From 0c4ed3350b7f663617b855fd6b64726125ef5461 Mon Sep 17 00:00:00 2001 From: Tony0410 <47945770+Tony0410@users.noreply.github.com> Date: Fri, 2 Oct 2026 00:17:15 +0800 Subject: [PATCH] wiki audit 2026-10-02: 2 new cron failures, cliprox/terra connection auth incident, delivery-failure semantics corrected, profile rewrite, broken wikilinks repaired - new: incidents/2026-10-01-cliproxy-connection-auth-expired.md (HTTP 401, credential fault, cannot self-recover) - systems/scheduled-tasks.md: 30 jobs / 27 enabled; failing 3 -> 6; streaks advanced; wiki-tree drift recorded - systems/messaging-integrations.md: two distinct thread-failure variants (lost vs thread-less fallback) - systems/current-profile.md: full rewrite from live config (no profiles/default/, smart-route, OmniRoute) - current-state.md / index.md / log.md: 2026-10-02 entry - repair: copied 5 vault-only pages referenced by index.md (ignis, nextcloud, 3 incidents) so wikilinks resolve - include pending stocktake output: skills-index.md 2026-09-27, raw/stocktake/freshness-2026-09-2{6,7}.txt --- current-state.md | 16 ++- incidents/2026-08-15-skills-index-drift.md | 43 ++++++++ .../2026-08-18-mnemosyne-capture-pipeline.md | 70 ++++++++++++ incidents/2026-08-29-gmail-read-state.md | 77 +++++++++++++ ...-10-01-cliproxy-connection-auth-expired.md | 74 +++++++++++++ index.md | 5 +- log.md | 10 ++ raw/stocktake/freshness-20260926.txt | 92 ++++++++++++++++ raw/stocktake/freshness-20260927.txt | 92 ++++++++++++++++ systems/current-profile.md | 34 +++--- systems/ignis.md | 64 +++++++++++ systems/messaging-integrations.md | 11 +- systems/nextcloud.md | 47 ++++++++ systems/scheduled-tasks.md | 43 +++++--- systems/skills-index.md | 102 ++++++++---------- 15 files changed, 684 insertions(+), 96 deletions(-) create mode 100644 incidents/2026-08-15-skills-index-drift.md create mode 100644 incidents/2026-08-18-mnemosyne-capture-pipeline.md create mode 100644 incidents/2026-08-29-gmail-read-state.md create mode 100644 incidents/2026-10-01-cliproxy-connection-auth-expired.md create mode 100644 raw/stocktake/freshness-20260926.txt create mode 100644 raw/stocktake/freshness-20260927.txt create mode 100644 systems/ignis.md create mode 100644 systems/nextcloud.md diff --git a/current-state.md b/current-state.md index ce0d2e4..187e47c 100644 --- a/current-state.md +++ b/current-state.md @@ -3,8 +3,8 @@ title: Current State type: concept status: active created: 2026-07-22 -updated: 2026-10-01 -verified_on: 2026-10-01 +updated: 2026-10-02 +verified_on: 2026-10-02 review_after: 2026-10-30 confidence: high tags: [system] @@ -12,7 +12,17 @@ sources: [live-config, live-cron-list, live-hermes-version] --- # Current State -Updated: 2026-10-01 +Updated: 2026-10-02 + +## Recent Changes (2026-10-02) +- **Cron fleet re-verified:** 30 jobs, 27 enabled / 3 disabled (live `~/.hermes/cron/jobs.json`). Failing set **3 → 6**: two *new* failures landed on 2026-10-01 — + - `06a0a1c8704f` (AI Newsletter Curation for Patrick, Thu 10:00) — `HTTP 401 … All 1 connection(s) authentication expired — please reconnect in the dashboard` on provider `custom:Omniroute:20128`, model `cliprox/terra`. Its failure notice reached topic 346; no digest was produced. **Not self-recovering** — needs the OmniRoute connection re-authenticated. Two other enabled jobs share that pin (`1b23c042e17d`, `79f9bb41ecf5`) and will fail next run. + - `0e753e9720fd` (Facebook Birthday Monthly Scrape, 09:00) — `HTTP 400`, `nvidia/deepseek-ai/deepseek-v4-flash` absent from the active NVIDIA catalog, confirming the earlier diagnosis that this is a **shared-pin** problem (sibling `fad5a86979d4` uses the same model). + - `066bb5191280` (Uber Eats Monthly Spend Report, 02:11) — report generated correctly; **delivery** failed with `configured thread_id 34795 for telegram:1793951355 was not found`. +- **Carried-over failures, streaks advanced:** `dca8482e4f76` 403 `MODEL_NOT_IN_PLAN` → streak 6; `1a8e90ea2271` HTTP 410 (retired `qwen3.5:397b`) → streak 8; `fad5a86979d4` HTTP 400 → streak 3. All three still need a model repin. +- **Telegram delivery semantics corrected — a "failed" delivery is not always a lost message.** Against `~/.hermes/cron/executions.db`, the 2026-10-01 failures carry the *fallback* variant: `configured thread_id for telegram: was not found; delivered without thread_id`. Content reaches the DM, yet the run is recorded `delivery_outcome: failed`. The 2026-09-30 incident's `Message thread not found` variant is the one that truly loses the message. Both variants are now documented in [[systems/messaging-integrations]]. +- **The wiki has two trees, and they have drifted in both directions (new finding, 2026-10-02):** the canonical source is **`/home/hermes/workspace/agent-estate-wiki`** — it holds the Gitea remote (`Anthony/agent-estate-wiki`), the Quartz build (`serve.py`, `package.json`, `public/`) and is what `wiki-maintain.sh` commits. **`/home/hermes/wiki/agent-estate-wiki`** is the *Obsidian/Ignis vault copy* (pages nested under `wiki/`, no git remote) that the iPad reads. The nightly audit is told to write to the vault path, so edits that skip the canonical tree never reach Gitea or the published site. Worse, the trees have diverged backwards too: `systems/ignis.md`, `systems/nextcloud.md` and three `incidents/` pages exist **only in the vault**, while `raw/stocktake/*`, `incidents/2026-09-02-sftpgo-outage.md`, `reports/communities-wa-social-media-audit-2026.md` and `agents/` exist **only in canonical**. `index.md` in canonical links `[[systems/ignis]]` and `[[systems/nextcloud]]`, both of which are broken there. Any one-way sync will silently delete pages — reconcile before trusting either tree. See [[systems/scheduled-tasks]]. +- **Skills inventory:** 344 `SKILL.md` under `~/.hermes/skills/` (live count 2026-10-02), against 341 in the last generated [[systems/skills-index]] (2026-09-27). The page cannot refresh while the stocktake job stays broken. ## Recent Changes (2026-10-01) - **Cron fleet re-verified:** 30 jobs, 27 enabled / 3 disabled (live `~/.hermes/cron/jobs.json`). Failing set **4 → 3**: `cbfe434a3b5e` returned to `ok` as predicted on 2026-09-30. The residual `1a8e90ea2271` dispatch error also cleared — its current failure is a different, upstream problem (below). diff --git a/incidents/2026-08-15-skills-index-drift.md b/incidents/2026-08-15-skills-index-drift.md new file mode 100644 index 0000000..6ef21c5 --- /dev/null +++ b/incidents/2026-08-15-skills-index-drift.md @@ -0,0 +1,43 @@ +--- +title: "Skills Index Drift — 4x Undercount" +type: incident +status: resolved +created: 2026-08-15 +updated: 2026-08-15 +resolved_on: 2026-08-15 +confidence: high +tags: [skills, wiki, drift, auto-regeneration] +sources: [session-investigation, agent-estate-wiki] +--- + +# Skills Index Drift — 4x Undercount + +## Summary +The `systems/skills-index.md` page in both wikis claimed **66 skills** when **330 were actually installed** — a 4x undercount. The page had been hand-written once on 2026-07-22/25 and never regenerated as the estate grew. + +## Root Cause +Static documentation for a mutable inventory. The skills tree at `~/.hermes/skills/` grew from ~66 to 330 skills over three weeks, but the wiki page was never updated because there was no automation to keep it in sync. + +## Impact +- Wiki page was 4x out of date +- Any inventory-based decisions (skill loading, capacity planning) would have been based on wrong numbers +- No functional impact — skills still loaded correctly via Tool Search + +## Resolution +1. Regenerated `systems/skills-index.md` from the live skill tree (all 330 skills, 26 categories) +2. Created `regenerate-skills-index.sh` script for automated regeneration +3. Set up cron job `1a8e90ea2271` to run daily at 03:00 AWST +4. Script auto-commits and pushes to Gitea (`Anthony/agent-estate-wiki`) +5. Quartz site at `http://100.118.5.51:9120/systems/skills-index` rebuilt and redeployed + +## Lesson +Static wiki pages that reflect **mutable inventory** (skills, services, cron jobs) **MUST be auto-regenerated on a schedule**, not hand-maintained. The moment the estate grows, a hand-written page becomes stale. + +## Prevention +- Daily cron job regenerates skills-index.md from live tree +- Page includes "auto-regenerated, do not hand-edit" warning +- Same script pattern is reusable for other inventory pages (cron jobs, services, agents) + +## Related +- [[systems/skills-index]] — The updated page +- [[systems/scheduled-tasks]] — The new cron job diff --git a/incidents/2026-08-18-mnemosyne-capture-pipeline.md b/incidents/2026-08-18-mnemosyne-capture-pipeline.md new file mode 100644 index 0000000..7782600 --- /dev/null +++ b/incidents/2026-08-18-mnemosyne-capture-pipeline.md @@ -0,0 +1,70 @@ +--- +title: "Mnemosyne Capture Pipeline Broken (Aug 18)" +type: incident +status: active +created: 2026-08-18 +updated: 2026-08-18 +verified_on: 2026-08-18 +confidence: high +tags: [memory, mnemosyne, hermes, incident, capture] +sources: [mnemosyne-db, health-monitor, run_agent.py] +--- + +# Mnemosyne Capture Pipeline Broken — 2026-08-18 + +## Impact +Working memory capture (`sync_turn`) stopped functioning after **2026-08-16 23:15:39**. As of verification on 2026-08-18, the pipeline had been broken for ~48 hours. Multiple active conversation turns during this period were **not captured** into working memory. The plugin loads, initializes, and tools work — but the post-turn sync path (`_sync_external_memory_for_turn` → `sync_all` → `sync_turn`) is not being triggered. + +**What remains healthy:** +- DB: 27M, 326 WM / 693 EP / 352 facts +- FTS indexes: all aligned (OK) +- Embedding coverage: 100% (WM), 201.6% total +- Last consolidation: within threshold +- Plugin: loads and registers correctly; config types are proper YAML + +## Root Cause +One of the silent guard conditions in `run_agent.py:_sync_external_memory_for_turn()` (line ~4333–4343) is blocking every turn. Three candidates: + +1. `if interrupted: return` — an interrupted flag may be stuck +2. `if not (self._memory_manager and final_response and original_user_message): return` — one of these is falsy +3. `if not (user_text and response_text): return` — text extraction failing + +Unlike the Aug 1 incident (stringified YAML `sync_roles`), the config is now clean — native YAML types verified. The failure is in the runtime guard logic, not configuration. + +## Diagnostic Steps +Add temporary diagnostic logging before each guard in `run_agent.py:_sync_external_memory_for_turn()` (around line 4333): + +```python +if interrupted: + logger.warning("MEMDEBUG: skip - interrupted=True") +if not (self._memory_manager and final_response and original_user_message): + logger.warning("MEMDEBUG: skip - manager=%s final=%s orig=%s", + bool(self._memory_manager), bool(final_response), bool(original_user_message)) +if not (user_text and response_text): + logger.warning("MEMDEBUG: skip - user_text=%s response_text=%s", + bool(user_text), bool(response_text)) +``` + +Then restart gateway (`hermes gateway restart` from external shell) and `grep MEMDEBUG ~/.hermes/logs/agent.log` after one conversation turn to identify which guard fires. + +## Verification +```bash +python3 -c " +import sqlite3 +db = '/home/hermes/.hermes/mnemosyne/data/mnemosyne.db' +conn = sqlite3.connect(db) +cur = conn.cursor() +cur.execute('SELECT MAX(created_at) FROM working_memory') +print('Last WM capture:', cur.fetchone()[0]) # Should be recent +" +``` + +## Prevention +- Never use `hermes config set memory.mnemosyne.` for list/dict/null values +- After any config change, verify YAML types with `yaml.safe_load` + `type()` on each field +- After any gateway restart, verify capture within 2 hours via health monitor + +## Related +- [[systems/mnemosyne]] +- [[incidents/2026-08-01-mnemosyne-capture-failure]] — Previous capture failure (YAML stringification) +- [[incidents/2026-07-29-mnemosyne-relay]] — Earlier relay scope corruption diff --git a/incidents/2026-08-29-gmail-read-state.md b/incidents/2026-08-29-gmail-read-state.md new file mode 100644 index 0000000..b63efae --- /dev/null +++ b/incidents/2026-08-29-gmail-read-state.md @@ -0,0 +1,77 @@ +--- +title: "Gmail Read-State Incident (2026-08-29)" +type: incident +status: active +created: 2026-08-29 +updated: 2026-08-29 +verified_on: 2026-08-29 +confidence: high +tags: [email, gmail, cron, himalaya, incident] +sources: [session:default/20260829_204103_9e1087] +--- + +# Gmail Read-State Incident + +**Date discovered:** 2026-08-29 20:41 AWST +**Status:** Active — mitigation in place, root cause identified but not fully fixed + +## Summary + +Anthony's Gmail inbox messages were being automatically marked as read without his consent. The issue was traced to Hermes cron jobs using Himalaya's `message read` command, which applies the "seen" flag even with `--preview`. + +## Timeline + +- **2026-08-29 20:41** — Anthony reports: "What is marking my Gmail email as read it is not meant to be" +- **Investigation** — Loaded skills: `gmail-imap-email-monitor`, `hermes-cron-operations`, `email-inbox-triage` +- **Root cause identified** — `fetch_newsletters.py` (line 49) runs: + ```bash + himalaya message read --preview --folder INBOX + ``` + Himalaya's `message read` command **automatically applies the "seen" flag** unless `--preview` is used for preview-only access. However, even `--preview` may still mark messages read in some configurations. +- **Other scripts checked** — `gmail_readonly_imap.py` uses `SELECT readonly` and `BODY.PEEK[]` (safe, does not mark read) +- **Mitigation applied:** + - Stopped `goimapnotify.service` (IMAP watcher) + - Paused "Important-mail monitor" cron job (if present) + - Newsletter digest already patched to use `--preview` + +## Root Cause + +The `fetch_newsletters.py` script at `/home/hermes/.hermes/scripts/fetch_newsletters.py` line 49: + +```python +r2 = subprocess.run( + ["himalaya", "message", "read", "--preview", "--folder", "INBOX", m["id"]], + capture_output=True, text=True, timeout=60 +) +``` + +Despite using `--preview`, Himalaya may still mark messages as read depending on configuration. The proper fix is to use readonly IMAP with `BODY.PEEK[]` instead of the `himalaya message read` command. + +## Impact + +- Newsletter emails processed by the Tech & AI Newsletter Digest cron job were marked as read +- Potential for other Gmail automation scripts to have similar behavior +- User trust issue — unexpected state changes in personal email + +## Resolution Status + +**Mitigation:** Partially complete +- `goimapnotify` stopped +- Important-mail monitor paused (if it existed) + +**Fix required:** +- Rewrite `fetch_newsletters.py` to use readonly IMAP (`BODY.PEEK[]`) instead of `himalaya message read` +- Audit all Gmail-related scripts for similar patterns +- Verify `gmail_action_digest_v3.py` and other email scripts use readonly access + +## Related Pages + +- [[systems/scheduled-tasks]] — Tech & AI Newsletter Digest cron job +- [[systems/messaging-integrations]] — Email integration patterns +- [[runbooks/job-radar]] — Email monitoring patterns (for reference) + +## Prevention + +- All Gmail IMAP scripts should use `SELECT readonly` and `BODY.PEEK[]` patterns +- Add a pre-commit check or linting rule for `himalaya message read` usage +- Document readonly email access pattern in a runbook diff --git a/incidents/2026-10-01-cliproxy-connection-auth-expired.md b/incidents/2026-10-01-cliproxy-connection-auth-expired.md new file mode 100644 index 0000000..04978d0 --- /dev/null +++ b/incidents/2026-10-01-cliproxy-connection-auth-expired.md @@ -0,0 +1,74 @@ +--- +title: OmniRoute cliprox/terra Connection Auth Expiry +type: incident +status: open +created: 2026-10-02 +updated: 2026-10-02 +verified_on: 2026-10-02 +confidence: high +tags: [cron, omniroute, provider, auth, incident] +sources: [live-jobs-json, cron-executions-db, cron-session-cron_06a0a1c8704f_20261001_100040] +--- + +# OmniRoute `cliprox/terra` Connection Auth Expiry + +**Window:** first failure 2026-10-01 10:00 AWST (job schedule `0 10 * * 4`); still open +**Status:** Open — not self-recovering +**Impact:** 1 job failed outright; 2 more enabled jobs share the same model pin and are expected to fail on their next runs + +## Symptoms + +Job `06a0a1c8704f` (**AI Newsletter Curation for Patrick**, Thu 10:00) aborted with: + +``` +HTTP 401: [openai-compatible-chat-2ea20f63-…] All 1 connection(s) authentication expired +— please reconnect in the dashboard +``` + +Provider `custom:Omniroute:20128`, model `cliprox/terra`. The run's failure notice was +delivered to forum topic `346`, but no newsletter digest was produced. + +## Root Cause + +A **connection credential at the provider**, not a missing or plan-gated model and not a +routing error. The error names a single connection (`All 1 connection(s)`) whose +authorisation lapsed, so the model pin itself is still valid — the *credential behind it* +is not. + +This matters because it is the one failure class from the 2026-10-01 sweep that **cannot +self-recover**. A retired or plan-gated model stays broken until repinned; an expired +connection stays broken until a human re-authenticates it in the dashboard. + +## Blast Radius + +Three enabled jobs run `cliprox/terra`: + +| Job | Name | Schedule | Delivery | +|---|---|---|---| +| `06a0a1c8704f` | AI Newsletter Curation for Patrick | `0 10 * * 4` | `telegram:-1004321904721:346` | +| `1b23c042e17d` | Enhanced Weekend Adventure Planner | `0 8 * * 5` | `telegram:-1004321904721:102` | +| `79f9bb41ecf5` | Weekly Review | `0 18 * * 0` | `origin` | + +Only `06a0a1c8704f` had run by 2026-10-02; the other two are exposed on their next +scheduled runs. + +## Fix + +Re-authenticate the OmniRoute connection for `cliprox/terra`. Do **not** repin these jobs +to another raw model as a first move — that treats a credential fault as a routing fault +and will produce a second, different outage. If the connection cannot be restored, repin +all three jobs together to a routing alias (`smart-route`). + +## Distinguish From + +- **Plan-gated model** (403 `MODEL_NOT_IN_PLAN`, job `dca8482e4f76`) — the upstream rejects + the model by plan; no credential involved. +- **Retired model** (HTTP 410, job `1a8e90ea2271`) — the model no longer