wiki(audit): 2026-10-28 window — radar stage-1 iteration cap (no handoff, stage-2 no-oped), stocktake 400 never alerted, Steel removed from the stack

This commit is contained in:
hermes
2026-10-29 00:41:30 +08:00
parent 2cbf0b65c1
commit ec0c30fb30
12 changed files with 374 additions and 27 deletions
+26 -3
View File
@@ -3,8 +3,8 @@ title: Browser Backend
type: system
status: active
created: 2026-07-22
updated: 2026-10-13
verified_on: 2026-10-13
updated: 2026-10-29
verified_on: 2026-10-29
confidence: high
tags: [browser, camofox, automation]
sources: [live-probe, config, session-history]
@@ -20,7 +20,7 @@ Browser automation for Hermes — web search, form filling, screenshot, CDP cont
- **Provider config:** `browser.cloud_provider: camofox`, `camera_provider: camofox`
- **REST API:** **`:9377`** — live-verified 2026-10-13 (`node server.js`, `CAMOFOX_PORT=9377`; `LISTEN *:9377`). **The `:9093` figure in earlier revisions of this page is stale** — nothing was listening on 9093 on 2026-10-13.
- **VNC viewer:** NovNC `websockify` on `127.0.0.1:6080` → `127.0.0.1:5900`, published as `https://ct460.kangaroo-eel.ts.net/vnc-camofox`
- **Steel Browser (CT201):** Still running but Hermes not connected — plugin disabled
- **Steel Browser (CT201):** **Not reachable as of 2026-10-29 00:3x** — host answers ping (2.5 ms) but CDP `:9223` and REST `:3000` refuse; plugin removed. See the 2026-10-29 correction below.
## Camofox (local `systemd --user` service)
@@ -109,6 +109,29 @@ until the next session starts.
the Hermes host (CT460). Containment drop-in documented. Same day, the 07:01 Job Radar session was audited
end-to-end and its memory-pressure evidence added above.
## Correction (2026-10-29) — Steel is out of the stack, not just disabled
Verified against live state at **2026-10-29 00:3x AWST**:
- **Hermes is back on Camofox.** `config.yaml` (mtime **2026-10-29 00:15:13**) reads
`browser.cloud_provider: camofox`, `browser.camera_provider: camofox`, `engine: auto`, `cdp_url: ""`.
- **The `browser-steel` plugin is gone** — `~/.hermes/plugins/browser-steel/` no longer exists and
`plugins.enabled` carries no steel entry, so the `plugin_steel` toolset cannot be selected. Backup taken
immediately before the change: `config.yaml.bak-pre-steel-plugin-removal-20261028T161324Z` (written
**2026-10-29 00:13:24**). A second backup, `config.yaml.bak-pre-cloudprovider-fix-20261028T220057Z`, records
the 2026-10-28 22:00 attempt.
- **The Steel endpoint is not serving.** `ping 100.96.244.39` (runtipi/CT201) answers **2.5 ms**, but
`http://100.96.244.39:9223/json/version` (CDP) and `http://100.96.244.39:3000/v1/health` (REST) both return
**000** — as does the LAN address `192.168.178.77:9223`. The tunnel route
`https://runtipi.kangaroo-eel.ts.net/steel` returns **502**, and `steel.martinwa.org` no longer resolves.
Earlier pages describing Steel as "still running on CT201" are superseded by this probe.
- ⚠ **Stale environment variable still exported:** `STEEL_BASE_URL=http://100.96.244.39:3000` is present in
**10 live Hermes processes** — the gateway tree (`3371780`, `3372125`, `3372912`, `3844013`, `3880214`,
`3880663`), `agent-browser` 0.26.0 (`3843841`), two chromium crashpad handlers (`3843878`, `3843880`) and
`agentmail-webhook.py` (`402`). It now points at a dead endpoint and clears only when the gateway is
restarted. The config is explicit (`cloud_provider: camofox`), so it does not currently misroute browser
calls — but it is a trap for anything that reads the variable.
