||
- Lint: all 15 pages in index ✅; no broken wikilinks ✅; no orphan pages ✅; frontmatter complete on all pages ✅; stale content fixed ✅
|
||||
- New pages needed: none (executor-security-analysis.md and zulip-migration.md live in work/projects/ — domain appropriate, no wiki pages required)
|
||||
|
||||
|
||||
@@ -118,3 +118,7 @@ Wrapper сам вызывает `/opt/homebrew/bin/obsidian-mcp /Users/admin/obs
|
||||
**2026-05-09 (2)** — фикс large payload: Buffer-based line splitting вместо string split
|
||||
(`edit_note` с большим контентом молча дропался). Добавлен per-call watchdog (5s timeout → kill & retry).
|
||||
MAX_RETRY повышен с 5 до 10.
|
||||
|
||||
## Related
|
||||
|
||||
[[personal-os-architecture]] [[personal-os-agent-rules]]
|
||||
|
||||
@@ -22,7 +22,7 @@ See: `personal-os-purpose.md`
|
||||
### Орёл / Eagle (Tactician + reactive layer) — Hermes Zulip agent
|
||||
- Reads `~/context/status.md`, daily/weekly briefs, vault via obsidian MCP
|
||||
- Zulip streams: `daily-brief` `inbox` `focus` `executor` `projects` `journal` `retrospector`
|
||||
- Cron jobs: generate-daily-brief (07:00 MTWRF), morning-brief (08:30 MTWRF), eod-summary (18:00 MTWRF), inbox-check (30 min 09–19 MTWRF), weekly-plan (Mon 08:00), weekly-review (Fri 17:00), retrospector (Fri 17:30), executor-autonomous (every 30 min 09–18 MTWRF), commit-vault (23:00 daily)
|
||||
- Cron jobs: morning-brief (08:30 MTWRF), eod-summary (18:00 MTWRF), inbox-check (30 min 09–19 MTWRF), weekly-plan (Mon 08:00), weekly-review (Fri 17:00), retrospector (Fri 17:30), commit-vault (23:00 daily), wiki-curation (02:00 daily)
|
||||
- Logs corrections to `corrections_log` table (SQL INSERT, silently on pushback)
|
||||
- **Never accesses Asana API directly** — only reads pre-rendered markdown and DB
|
||||
|
||||
@@ -38,14 +38,13 @@ See: `personal-os-purpose.md`
|
||||
- Prompt: `~/Developer/personal-os/agent/prompts/executor-bug-fix.md`
|
||||
|
||||
**Autonomous mode**: hourly cron (09–18 workdays) → #executor
|
||||
- Maintains a queue from: My Hack Days, Watched, O-L Backlog, stale My Tasks
|
||||
- Analyzes tasks → posts "[Auto] Ready to start" with complexity/feasibility
|
||||
- Waits for "go {gid}" to start; no reply = moves to next analysis
|
||||
- Max 1 active fix at a time; handles CI/review on open draft PRs
|
||||
- Stops touching a PR once Alex moves it out of draft or pushes commits
|
||||
- No Asana comments; no touching other people's PRs
|
||||
> ⚠️ Stale as of 2026-05-11: Original LLM-orchestrated autonomous cron **paused**. Replaced by v2 bash daemons:
|
||||
|
||||
**Autonomous mode (v2 — bash daemons, active 2026-05-11+):**
|
||||
- `executor-runner.sh` — cron `*/5`; processes queued/in_progress/pr states; max 2 concurrent workers; spawns focused worker prompt per state; exits when no actionable tasks remain
|
||||
- `executor-analyzer.sh` — cron `*/5`; picks one unanalyzed task, runs `claude -p` analysis prompt, sets `for_review`/`awaiting_go`/`skip`, exits; restarts for next task
|
||||
- Worker prompts in `~/Developer/personal-os/agent/prompts/executor-worker-*.md`
|
||||
- Queue state in `executor_queue` table; live plan: `~/Developer/personal-os/briefs/executor-queue.md`
|
||||
- Prompt: `~/Developer/personal-os/agent/prompts/executor-autonomous.md`
|
||||
|
||||
**Shared**:
|
||||
- Worktree at `~/DuckDuckGo/apple-browsers.git/.claude/worktrees/executor-{gid}-{slug}/`
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
---
|
||||
namespace: work
|
||||
tags: [system, purpose, adhd, design]
|
||||
last_updated: 2026-04-28
|
||||
last_updated: 2026-05-14
|
||||
confidence: 1.0
|
||||
---
|
||||
|
||||
@@ -40,7 +40,7 @@ The system has enough moving parts. New capabilities go into existing components
|
||||
| Agent | Role | When |
|
||||
|-------|------|------|
|
||||
| **Стратег (Strategist)** | Data pipeline — reads Asana + ActivityWatch, writes status.md | Every 30 min, workdays |
|
||||
| **Орёл / Eagle (Tactician)** | Discord-facing reactive agent — briefs, inbox, focus gating | Cron + on-demand |
|
||||
| **Орёл / Eagle (Tactician)** | Zulip-facing reactive agent — briefs, inbox, focus gating | Cron + on-demand |
|
||||
| **Ретроспектор (Retrospector)** | Weekly pattern analysis — corrections, quadrant drift, visibility | Friday 17:30 |
|
||||
| **Исполнитель (Executor)** | On-demand bug-fix worker — analysis → fix → PR → CI loop | Explicit trigger only |
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
---
|
||||
namespace: work
|
||||
tags: [system, self-modification, eagle, meta]
|
||||
last_updated: 2026-04-28
|
||||
last_updated: 2026-05-14
|
||||
confidence: 1.0
|
||||
---
|
||||
|
||||
@@ -20,7 +20,7 @@ How Eagle (and Alex via Claude Code) can safely evolve the system without breaki
|
||||
Eagle reads and writes its own prompts. When Alex says "add X to the morning brief" or "change how inbox triage handles Y":
|
||||
|
||||
1. Read the current prompt: `~/Developer/personal-os/agent/prompts/<name>.md`
|
||||
2. Draft the change, show the diff in Discord
|
||||
2. Draft the change, show the diff in Zulip
|
||||
3. On confirmation: write the file
|
||||
4. Commit: `cd ~/Developer/personal-os && git add agent/prompts/<name>.md && git commit -m "[YYYY-MM-DD] prompt: <description>"`
|
||||
|
||||
|
||||
Reference in New Issue
Block a user