exists upstream. +- **Catalog-missing model** (HTTP 400, jobs `fad5a86979d4` / `0e753e9720fd`) — the model + name is absent from the provider's live catalog. + +## Related + +- [[systems/scheduled-tasks]] +- [[systems/model-providers]] +- [[systems/omniroute]] diff --git a/index.md b/index.md index 9ec3374..71b5370 100644 --- a/index.md +++ b/index.md @@ -1,6 +1,6 @@ # Anthony's Systems Wiki > Operational knowledge for Anthony's agents, infrastructure, -> model routing and automation. Last updated: 2026-10-01 +> model routing and automation. Last updated: 2026-10-02 ## Start here - [[current-state]] — Current systems status @@ -28,10 +28,11 @@ ### Integrations - [[systems/messaging-integrations]] — Telegram, Discord, email, Slack, etc. -- [[systems/scheduled-tasks]] — 30 cron jobs (27 enabled, 3 disabled) +- [[systems/scheduled-tasks]] — 30 cron jobs (27 enabled, 3 disabled; 6 failing as of 2026-10-02) - [[systems/skills-index]] — Installed skills inventory (auto-regenerated daily) ## Incidents +- [[incidents/2026-10-01-cliproxy-connection-auth-expired]] — OmniRoute `cliprox/terra` connection credential expired; 1 job failed, 2 more share the pin (open 2026-10-01) - [[incidents/2026-09-28-hermes-managed-runtime-deps]] — Managed-runtime venvs missing `dotenv`/`mnemosyne` broke every cron worker (resolved 2026-09-30); dependency guard now runs every 15 min - [[incidents/2026-08-18-mnemosyne-capture-pipeline]] — Mnemosyne capture pipeline broken (active); ~48h of turns not captured - [[incidents/2026-08-15-skills-index-drift]] — Skills index 4x undercount (66 vs 330 installed); fixed via auto-regeneration diff --git a/log.md b/log.md index 6946cd2..d01f558 100644 --- a/log.md +++ b/log.md @@ -278,3 +278,13 @@ - **Updated `index.md` and `current-state.md`** — last-updated bumped to 2026-10-01 with a Recent Changes block. - **Vault sync:** the same page edits were mirrored into `/home/hermes/wiki/agent-estate-wiki/wiki/` (Obsidian/Ignis vault) so the iPad view matches the Gitea source. New-page reminders for the vault: pages live under `wiki/`, not at the tree root, and `index.md` sits at the vault root. - No secrets written. + +## [2026-10-02] update | Nightly wiki audit — two new cron failures, delivery-failure semantics, wiki-tree split +- **New page:** `incidents/2026-10-01-cliproxy-connection-auth-expired.md` — job `06a0a1c8704f` (AI Newsletter Curation for Patrick) failed at its 2026-10-01 10:00 run with `HTTP 401: … All 1 connection(s) authentication expired — please reconnect in the dashboard` (provider `custom:Omniroute:20128`, model `cliprox/terra`). Documented as its own incident because it is a **credential** fault, not a model/routing fault, and therefore cannot self-recover. Two more enabled jobs share the pin (`1b23c042e17d`, `79f9bb41ecf5`). +- **Updated `systems/scheduled-tasks.md`** — counts re-verified against live `~/.hermes/cron/jobs.json`: still 30 jobs (27 enabled, 3 disabled), but the failing set moved **3 → 6**. New on 2026-10-01: `06a0a1c8704f` (HTTP 401), `0e753e9720fd` (HTTP 400 — same NVIDIA model pin as the already-failing `fad5a86979d4`, confirming the shared-pin diagnosis), `066bb5191280` (delivery failed; report itself generated). Streaks advanced: `dca8482e4f76` ×5→×6, `1a8e90ea2271` ×7→×8, `fad5a86979d4` ×3. Table rows updated for all seven affected jobs; Known Issues rewritten with the provider detail and a new entry recording the two divergent wiki trees. +- **Updated `systems/messaging-integrations.md`** — corrected a wrong page fact. The page previously stated that a bad `thread_id` always loses the message. The 2026-10-01 records show **two variants**: `Message thread not found` (hard failure, message lost — the 2026-09-30 case) and `configured thread_id for telegram: was not found; delivered without thread_id` (a thread-less fallback send *does* occur, yet the run is still recorded `delivery_outcome: failed`). Readers must not assume "delivery failed" means the message never arrived. Also recorded that two of the three bare-`telegram` jobs failed for real on 2026-10-01, and corrected the offsetting table row that read "not failing today". +- **Updated `systems/current-profile.md`** — full rewrite; the page was last verified 2026-08-28 and four facts had drifted: there is no `~/.hermes/profiles/default/` directory (the default profile is the top-level config; `ops` is the only named sub-profile), the model default is `smart-route` (not `freellmapi-auto`), the default provider is `custom` → `http://100.78.63.20:20128` / OmniRoute (litellm is now only the last fallback entry), and the config is `_config_version: 46`. Added live counts (5 MCP servers, 11 plugins, 344 skills) and the pet/skin/approval settings. +- **Updated `current-state.md`** — new **Recent Changes (2026-10-02)** block; frontmatter dates bumped. +- **Updated `index.md`** — last-updated to 2026-10-02; cron line now notes the failing count. +- **Structural finding — the wiki exists as two trees and they have drifted both ways.** `/home/hermes/workspace/agent-estate-wiki` is canonical: it holds the Gitea remote (`Anthony/agent-estate-wiki`), the Quartz build and is what `wiki-maintain.sh` commits. `/home/hermes/wiki/agent-estate-wiki` is the Obsidian/Ignis vault copy the iPad reads (pages under `wiki/`, no git remote). The audit prompt names only the vault path. The trees have also lost pages in *opposite* directions — `systems/ignis.md`, `systems/nextcloud.md` and three `incidents/` pages exist only in the vault, while `raw/stocktake/*`, `agents/`, `incidents/2026-09-02-sftpgo-outage.md` and `reports/communities-wa-social-media-audit-2026.md` exist only in canonical — so canonical `index.md` currently links two pages that do not exist there. A one-way sync in either direction silently deletes files. This run wrote to **both** trees. +- No secrets written; all credential-shaped values in config remain redacted. diff --git a/raw/stocktake/freshness-20260926.txt b/raw/stocktake/freshness-20260926.txt new file mode 100644 index 0000000..fdc400a --- /dev/null +++ b/raw/stocktake/freshness-20260926.txt @@ -0,0 +1,92 @@ +# Wiki freshness audit — 2026-09-26 +Threshold: >21 days since `updated` + +## STALE (69) + +- [ 66d] comparisons/camoufox-vs-chrome.md (updated 2026-07-22) +- [ 66d] comparisons/hermes-vs-nanobot.md (updated 2026-07-22) +- [ 66d] concepts/agent-memory.md (updated 2026-07-22) +- [ 66d] concepts/model-routing.md (updated 2026-07-22) +- [ 66d] concepts/persistent-shells.md (updated 2026-07-22) +- [ 66d] concepts/tool-calling.md (updated 2026-07-22) +- [ 66d] decisions/index.md (updated 2026-07-22) +- [ 66d] decisions/keep-openrouter-as-fallback.md (updated 2026-07-22) +- [ 66d] decisions/persistent-shell-enabled.md (updated 2026-07-22) +- [ 66d] experiments/index.md (updated 2026-07-22) +- [ 66d] infrastructure/backups.md (updated 2026-07-22) +- [ 66d] infrastructure/credentials-map.md (updated 2026-07-22) +- [ 66d] infrastructure/docker-services.md (updated 2026-07-22) +- [ 66d] infrastructure/domains-and-tunnels.md (updated 2026-07-22) +- [ 66d] infrastructure/network-map.md (updated 2026-07-22) +- [ 66d] queries/retained-research-answers.md (updated 2026-07-22) +- [ 66d] runbooks/backup-wiki.md (updated 2026-07-22) +- [ 66d] runbooks/diagnose-docker.md (updated 2026-07-22) +- [ 66d] runbooks/provider-health.md (updated 2026-07-22) +- [ 66d] runbooks/recover-docker-service.md (updated 2026-07-22) +- [ 66d] runbooks/restart-browser.md (updated 2026-07-22) +- [ 66d] runbooks/restart-hermes.md (updated 2026-07-22) +- [ 66d] runbooks/restore-openrouter.md (updated 2026-07-22) +- [ 66d] runbooks/test-openrouter.md (updated 2026-07-22) +- [ 66d] runbooks/troubleshoot-tool-loop.md (updated 2026-07-22) +- [ 66d] runbooks/update-hermes-safely.md (updated 2026-07-22) +- [ 66d] systems/cloudflare-tunnel.md (updated 2026-07-22) +- [ 66d] systems/headless-server.md (updated 2026-07-22) +- [ 66d] systems/home-assistant.md (updated 2026-07-22) +- [ 66d] systems/messaging-integrations.md (updated 2026-07-22) +- [ 66d] systems/openrouter.md (updated 2026-07-22) +- [ 66d] systems/terminal-backend.md (updated 2026-07-22) +- [ 63d] runbooks/gateway-resource-resilience.md (updated 2026-07-25) +- [ 63d] systems/hermes-agent.md (updated 2026-07-25) +- [ 63d] systems/tool-search.md (updated 2026-07-25) +- [ 62d] systems/homepage-dashboard.md (updated 2026-07-26) +- [ 62d] systems/obsidian.md (updated 2026-07-26) +- [ 60d] runbooks/job-radar.md (updated 2026-07-28) +- [ 60d] runbooks/multiplexer-setup.md (updated 2026-07-28) +- [ 59d] systems/opencode-go.md (updated 2026-07-29) +- [ 58d] systems/hermes-ui.md (updated 2026-07-30) +- [ 56d] incidents/2026-08-01-mnemosyne-capture-failure.md (updated 2026-08-01) +- [ 56d] systems/memory-backend.md (updated 2026-08-01) +- [ 55d] comparisons/steel-vs-camoufox.md (updated 2026-08-02) +- [ 55d] concepts/browser-automation.md (updated 2026-08-02) +- [ 55d] decisions/rollback-steel-to-camofox.md (updated 2026-08-02) +- [ 55d] reports/uber-eats/index.md (updated 2026-08-02) +- [ 55d] systems/browser-backend.md (updated 2026-08-02) +- [ 