## Related
- [[comparisons/steel-vs-camoufox]]
- [[concepts/browser-automation]]
+4 -3
View File
@@ -3,8 +3,8 @@ title: Scheduled Tasks
type: system
status: active
created: 2026-07-22
updated: 2026-10-28
verified_on: 2026-10-28
updated: 2026-10-29
verified_on: 2026-10-29
review_after: 2026-11-03
confidence: high
tags: [cron, scheduled, automation]
@@ -14,7 +14,8 @@ sources: [live-cron-list, live-jobs-json, cron-executions-db]
# Scheduled Tasks
## Count
- **Current as of 2026-10-28 00:2x AWST (live `jobs.json` + `executions.db`) — the radar's budget overrun stopped being silent, and the radar is now two jobs.** Window 2026-10-27: **172 `completed` / 1 `failed`** (+ this audit `running`). The single failure is `dca8482e4f76` (**Daily Marketing Job Radar - Discovery**), which ran **07:01:08 → 11:03:54** (**4 h 2 m 46 s**), closed `failed`, and delivered a report that opens *"INCOMPLETE (tool-call budget exhausted before Notion write stage)"* — discovery/verify/dedup/classify finished, **Notion ingestion, cover-letter generation and the final audit did not run**. Incident row `dca848_e93a538ade6b` opened **11:03:53**, `alerted` 11:03:59, **still open** (`failure_type: auth`, which does not describe a budget fault) → [[incidents/2026-10-27-job-radar-budget-exhausted]]. **Response, same day:** the radar was split into a **two-stage pipeline** — stage 1 `dca8482e4f76` (Discovery, `0 7 * * 1-5`, `deliver: local`, failures → topic 1030) and new stage 2 **`5fc292ff0f3b`** (Daily Marketing Job Radar - Write and Letters, `30 11,14 * * 1-5`, Telegram topic 1030, created **2026-10-27T17:34:15**; two test fires the same evening, 17:35:00 → 17:36:52 and 17:38:38 → 17:43:42, both `completed`, delivery `suppressed`, `last_status: ok`) → [[runbooks/job-radar]]. **Fleet 28 → 29 jobs (26 enabled / 3 disabled).** **Unclosed incident rows 3 → 2:** the two rows the 2026-10-26 planned restart raised (`ea79a2_a4661554a3c2`, `ea79a2_c3ab2d784ba3`) **auto-closed 00:38:32**, and the radar row opened. **Non-clean `last_status` 4 → 5** (churn): `ea79a2107e36` cleared to `ok`; `dca8482e4f76` joined as `error` (streak 1) and `08eb86f02d37` re-joined as `delivery_queued` — still non-clean: `0e753e9720fd` (error), `fad5a86979d4` (delivery_failed), `066bb5191280` (delivery_failed). **Pins unchanged.** The 2026-10-26 orphan class **did not recur** — every 10-27 run except the radar's completed.