55d] systems/mnemosyne.md (updated 2026-08-02) +- [ 50d] systems/nanobot.md (updated 2026-08-07) +- [ 45d] comparisons/memory-backends.md (updated 2026-08-12) +- [ 45d] comparisons/model-routers.md (updated 2026-08-12) +- [ 44d] infrastructure/proxmox.md (updated 2026-08-13) +- [ 43d] infrastructure/hosts.md (updated 2026-08-14) +- [ 43d] systems/guanaco.md (updated 2026-08-14) +- [ 43d] systems/omniroute.md (updated 2026-08-14) +- [ 42d] agents/hermes-production.md (updated 2026-08-15) +- [ 42d] agents/index.md (updated 2026-08-15) +- [ 42d] agents/open-claw.md (updated 2026-08-15) +- [ 42d] agents/qwenpaw.md (updated 2026-08-15) +- [ 42d] agents/zeroclaw.md (updated 2026-08-15) +- [ 41d] CONTRIBUTING.md (updated 2026-08-16) +- [ 40d] agents/hermes-chaos.md (updated 2026-08-17) +- [ 40d] agents/nanobot.md (updated 2026-08-17) +- [ 37d] systems/model-providers.md (updated 2026-08-20) +- [ 29d] reports/communities-wa-social-media-audit-2026.md (updated 2026-08-28) +- [ 29d] systems/current-profile.md (updated 2026-08-28) +- [ 22d] current-state.md (updated 2026-09-04) +- [ 22d] incidents/2026-09-02-sftpgo-outage.md (updated 2026-09-04) + +## FRESH (3) + +- [ 5d] infrastructure/tailscale.md +- [ 7d] systems/scheduled-tasks.md +- [ 0d] systems/skills-index.md + +## NO updated DATE (7) + +- SCHEMA.md +- experiments/active/example.md +- incidents/2026-07-29-mnemosyne-relay.md +- incidents/2026-08-04-omniroute-free-deepseek-silent-stops.md +- index.md +- log.md +- reports/uber-eats/2026-07.md + +TOTAL: 69 stale, 3 fresh, 7 no-date of 79 pages \ No newline at end of file diff --git a/raw/stocktake/freshness-20260927.txt b/raw/stocktake/freshness-20260927.txt new file mode 100644 index 0000000..0c37202 --- /dev/null +++ b/raw/stocktake/freshness-20260927.txt @@ -0,0 +1,92 @@ +# Wiki freshness audit — 2026-09-27 +Threshold: >21 days since `updated` + +## STALE (69) + +- [ 67d] comparisons/camoufox-vs-chrome.md (updated 2026-07-22) +- [ 67d] comparisons/hermes-vs-nanobot.md (updated 2026-07-22) +- [ 67d] concepts/agent-memory.md (updated 2026-07-22) +- [ 67d] concepts/model-routing.md (updated 2026-07-22) +- [ 67d] concepts/persistent-shells.md (updated 2026-07-22) +- [ 67d] concepts/tool-calling.md (updated 2026-07-22) +- [ 67d] decisions/index.md (updated 2026-07-22) +- [ 67d] decisions/keep-openrouter-as-fallback.md (updated 2026-07-22) +- [ 67d] decisions/persistent-shell-enabled.md (updated 2026-07-22) +- [ 67d] experiments/index.md (updated 2026-07-22) +- [ 67d] infrastructure/backups.md (updated 2026-07-22) +- [ 67d] infrastructure/credentials-map.md (updated 2026-07-22) +- [ 67d] infrastructure/docker-services.md (updated 2026-07-22) +- [ 67d] infrastructure/domains-and-tunnels.md (updated 2026-07-22) +- [ 67d] infrastructure/network-map.md (updated 2026-07-22) +- [ 67d] queries/retained-research-answers.md (updated 2026-07-22) +- [ 67d] runbooks/backup-wiki.md (updated 2026-07-22) +- [ 67d] runbooks/diagnose-docker.md (updated 2026-07-22) +- [ 67d] runbooks/provider-health.md (updated 2026-07-22) +- [ 67d] runbooks/recover-docker-service.md (updated 2026-07-22) +- [ 67d] runbooks/restart-browser.md (updated 2026-07-22) +- [ 67d] runbooks/restart-hermes.md (updated 2026-07-22) +- [ 67d] runbooks/restore-openrouter.md (updated 2026-07-22) +- [ 67d] runbooks/test-openrouter.md (updated 2026-07-22) +- [ 67d] runbooks/troubleshoot-tool-loop.md (updated 2026-07-22) +- [ 67d] runbooks/update-hermes-safely.md (updated 2026-07-22) +- [ 67d] systems/cloudflare-tunnel.md (updated 2026-07-22) +- [ 67d] systems/headless-server.md (updated 2026-07-22) +- [ 67d] systems/home-assistant.md (updated 2026-07-22) +- [ 67d] systems/messaging-integrations.md (updated 2026-07-22) +- [ 67d] systems/openrouter.md (updated 2026-07-22) +- [ 67d] systems/terminal-backend.md (updated 2026-07-22) +- [ 64d] runbooks/gateway-resource-resilience.md (updated 2026-07-25) +- [ 64d] systems/hermes-agent.md (updated 2026-07-25) +- [ 64d] systems/tool-search.md (updated 2026-07-25) +- [ 63d] systems/homepage-dashboard.md (updated 2026-07-26) +- [ 63d] systems/obsidian.md (updated 2026-07-26) +- [ 61d] runbooks/job-radar.md (updated 2026-07-28) +- [ 61d] runbooks/multiplexer-setup.md (updated 2026-07-28) +- [ 60d] systems/opencode-go.md (updated 2026-07-29) +- [ 59d] systems/hermes-ui.md (updated 2026-07-30) +- [ 57d] incidents/2026-08-01-mnemosyne-capture-failure.md (updated 2026-08-01) +- [ 57d] systems/memory-backend.md (updated 2026-08-01) +- [ 56d] comparisons/steel-vs-camoufox.md (updated 2026-08-02) +- [ 56d] concepts/browser-automation.md (updated 2026-08-02) +- [ 56d] decisions/rollback-steel-to-camofox.md (updated 2026-08-02) +- [ 56d] reports/uber-eats/index.md (updated 2026-08-02) +- [ 56d] systems/browser-backend.md (updated 2026-08-02) +- [ 56d] systems/mnemosyne.md (updated 2026-08-02) +- [ 51d] systems/nanobot.md (updated 2026-08-07) +- [ 46d] comparisons/memory-backends.md (updated 2026-08-12) +- [ 46d] comparisons/model-routers.md (updated 2026-08-12) +- [ 45d] infrastructure/proxmox.md (updated 2026-08-13) +- [ 44d] infrastructure/hosts.md (updated 2026-08-14) +- [ 44d] systems/guanaco.md (updated 2026-08-14) +- [ 44d] systems/omniroute.md (updated 2026-08-14) +- [ 43d] agents/hermes-production.md (updated 2026-08-15) +- [ 43d] agents/index.md (updated 2026-08-15) +- [ 43d] agents/open-claw.md (updated 2026-08-15) +- [ 43d] agents/qwenpaw.md (updated 2026-08-15) +- [ 43d] agents/zeroclaw.md (updated 2026-08-15) +- [ 42d] CONTRIBUTING.md (updated 2026-08-16) +- [ 41d] agents/hermes-chaos.md (updated 2026-08-17) +- [ 41d] agents/nanobot.md (updated 2026-08-17) +- [ 38d] systems/model-providers.md (updated 2026-08-20) +- [ 30d] reports/communities-wa-social-media-audit-2026.md (updated 2026-08-28) +- [ 30d] systems/current-profile.md (updated 2026-08-28) +- [ 23d] current-state.md (updated 2026-09-04) +- [ 23d] incidents/2026-09-02-sftpgo-outage.md (updated 2026-09-04) + +## FRESH (3) + +- [ 6d] infrastructure/tailscale.md +- [ 8d] systems/scheduled-tasks.md +- [ 0d] systems/skills-index.md + +## NO updated DATE (7) + +- SCHEMA.md +- experiments/active/example.md +- incidents/2026-07-29-mnemosyne-relay.md +- incidents/2026-08-04-omniroute-free-deepseek-silent-stops.md +- index.md +- log.md +- reports/uber-eats/2026-07.md + +TOTAL: 69 stale, 3 fresh, 7 no-date of 79 pages \ No newline at end of file diff --git a/systems/current-profile.md b/systems/current-profile.md index 3b1d7a6..1439603 100644 --- a/systems/current-profile.md +++ b/systems/current-profile.md @@ -3,29 +3,35 @@ title: Current Hermes Profile type: system status: active created: 2026-07-22 -updated: 2026-08-28 -verified_on: 2026-08-28 +updated: 2026-10-02 +verified_on: 2026-10-02 confidence: high tags: [system, hermes, profile] -sources: [raw/configs/hermes-config-sanitized.txt] +sources: [raw/configs/hermes-config-sanitized.txt, live-config] --- # Current Hermes Profile ## Active Profile - **Name:** `default` -- **Location:** `~/.hermes/profiles/default/` -- **No other profiles confirmed** +- **Location:** implicit — the top-level `~/.hermes/config.yaml`. There is **no** `~/.hermes/profiles/default/` directory (verified 2026-10-02); `~/.hermes/profiles/` holds only named sub-profiles. +- **Other profiles present:** `ops` only (`~/.hermes/profiles/ops/`) — the Tusk elephant persona, with its own SOUL.md, skills, plugins and memories (last modified 2026-09-30). Other profiles do **not** affect this session; see the profile-isolation note below. -## Key Settings -- **Model default:** `freellmapi-auto` -- **Default provider:** `custom:litellm` → `http://litellm:4000/v1` +## Key Settings (verified against live config 2026-10-02) +- **Model default:** `smart-route` (was `freellmapi-auto` at the 2026-08-28 snapshot; Anthony rejects the free routing combos as a default) +- **Default provider:** `custom` → `http://100.78.63.20:20128` (OmniRoute). The 2026-08-28 record said `custom:litellm` → `http://litellm:4000/v1` — that is now only the *last* entry in the fallback chain (`custom` / `or-inclusionai_ling-2_6-1t`). +- **Fallback chain:** 6 providers, ending at `litellm:4000` +- **Auxiliary vision model:** `stepfun/step-3.7-flash:free` on `nous` - **Switch persistence:** `persist_switch_by_default: false` - **Timezone:** `Australia/Perth` -- **Approvals mode:** off +- **Approvals mode:** `off` (`destructive_slash_confirm: false`, `mcp_reload_confirm: false`) - **Memory:** Mnemosyne, session-scoped, auto-sleep enabled -- **Pet slug:** none -- **Skin:** slate +- **Config version:** `_config_version: 46`; config file ≈514 KB / ≈13,200 lines +- **MCP servers:** 5 configured +- **Plugins enabled:** 11 +- **Pet:** configured slug `rhino`, but `enabled: false` (render mode `unicode`, scale 0.55) +- **Skin:** `slate` +- **Personality:** empty string in config — the active persona comes from `SOUL.md`, not this key ## Paths - Config: `~/.hermes/config.yaml` @@ -34,10 +40,12 @@ sources: [raw/configs/hermes-config-sanitized.txt] - Bin: `~/.local/bin/hermes` ## Current Employment Context -- **Role:** Social Media Officer, Western Australian Department of Communities +- **Role:** Social media / communications, Western Australian Department of Communities - **Started:** August 2026 +- **Background:** 15+ years in marketing and communications across energy, technology, customer engagement and public campaigns - **Relevant working document:** [[reports/communities-wa-social-media-audit-2026]] ## Related - [[systems/hermes-agent]] -- [[model-providers]] \ No newline at end of file +- [[systems/model-providers]] +- [[systems/memory-backend]] diff --git a/systems/ignis.md b/systems/ignis.md new file mode 100644 index 0000000..ac06ba0 --- /dev/null +++ b/systems/ignis.md @@ -0,0 +1,64 @@ +--- +title: Ignis +type: system +status: active +created: 2026-08-19 +updated: 2026-08-19 +verified_on: 2026-08-19 +confidence: high +tags: [ignis, obsidian, browser-native, wiki, docker] +sources: [live-probe, docker-inspect] +--- + +# Ignis + +## Purpose +Browser-native Obsidian interface for the agent estate wiki. Provides full Obsidian functionality (graph view, backlinks, plugins, themes) via a web browser without needing the Electron desktop app. + +## Details +- **Image:** `ignis-subpath:0.8.9` (custom build with subpath support) +- **Container:** `ignis` on CT460 (Hermes LXC) +- **Port:** `8080` (bound to `0.0.0.0`) +- **Tailscale Serve:** `https://hermes.kangaroo-eel.ts.net/ignis` → `http://127.0.0.1:8080` +- **Privileged:** No (subpath build handles glibc threading without it) +- **Restart:** `unless-stopped` + +## Volume Mounts +| Host Path | Container Path | Purpose | +|---|---|---| +| `/home/hermes/wiki/agent-estate-wiki` | `/vaults/wiki` | Wiki vault (read/write) | +| `ignis-data` (named) | `/app/data` | Ignis app data | +| `ignis-obsidian-app` (named) | `/app/obsidian-app` | Obsidian app cache | + +## Environment +- `PUID=1000`, `PGID=1000` +- `VAULT_ROOT=/vaults` — Ignis default is `/vaults`, wiki vault mounted at `/vaults/wiki` +- `WS_ORIGINS=https://hermes.kangaroo-eel.ts.net` — WebSocket origin for Tailscale access + +## Docker Compose +Located at `/home/hermes/docker/ignis/docker-compose.yml` on CT460. + +## Access +- **Tailscale (primary):** `https://hermes.kangaroo-eel.ts.net/ignis` +- **Local (on CT460):** `http://localhost:8080` +- **Quartz (read-only):** `https://hermes.kangaroo-eel.ts.net/wiki` — static site from same vault source + +## Features Confirmed +- Full browser-native Obsidian (themes, plugins, core functionality) +- Multi-tab/multi-device live editing +- Built-in file upload/download +- Graph view, backlinks, outline (requires HTTPS secure context — provided by Tailscale) +- Mobile-optimised UI on small screens + +## Considerations +- **Single-user design** — ideal for personal use, no built-in authentication +- **Security:** Tailscale private network + HTTPS provides access control +- **Git sync:** Vault backed by Gitea git repo; avoid simultaneous edits via Ignis and git to prevent conflicts +- **No plugins installed:** Vault currently has zero Obsidian plugins — no compatibility concerns +- **Quartz coexistence:** Quartz serves a static site from the same vault source; Ignis provides live editing. Both can read from the same files. + +## Related +- [[systems/obsidian]] — Obsidian vault structure +- [[infrastructure/docker-services]] — Docker compose files +- [[infrastructure/hosts]] — CT460 host details +- [[infrastructure/tailscale]] — Tailscale serve routes diff --git a/systems/messaging-integrations.md b/systems/messaging-integrations.md index cfa39de..6a95919 100644 --- a/systems/messaging-integrations.md +++ b/systems/messaging-integrations.md @@ -3,8 +3,8 @@ title: Messaging Integrations type: system status: active created: 2026-07-22 -updated: 2026-10-01 -verified_on: 2026-10-01 +updated: 2026-10-02 +verified_on: 2026-10-02 confidence: high tags: [messaging, telegram, discord, email, integrations] sources: [raw/configs/hermes-config-sanitized.txt, live-jobs-json] @@ -23,7 +23,10 @@ sources: [raw/configs/hermes-config-sanitized.txt, live-jobs-json] ### Delivery target semantics (verified 2026-10-01) - A **bare `deliver: "telegram"` resolves to the home DM (`1793951355`)** — *not* to the primary group. It is not a "send to the main chat" shorthand. - To reach a forum topic you must use the full form **`telegram::`**, e.g. `telegram:-1004321904721:102`. -- Consequence: a job that names a group topic ID but is actually pointed at the DM hard-fails with `configured thread_id … was not found` / `Message thread not found`, and **the message is lost** — it is not silently downgraded to a thread-less send. This caused the 2026-09-30 delivery incident on `fad5a86979d4`, `1b23c042e17d` and `c8d52904e1d6`. +- Consequence: a job that names a group topic ID but is actually pointed at the DM fails with `configured thread_id … was not found` / `Message thread not found`. **Two variants are observed, and they behave differently** (verified 2026-10-02 against `~/.hermes/cron/executions.db`): + - `Message thread not found` — hard failure, **the message is lost** (the 2026-09-30 incident variant). + - `configured thread_id for telegram: was not found; delivered without thread_id` — a **thread-less fallback send** does occur, yet the run is still recorded as `last_status: delivery_failed` / `delivery_outcome: failed`. Content reaches the DM; the delivery is marked failed anyway, so the job record reads like a lost message. + - Do not assume "delivery failed" means the message never arrived — check the error variant before reporting a report as missing. ## Discord - **Status:** enabled, streaming true @@ -51,7 +54,7 @@ sources: [raw/configs/hermes-config-sanitized.txt, live-jobs-json] ## Known Issues - **Telegram thread-delivery failures — resolved 2026-09-30.** Jobs `fad5a86979d4` and `1b23c042e17d` reported `configured thread_id 34795 … was not found`, and `c8d52904e1d6` reported `Message thread not found` (`last_status: delivery_failed`). Root cause was the *target*, not the topic: those jobs used a bare `deliver: "telegram"`, which resolves to the home DM where group topic IDs do not exist. `1b23c042e17d` and `c8d52904e1d6` were retargeted to `telegram:-1004321904721:102` and verified end-to-end. See [[systems/scheduled-tasks]]. -- **Three jobs still deliver to the home DM via a bare `telegram` target** (`0e753e9720fd`, `fad5a86979d4`, `066bb5191280`). Not failing today, but they carry stale `thread_id` errors and sit in the same failure class as the incident above — retarget them to a group topic. +- **Three jobs still deliver to the home DM via a bare `telegram` target** (`0e753e9720fd`, `fad5a86979d4`, `066bb5191280`). **No longer theoretical — two of them failed delivery on 2026-10-01:** `066bb5191280` (02:11) and `0e753e9720fd` (09:01) both recorded `delivery_outcome: failed` with the thread-less-fallback variant above, in the same failure class as the 2026-09-30 incident. Retarget them to `telegram:-1004321904721:`. See [[systems/scheduled-tasks]]. ## Multi-bot group chat (open question, raised 2026-09-30) Anthony asked whether his other Hermes instances (the estate VMs/CTs) could share a group chat. diff --git a/systems/nextcloud.md b/systems/nextcloud.md new file mode 100644 index 0000000..15a90f3 --- /dev/null +++ b/systems/nextcloud.md @@ -0,0 +1,47 @@ +--- +title: Nextcloud +type: system +status: active +created: 2026-08-17 +updated: 2026-08-17 +verified_on: 2026-08-17 +confidence: high +tags: [nextcloud, file-sharing, self-hosted, infrastructure] +sources: [] +--- + +# Nextcloud + +## Overview +Self-hosted file sync and sharing platform running on Proxmox LXC container. + +## Details +- **Container:** CT270 (`nextcloud`) +- **OS:** Debian GNU/Linux 12 (NextCloudPi image via community-scripts) +- **Hostname:** `nextcloud` +- **IP:** `192.168.178.56` (LAN), `100.90.102.19` (Tailscale) +- **Version:** 33.0.2.2 (Nextcloud 33) +- **Public URL:** `nextcloud.martinwa.org` (via Cloudflare Tunnel) + +## Apps +| App | Version | Status | Notes | +|---|---|---|---| +| memories | 8.1.0 | active | Photo management | +| metadata | 0.24.0 | active | | +| ncdownloader | 1.0.23 | **disabled** | Incompatible with NC33 — calls removed method `OC\Server::getAppConfig()` | +| news | 28.7.0 | active | RSS reader | +| nextcloud_announcements | 5.0.0 | active | | + +## Known Issues +- **ncdownloader v1.0.23 incompatible with Nextcloud 33 (2026-08-17):** App calls `OC\Server::getAppConfig()` which was removed in NC33. Crashes the `/settings/admin/overview` page with a fatal error. Fix: disable the app via `occ app:disable ncdownloader`. No data loss — ncdownloader settings preserved in DB, app just needs a compatible update. + +## Access +- Admin user: `Anthony` +- Authentication: user_oidc (OpenID Connect) +- Browser access via iPad (CriOS/150) + +## Related +- [[infrastructure/proxmox]] — Container 270 in LXC table +- [[infrastructure/network-map]] — Network address +- [[infrastructure/domains-and-tunnels]] — Cloudflare Tunnel route +- [[systems/homepage-dashboard]] — Dashboard service entry diff --git a/systems/scheduled-tasks.md b/systems/scheduled-tasks.md index 533877e..987434c 100644 --- a/systems/scheduled-tasks.md +++ b/systems/scheduled-tasks.md @@ -3,8 +3,8 @@ title: Scheduled Tasks type: system status: active created: 2026-07-22 -updated: 2026-10-01 -verified_on: 2026-10-01 +updated: 2026-10-02 +verified_on: 2026-10-02 confidence: high tags: [cron, scheduled, automation] sources: [live-cron-list, live-jobs-json] @@ -13,23 +13,30 @@ sources: [live-cron-list, live-jobs-json] # Scheduled Tasks ## Count -- **Total jobs:** 30 — 27 enabled, 3 disabled (verified from live `~/.hermes/cron/jobs.json`, 2026-10-01) -- **Failing:** 3 — `dca8482e4f76` (403 `MODEL_NOT_IN_PLAN`, streak 5), `1a8e90ea2271` (HTTP 410, model retired upstream, streak 7), `fad5a86979d4` (HTTP 400, model absent from the NVIDIA live catalog, streak 3) -- **Stale status flag:** 1 — `1b23c042e17d` still reads `delivery_failed` from its pre-fix run. The delivery target was corrected on 2026-09-30 and its next run clears the flag. -- Historic count progression: 26 (2026-09-19) → 30 (2026-09-25) → 30 (2026-09-30) → 30 (2026-10-01) +- **Total jobs:** 30 — 27 enabled, 3 disabled (verified from live `~/.hermes/cron/jobs.json`, 2026-10-02) +- **Failing (last run):** 6 — + - `dca8482e4f76` — 403 `MODEL_NOT_IN_PLAN`, streak 6 + - `1a8e90ea2271` — HTTP 410, model retired upstream, streak 8 + - `fad5a86979d4` — HTTP 400, model absent from the NVIDIA live catalog, streak 3 (last run 2026-09-30) + - `06a0a1c8704f` — **new 2026-10-01** — HTTP 401, provider-connection auth expired + - `0e753e9720fd` — **new 2026-10-01** — HTTP 400, same NVIDIA pin as `fad5a86979d4` + - `066bb5191280` — **new 2026-10-01** — delivery failed (DM thread); the report itself generated +- **Stale status flag:** 1 — `1b23c042e17d` still reads `delivery_failed` from its pre-fix run. Its delivery target was corrected on 2026-09-30; the next run (2026-10-02 08:00) clears the flag — but that run is also exposed to the `cliprox/terra` auth fault below. +- **Shared model pin at risk:** 3 enabled jobs run `cliprox/terra` — `06a0a1c8704f`, `1b23c042e17d`, `79f9bb41ecf5`. One of the three (`06a0a1c8704f`) has already failed on that pin. +- Historic count progression: 26 (2026-09-19) → 30 (2026-09-25) → 30 (2026-09-30) → 30 (2026-10-01) → 30 (2026-10-02) ## Job Table | Name | ID | Schedule | Delivery | Skills | Script | Notes | |---|---|---|---|---|---|---| | AgentMail Rhino Inbox Poll | `0a7f933d06e2` | `* * * * *` | origin | terminal | `agentmail-poll.py` | **disabled** since 2026-07-27 (legacy) | -| AI Newsletter Curation for Patrick (Weekly) | `06a0a1c8704f` | `0 10 * * 4` | telegram:-1004321904721:346 | — | — | | +| AI Newsletter Curation for Patrick (Weekly) | `06a0a1c8704f` | `0 10 * * 4` | telegram:-1004321904721:346 | — | — | ⚠ HTTP 401 ×1 (2026-10-01) — `cliprox/terra` provider connection auth expired; shares the pin with `1b23c042e17d`, `79f9bb41ecf5` | | Daily Birthday Checker | `a432898b55a4` | `30 7 * * *` | telegram:1793951355 | — | `birthday_check.py` | | -| Daily Marketing Job Radar | `dca8482e4f76` | `0 7 * * 1-5` | telegram:-1004321904721:1030 | job-search-automation | — | ⚠ 403 `MODEL_NOT_IN_PLAN` ×5 — see Known Issues | +| Daily Marketing Job Radar | `dca8482e4f76` | `0 7 * * 1-5` | telegram:-1004321904721:1030 | job-search-automation | — | ⚠ 403 `MODEL_NOT_IN_PLAN` ×6 — see Known Issues | | DHL Tracking - Parcel 8052838382 | `62619aa6bcb3` | `0 8,11,14,17,20 * * *` | telegram:1793951355 | — | `dhl_tracking_monitor.py` | no-agent; added 2026-09-24 | -| Enhanced Weekend Adventure Planner | `1b23c042e17d` | `0 8 * * 5` | telegram:-1004321904721:102 | — | — | delivery target corrected 2026-09-30 (was bare `telegram` → home DM); `delivery_failed` flag is stale | +| Enhanced Weekend Adventure Planner | `1b23c042e17d` | `0 8 * * 5` | telegram:-1004321904721:102 | — | — | delivery target corrected 2026-09-30 (was bare `telegram` → home DM); `delivery_failed` flag is stale. Runs on `cliprox/terra` — same pin that failed 2026-10-01 | | Evening Stand-Down Briefing | `e530c89f2be0` | `45 18 * * 1-5` | telegram:-1004321904721 | — | `evening_standdown.py` | no-agent | -| Facebook Birthday Monthly Scrape | `0e753e9720fd` | `0 9 1 * *` | telegram | — | — | bare `telegram` → home DM; should be retargeted to a group topic | +| Facebook Birthday Monthly Scrape | `0e753e9720fd` | `0 9 1 * *` | telegram | — | — | ⚠ HTTP 400 ×1 (2026-10-01) — `nvidia/deepseek-ai/deepseek-v4-flash` not in the active NVIDIA catalog; delivery also failed on the DM thread. Bare `telegram` → home DM; retarget to a group topic | | Facebook Birthday Weekly Registry Sync | `fad5a86979d4` | `0 3 * * 1` | telegram | — | `birthday_check.py` | ⚠ HTTP 400 ×3 — `nvidia/deepseek-ai/deepseek-v4-flash` not in the active NVIDIA catalog; bare `telegram` target should move to a group topic | | FreshRSS Midday News Briefing | `ecc1fc13655a` | `0 12 * * *` | telegram:-1004321904721:346 | — | `freshrss_intelligence_v2.py` | | | GitHub Trending Radar — Weekly Roundup | `c0a9fa314542` | `0 9 * * 1` | telegram:1793951355 | — | — | ⚠ Telegram bot token in `github-trending-radar/config.json` revoked (`getMe` → 401); digest builds, push fails | @@ -46,11 +53,11 @@ sources: [live-cron-list, live-jobs-json] | Political News Digest (Mon/Thu) | `0e519874d280` | `0 8 * * 1,4` | telegram:-1004321904721:346 | — | — | | | Rhino AgentMail Inbox Watcher | `f77b7e46bd09` | `every 5m` | origin | — | `agentmail-rhino-watch.sh` | **disabled** since 2026-07-27 (legacy) | | Tech & AI Newsletter Digest (Analytical) | `85edf6772bca` | `0 7 * * *` | telegram:-1004321904721:346 | — | — | | -| Uber Eats Monthly Spend Report | `066bb5191280` | `0 2 1 * *` | telegram | camofox-browser-automation, browser-backend-verification | — | bare `telegram` → home DM; carries a stale DM-thread delivery error | -| Weekly Review | `79f9bb41ecf5` | `0 18 * * 0` | origin | weekly-review | — | | +| Uber Eats Monthly Spend Report | `066bb5191280` | `0 2 1 * *` | telegram | camofox-browser-automation, browser-backend-verification | — | ⚠ delivery failed 2026-10-01 (`configured thread_id 34795 for telegram:1793951355 was not found`) — the 2026-09 report generated fine, only the send failed. Bare `telegram` → home DM; retarget to a group topic | +| Weekly Review | `79f9bb41ecf5` | `0 18 * * 0` | origin | weekly-review | — | runs on `cliprox/terra` — same pin that failed 2026-10-01 | | weekly-save-restricted-bot-restart | `a688ed7b7ab0` | `0 3 * * 0` | local | — | `restart-save-restricted-bot.sh` | no-agent; script restored 2026-09-30 | | Wiki Audit — Nightly | `cbfe434a3b5e` | `59 23 * * *` | local | task-approach | — | Reviews past 24h for wiki changes | -| wiki-stocktake-maintenance | `1a8e90ea2271` | `0 3 * * *` | local | — | `wiki-maintain.sh` | ⚠ HTTP 410 ×7 — `qwen3.5:397b` retired 2026-09-25; needs repinning. Regenerates skills-index, freshness audit, rebuilds Quartz, commits to Gitea | +| wiki-stocktake-maintenance | `1a8e90ea2271` | `0 3 * * *` | local | — | `wiki-maintain.sh` | ⚠ HTTP 410 ×8 — `qwen3.5:397b` retired 2026-09-25; needs repinning. Regenerates skills-index, freshness audit, rebuilds Quartz, commits to Gitea | | 🦝 Hermes Config Backup to Gitea (Daily) | `e27da6c34bbb` | `0 11 * * *` | origin | — | `hermes-config-backup.sh` | no-agent | ## Removed Jobs @@ -76,12 +83,14 @@ sources: [live-cron-list, live-jobs-json] - **Residual pre-fix dispatch errors cleared:** `cbfe434a3b5e` returned to `ok` on its next run as predicted. The `1a8e90ea2271` error of the same era also cleared — its current failure is a *different*, upstream problem (below). ### Open -- **Daily Marketing Job Radar — 403 `MODEL_NOT_IN_PLAN` (2026-09-26 → 30, streak 5):** Job `dca8482e4f76` is pinned to `custom:omni-101` / `gpt-5.6-terra`; the upstream (`command-code`) rejects it with `GPT-5.6 Terra available in Pro and above plans`. Anthony's primary job pipeline — needs a model or provider change; it cannot self-recover. See [[runbooks/job-radar]]. -- **wiki-stocktake-maintenance — HTTP 410, model retired (streak 7):** Job `1a8e90ea2271` is pinned to `ollama-cloud / qwen3.5:397b`, which Ollama retired on 2026-09-25 (`qwen3.5:397b was retired at 2026-09-25 00:00:00 -0700 PDT`). It cannot self-recover — it needs a new model pin. Until then the daily 03:00 stocktake (skills-index regeneration, freshness audit, Quartz rebuild, Gitea commit) does not run. -- **Facebook Birthday Weekly Registry Sync — HTTP 400, model missing from catalog (streak 3):** Job `fad5a86979d4` is pinned to `nvidia/deepseek-ai/deepseek-v4-flash`; the provider reports the model is `not available in the active live catalog for provider 'nvidia'`. The sibling job `0e753e9720fd` uses the same pin, so this is an upstream catalog/availability issue rather than a per-job config error. Safest durable fix is repinning to a routing alias (`smart-route`) instead of a raw model name. +- **Daily Marketing Job Radar — 403 `MODEL_NOT_IN_PLAN` (2026-09-26 → 10-01, streak 6):** Job `dca8482e4f76` is pinned to `custom:omni-101` / `gpt-5.6-terra`; the upstream (`command-code`) rejects it with `GPT-5.6 Terra available in Pro and above plans`. Anthony's primary job pipeline — needs a model or provider change; it cannot self-recover. See [[runbooks/job-radar]]. +- **`cliprox/terra` provider connection auth expired — NEW 2026-10-01 (streak 1):** Job `06a0a1c8704f` (AI Newsletter Curation for Patrick) failed with `HTTP 401: [openai-compatible-chat-2ea20f63-…] All 1 connection(s) authentication expired — please reconnect in the dashboard` (provider `custom:Omniroute:20128`, model `cliprox/terra`). Its failure notice reached topic 346; no digest was produced. This is a *credential/connection* problem at the proxy, not a missing model — it will not self-recover until the connection is re-authenticated. **Two more enabled jobs run the same pin** (`1b23c042e17d` Enhanced Weekend Adventure Planner, `79f9bb41ecf5` Weekly Review) and are expected to fail on their next runs. Re-authenticate the OmniRoute connection before repinning anything. +- **wiki-stocktake-maintenance — HTTP 410, model retired (streak 8):** Job `1a8e90ea2271` is pinned to `ollama-cloud / qwen3.5:397b`, which Ollama retired on 2026-09-25 (`qwen3.5:397b was retired at 2026-09-25 00:00:00 -0700 PDT`). It cannot self-recover — it needs a new model pin. Until then the daily 03:00 stocktake (skills-index regeneration, freshness audit, Quartz rebuild, Gitea commit) does not run. The page most visibly affected is [[systems/skills-index]], whose last generated run was 2026-09-27 (341 skills) against 344 skills live on 2026-10-02. +- **Facebook Birthday scrapes — HTTP 400, model missing from catalog (streak 3 / 1):** Job `fad5a86979d4` (weekly) is pinned to `nvidia/deepseek-ai/deepseek-v4-flash`; the provider reports the model is `not available in the active live catalog for provider 'nvidia'`. **Confirmed as a shared-pin issue on 2026-10-01**, when sibling job `0e753e9720fd` (monthly) failed on the same pin at its own 09:00 run. Safest durable fix is repinning both to a routing alias (`smart-route`) instead of a raw model name. - **GitHub Trending Radar — revoked Telegram bot token:** Job `c0a9fa314542` builds its digest successfully, then fails the Telegram push (`getMe` → 401 Unauthorized). The token lives in `/home/hermes/workspace/github-trending-radar/config.json` and needs replacing from @BotFather. Digest content is recoverable from the script's `--dry-run` output in the interim. - **Stale provider key `custom:omni` (2 jobs):** the provider was removed from `custom_providers` (the live 2026-10-01 set is `litellm`, `guacano`, `Omniroute:20128`, `command-code`, `omni-101`). Jobs `e530c89f2be0` and `d40085da631c` still name it; both run `smart-route`, and the default `custom` provider resolves to the same base URL (`http://100.78.63.20:20128`), so no failure has been observed — but the references should be normalised to `custom:omni-101`. -- **Bare `telegram` delivery targets (3 jobs):** `0e753e9720fd`, `fad5a86979d4`, `066bb5191280` deliver to the home DM rather than a group topic. Not a failure by itself, but it is the same class of misconfiguration that caused the 2026-09-30 thread-delivery incident, and it leaves stale `thread_id` errors on their records. Retarget to `telegram:-1004321904721:`. +- **Bare `telegram` delivery targets (3 jobs) — now demonstrably breaking sends:** `0e753e9720fd`, `fad5a86979d4`, `066bb5191280` deliver to the home DM rather than a group topic. As of 2026-10-01 this is no longer theoretical: `066bb5191280` (02:11) and `0e753e9720fd` (09:01) both recorded `delivery_outcome: failed` with `configured thread_id 34795 for telegram:1793951355 was not found`. Work generated correctly; the delivery did not. Retarget all three to `telegram:-1004321904721:`. See [[systems/messaging-integrations]]. +- **Two wiki trees, drifted in both directions (NEW 2026-10-02):** `/home/hermes/workspace/agent-estate-wiki` is the canonical source (Gitea remote `Anthony/agent-estate-wiki`, Quartz build, `wiki-maintain.sh` target). `/home/hermes/wiki/agent-estate-wiki` is the **Obsidian/Ignis vault copy** the iPad reads — pages nested under `wiki/`, and **no git remote at all**. The nightly audit job's prompt names only the vault path, so edits that miss the canonical tree never reach Gitea or the published site. The two have also diverged *backwards* (`systems/ignis.md`, `systems/nextcloud.md`, three `incidents/` pages exist only in the vault; `raw/stocktake/*`, `agents/`, `incidents/2026-09-02-sftpgo-outage.md` only in canonical) — a naive one-way sync deletes pages. See [[systems/hermes-agent]]. ### Historical - **Mnemosyne Watchdog incident (2026-08-19):** Job `96eb95ce12f2` cycled for ~2 hours reporting no consolidation for 36–41.5+ hours. See [[systems/mnemosyne]]. diff --git a/systems/skills-index.md b/systems/skills-index.md index f821fee..116d447 100644 --- a/systems/skills-index.md +++ b/systems/skills-index.md @@ -3,8 +3,8 @@ title: Installed Skills type: system status: active created: 2026-07-22 -updated: 2026-09-25 -verified_on: 2026-09-25 +updated: 2026-09-27 +verified_on: 2026-09-27 confidence: high tags: [skills, hermes] sources: [] @@ -20,6 +20,43 @@ This page is auto-regenerated from the live skill inventory. Do not hand-edit. - Category = directory structure under `~/.hermes/skills/` (`category/skill/SKILL.md`). - Skills directly under `~/.hermes/skills/` group under `uncategorized`. +## .Archive (34) + +- `agentmail-webhook-tailscale` — # AgentMail Real-Time Webhook via Tailscale Funnel +- `anthropic-spend-forensics` — # Anthropic Spend Forensics +- `briefing-visualization` — # Briefing Visualization +- `container-cpu-forensics` — # Container CPU Forensics +- `cookie-jar-import` — # Cookie Jar Import +- `cover-letter-generation` — # Cover Letter Generation +- `cron-prompt-service-integration` — # Cron Prompt → Local Service Integration +- `cua-driver-linux-accessibility` — # cua-driver Linux AT-SPI Accessibility Setup +- `custom-dashboard-ops` — # Custom Dashboard Operations (Tony0410/custom-dashboard) +- `decision-briefing-dashboards` — # Decision Briefing Dashboards +- `employment-forms` — # Employment Forms (application & onboarding) +- `guanaco-ops` — # Guanaco Operations +- `hermes-config-backup` — # Hermes Config Backup (Gitea, Daily) +- `hermes-multiplex-telegram-ops` — # Hermes Multiplex Telegram Ops +- `hermes-profile-scoped-platform-troubleshooting` — # Hermes Profile-Scoped Platform Troubleshooting +- `hermes-session-context-ops` — # Hermes Session-Context Operations +- `hermes-web-backend-config` — # Hermes Web Backend Config +- `homelab-migration-planning` — # Test +- `in-repo-documentation` — # In-Repository Documentation +- `jobs-dashboard-server-ops` — # Jobs Dashboard Server Ops +- `llm-proxy-streaming` — # LLM Proxy Streaming Debugging +- `multi-agent-estate-knowledge` — # Multi-Agent Estate Knowledge +- `pve-lxc-intrusion-detection` — # PVE LXC Intrusion / Cryptominer Detection +- `qwenpaw-agent-operations` — # QwenPaw Agent Operations +- `rclone-mount-ops` — # Rclone Mount Operations +- `security-incident-response` — # Security Incident Response +- `self-hosted-dashboard-deployment-verification` — # Self-Hosted Dashboard Deployment Verification +- `session-verification` — # Session Verification Protocol +- `simple-directives-execution` — # Simple Directives Execution +- `soul-md-design` — # SOUL.md Design — Community-Research-Driven Agent Personalities +- `tailscale-cert-for-docker-https` — # Tailscale Cert for Docker HTTPS Services +- `versioning-live-services` — # Versioning Live Services +- `video-translation-dubbing` — # Video Translation and Dubbing Pipeline +- `wiki-web-hosting` — # Wiki Web Hosting + ## Apple (4) - `apple-notes` — # Apple Notes @@ -62,14 +99,6 @@ This page is auto-regenerated from the live skill inventory. Do not hand-edit. - `cloudflare-tunnel-ops` — # Cloudflare Tunnel Operations 🦝🌐 -## Conduct (1) - -- `simple-directives-execution` — # Simple Directives Execution - -## Cookie Jar Import (1) - -- `cookie-jar-import` — # Cookie Jar Import - ## Creative (18) - `architecture-diagram` — # Architecture Diagram Skill @@ -103,14 +132,12 @@ This page is auto-regenerated from the live skill inventory. Do not hand-edit. - `ddia-systems` — # Designing Data-Intensive Applications Framework -## Devops (132) +## Devops (111) - `abyss-ios-pairing` — # Pair iPhone with The Abyss (iOS) - `agent-extension-audit` — # Agent Extension Audit - `agent-observability` — # Agent Observability - `agent-stack-weekly-review` — # Agent Stack Weekly Review -- `agentmail-webhook-tailscale` — # AgentMail Real-Time Webhook via Tailscale Funnel -- `anthropic-spend-forensics` — # Anthropic Spend Forensics - `browser-automation-recovery` — # Browser Automation Recovery - `browser-backend-verification` — # Browser Backend Verification - `browser-tab-lifecycle-and-recovery` — # Browser Tab Lifecycle & Recovery @@ -120,17 +147,13 @@ This page is auto-regenerated from the live skill inventory. Do not hand-edit. - `chat4000-ops` — # chat4000 Operations & Pairing - `cloudflare-ops` — # Cloudflare Operations - `codex-via-cliproxy` — # Codex CLI via Cliproxy (mitmproxy redirect) -- `container-cpu-forensics` — # Container CPU Forensics - `courier-tracking-monitor` — # Courier / Shipment Tracking Monitor - `crawlee-batch-scrape` — ## Installation - `cron-job-maintenance` — ## Mnemosyne Watchdog Cron Job — Conflict Alert Thresholds (2026-07-25) -- `cron-prompt-service-integration` — # Cron Prompt → Local Service Integration - `cronjob-prompt-hardening` — ## Why This Exists - `cross-profile-session-handoff` — # Cross-Profile Session Handoff - `cua-computer-use` — # CUA Computer Use Automation - `cua-driver-lifecycle` — # cua-driver Lifecycle Management -- `cua-driver-linux-accessibility` — # cua-driver Linux AT-SPI Accessibility Setup -- `custom-dashboard-ops` — # Custom Dashboard Operations (Tony0410/custom-dashboard) - `dashboard-server-ops` — # Dashboard Server Operations - `devops` — (no description) - `docker-management` — # Docker Management @@ -142,11 +165,9 @@ This page is auto-regenerated from the live skill inventory. Do not hand-edit. - `gmail-imap-email-monitor` — # Gmail IMAP Email Monitor (Cron) - `google-apis` — # Google APIs Tool Suite - `google-contacts-birthday-sync` — > **See also:** -- `guanaco-ops` — # Guanaco Operations - `hermes-agent-install` — # Hermes Agent Install & Upgrade - `hermes-agent-ops` — ### Dashboard Auth Plugin — `basic` Must Be Enabled - `hermes-api-vault` — # Hermes API Vault -- `hermes-config-backup` — # Hermes Config Backup (Gitea, Daily) - `hermes-config-diagnostics` — # Hermes Config Diagnostics - `hermes-cron-operations` — # Hermes Cron Operations - `hermes-cron-patterns` — ## Reference Files @@ -156,17 +177,13 @@ This page is auto-regenerated from the live skill inventory. Do not hand-edit. - `hermes-mattermost-integration` — # Hermes Mattermost Integration - `hermes-memory-systems` — # Hermes Agent Memory Systems - `hermes-multi-agent` — # Hermes Multi-Agent Architecture -- `hermes-multiplex-telegram-ops` — # Hermes Multiplex Telegram Ops - `hermes-plugin-live-verification` — # Hermes Plugin Live Verification - `hermes-plugin-ops` — ### Session Learnings (2026-07-07) - `hermes-profile-ops` — # Hermes Profile Operations -- `hermes-profile-scoped-platform-troubleshooting` — # Hermes Profile-Scoped Platform Troubleshooting - `hermes-provider-configuration` — # Hermes Provider Configuration - `hermes-routing-and-domains` — # Hermes Routing & Domains - `hermes-self-diagnosis` — # Hermes Self-Diagnosis -- `hermes-session-context-ops` — # Hermes Session-Context Operations - `hermes-soul-forge` — # Soul Forge Plugin Operations -- `hermes-web-backend-config` — # Hermes Web Backend Config - `hermes-web-tools` — # Hermes Web Tools (this instance) - `hermes-webui-ops` — # Hermes WebUI Operations - `hindsight-docs` — # Hindsight Documentation Skill @@ -181,14 +198,12 @@ This page is auto-regenerated from the live skill inventory. Do not hand-edit. - `homelab-virtual-desktop` — # Homelab Virtual Desktop (for computer-use) - `ignis-ops` — # Ignis Deployment & Operations - `job-board-scraping-reference` — # Job Board Scraping Reference -- `jobs-dashboard-server-ops` — # Jobs Dashboard Server Ops - `kanban-orchestrator` — # Kanban Orchestrator — Decomposition Playbook - `kanban-worker` — # Kanban Worker — Pitfalls and Examples - `linux-systemd-desktop` — # Linux headless desktop as a systemd user service - `litellm-openrouter-key-pooling` — # LiteLLM OpenRouter Key Pooling - `litellm-proxy-ops` — # LiteLLM Proxy Operations - `llm-model-diagnostics` — # LLM Model Diagnostics -- `llm-proxy-streaming` — # LLM Proxy Streaming Debugging - `mattermost-ops` — # Mattermost Operations 🦝📡 - `mattermost-platform-ops` — # Mattermost Platform Operations - `mcp-agent-integration` — # MCP Agent Integration @@ -208,20 +223,14 @@ This page is auto-regenerated from the live skill inventory. Do not hand-edit. - `omniroute-skill-execution` — # Execute Skills on OmniRoute MCP - `openclaw-ops` — # Open-Claw Operations & Configuration - `pre-flight-investigation` — # Pre-Flight Investigation -- `pve-lxc-intrusion-detection` — # PVE LXC Intrusion / Cryptominer Detection - `pve-ops` — # PVE Operations - `pve-vm-console-recovery` — # PVE VM Console Recovery (headless keystroke injection) -- `qwenpaw-agent-operations` — # QwenPaw Agent Operations - `radar-jobs-dashboard` — # RADAR Jobs Dashboard - `readlater-ops` — # ReadLater Operations - `runtipi-container-management` — # Runtipi Container Management - `sdlc-review` — # SDLC Review Skill -- `security-incident-response` — # Security Incident Response - `self-hosted-app-deploy` — # Self-Hosted App Deployment -- `self-hosted-dashboard-deployment-verification` — # Self-Hosted Dashboard Deployment Verification -- `session-verification` — # Session Verification Protocol - `solutions-first-agent-conduct` — # Solutions-First Agent Conduct -- `tailscale-cert-for-docker-https` — # Tailscale Cert for Docker HTTPS Services - `tailscale-ops` — # Tailscale Operations 🦝🔗 - `tailscale-serve-route-management` — # Tailscale Serve Route Management - `tailscale-serve-routes` — # Tailscale Serve Route Management @@ -230,7 +239,6 @@ This page is auto-regenerated from the live skill inventory. Do not hand-edit. - `tmux-config` — # tmux-config - `tool-ecosystem-evaluation` — # Tool Ecosystem Evaluation - `uber-eats-monitor` — # Uber Eats Order Monitor -- `versioning-live-services` — # Versioning Live Services - `vision-model-validation` — # Vision Model Validation via OmniRoute - `watchers` — # Watchers - `web-content-extraction` — # Web Content Extraction — Fallback Techniques @@ -309,13 +317,12 @@ This page is auto-regenerated from the live skill inventory. Do not hand-edit. - `groktocrawl-deployment` — # GroktoCrawl Self-Hosted Deployment -## Hermes (5) +## Hermes (4) - `hermes-personality-soulmd` — # Hermes Personality & SOUL.md - `hermes-telegram-miniapp` — # Hermes Telegram Mini App — Deploy & Operate - `hermes-tts-configuration` — # Hermes TTS & Voice Configuration - `hermes-ui-ops` — # Hermes UI Operations -- `soul-md-design` — # SOUL.md Design — Community-Research-Driven Agent Personalities ## Hermes Api Vault (1) @@ -337,10 +344,6 @@ This page is auto-regenerated from the live skill inventory. Do not hand-edit. - `hermes-themes` — # Hermes Themes Skill -## Homelab Migration Planning (1) - -- `homelab-migration-planning` — # Test - ## Interactive Reference Pages (1) - `interactive-reference-pages` — # Interactive Reference Pages @@ -399,9 +402,8 @@ This page is auto-regenerated from the live skill inventory. Do not hand-edit. - `serving-llms-vllm` — # vLLM - High-Performance LLM Serving - `weights-and-biases` — # Weights & Biases: ML Experiment Tracking & MLOps -## Note Taking (3) +## Note Taking (2) -- `multi-agent-estate-knowledge` — # Multi-Agent Estate Knowledge - `obsidian-vault-from-git` — ## Obsidian Vault from Git - `obsidian-vault-manager` — # Obsidian Vault Manager @@ -417,18 +419,14 @@ This page is auto-regenerated from the live skill inventory. Do not hand-edit. - `pragmatic-programmer` — # The Pragmatic Programmer Framework -## Productivity (30) +## Productivity (26) - `airtable` — # Airtable — Bases, Tables & Records - `box` — # Box -- `briefing-visualization` — # Briefing Visualization -- `cover-letter-generation` — # Cover Letter Generation - `custom-pet-authoring` — # Custom Pet Authoring - `data-share-to-ai-artefact` — # data-share-to-ai-artefact -- `decision-briefing-dashboards` — # Decision Briefing Dashboards - `document-to-action-items` — # Document to Action Items - `docx` — # Docx Skill -- `employment-forms` — # Employment Forms (application & onboarding) - `google-workspace` — # Google Workspace - `maps` — # Maps Skill - `meeting-action-items` — # Meeting Action Items @@ -454,10 +452,6 @@ This page is auto-regenerated from the live skill inventory. Do not hand-edit. - `proxmox-operations` — # Proxmox Operations -## Rclone Mount Ops (1) - -- `rclone-mount-ops` — # Rclone Mount Operations - ## Refactoring Patterns (1) - `refactoring-patterns` — # Refactoring Patterns Framework @@ -503,7 +497,7 @@ This page is auto-regenerated from the live skill inventory. Do not hand-edit. - `software-design-philosophy` — # A Philosophy of Software Design Framework -## Software Development (20) +## Software Development (19) - `code-wiki` — # Code Wiki Skill - `codebase-inspection` — # Codebase Inspection with pygount @@ -511,7 +505,6 @@ This page is auto-regenerated from the live skill inventory. Do not hand-edit. - `dogfood` — # Dogfood: Systematic Web Application QA Testing - `github` — # GitHub - `hermes-agent-skill-authoring` — # Authoring Hermes-Agent Skills (in-repo) -- `in-repo-documentation` — # In-Repository Documentation - `inspecting-hermes-desktop-dom` — # Inspecting the live Hermes desktop DOM - `live-application-verification` — # Live Application Verification - `node-inspect-debugger` — # Node.js Inspect Debugger @@ -546,14 +539,9 @@ This page is auto-regenerated from the live skill inventory. Do not hand-edit. - `ux-heuristics` — # UX Heuristics Framework -## Video Translation Dubbing (1) - -- `video-translation-dubbing` — # Video Translation and Dubbing Pipeline - -## Web (2) +## Web (1) - `blocked-page-recovery` — # Blocked-Page Recovery -- `wiki-web-hosting` — # Wiki Web Hosting ## Web Design Reviewer (1)