- **Current as of 2026-10-29 00:3x AWST (live `jobs.json` + `executions.db`) — the radar's two-stage split ran for real and the discovery stage still could not finish: stage 1 hit the agent iteration cap and wrote no handoff, so both stage-2 slots correctly no-oped.** Fleet unchanged at **29 jobs (26 enabled / 3 disabled)**; non-clean `last_status` **5 → 5**; unclosed incident rows **2 → 4**. Window **2026-10-28 settled 168 / 2**, and both failures are in-window. `dca8482e4f76` (Job Radar stage 1) ran **07:00:32 → 10:33:18** (**3 h 32 m 46 s**), closed **`failed`**, **`failure_streak: 2`**, on *"hit the agent iteration cap before the handoff could be written"*; `~/.hermes/radar-ref/handoff/` holds only `2026-10-27.json`, and stage 2 (`5fc292ff0f3b`) fired **11:30:27 → 11:31:31** and **14:30:27 → 14:31:43**, both `completed` / **`suppressed`** — the no-op path, confirmed in production → [[incidents/2026-10-28-job-radar-stage1-iteration-cap]]. The other failure is the **03:00 stocktake** (`1a8e90ea2271`): **03:00:28 → 03:37:58** (37 m 30 s), `failed`, **streak 1**, delivery `suppressed`, on `RuntimeError: [400] … duplicate field 'reasoning_content' at line 1 column 512203` — the provider could not deserialize the model's own 512 KB final response. It filed incident `1a8e90_f57ab4cafab8` in state **`detected`** and **never alerted**, and left `systems/skills-index.md` modified and `raw/stocktake/freshness-20261028.txt` untracked; the 2026-10-29 audit committed both. **Steel left the stack in-window:** `browser.cloud_provider`/`camera_provider` are back to **`camofox`** (config mtime 2026-10-29 00:15:13), the `browser-steel` plugin was **removed** (backup `config.yaml.bak-pre-steel-plugin-removal-20261028T161324Z` written 00:13:24), and the endpoint is **not serving** — CDP `:9223`/REST `:3000` refuse, tunnel `/steel` **502**, `steel.martinwa.org` unresolved — while **`STEEL_BASE_URL=http://100.96.244.39:3000` is still exported into 10 live Hermes processes** and clears only on a gateway restart → [[systems/browser-backend]], [[decisions/rollback-steel-to-camofox]]. **2026-10-27 settled 173 / 1** (was 172 / 1 at the 2026-10-28 audit — one late run landed after that count). **Pins: 12 `smart-route` / 6 `free-stack` / 7 unpinned / 1 `deepseek-paid-smart`.**
- **Prior window — as of 2026-10-28 00:2x AWST** (live `jobs.json` + `executions.db`) — the radar's budget overrun stopped being silent, and the radar is now two jobs.** Window 2026-10-27: **172 `completed` / 1 `failed`** (+ this audit `running`). The single failure is `dca8482e4f76` (**Daily Marketing Job Radar - Discovery**), which ran **07:01:08 → 11:03:54** (**4 h 2 m 46 s**), closed `failed`, and delivered a report that opens *"INCOMPLETE (tool-call budget exhausted before Notion write stage)"* — discovery/verify/dedup/classify finished, **Notion ingestion, cover-letter generation and the final audit did not run**. Incident row `dca848_e93a538ade6b` opened **11:03:53**, `alerted` 11:03:59, **still open** (`failure_type: auth`, which does not describe a budget fault) → [[incidents/2026-10-27-job-radar-budget-exhausted]]. **Response, same day:** the radar was split into a **two-stage pipeline** — stage 1 `dca8482e4f76` (Discovery, `0 7 * * 1-5`, `deliver: local`, failures → topic 1030) and new stage 2 **`5fc292ff0f3b`** (Daily Marketing Job Radar - Write and Letters, `30 11,14 * * 1-5`, Telegram topic 1030, created **2026-10-27T17:34:15**; two test fires the same evening, 17:35:00 → 17:36:52 and 17:38:38 → 17:43:42, both `completed`, delivery `suppressed`, `last_status: ok`) → [[runbooks/job-radar]]. **Fleet 28 → 29 jobs (26 enabled / 3 disabled).** **Unclosed incident rows 3 → 2:** the two rows the 2026-10-26 planned restart raised (`ea79a2_a4661554a3c2`, `ea79a2_c3ab2d784ba3`) **auto-closed 00:38:32**, and the radar row opened. **Non-clean `last_status` 4 → 5** (churn): `ea79a2107e36` cleared to `ok`; `dca8482e4f76` joined as `error` (streak 1) and `08eb86f02d37` re-joined as `delivery_queued` — still non-clean: `0e753e9720fd` (error), `fad5a86979d4` (delivery_failed), `066bb5191280` (delivery_failed). **Pins unchanged.** The 2026-10-26 orphan class **did not recur** — every 10-27 run except the radar's completed. *(superseded by the 2026-10-29 entry above)*
- **Prior window — as of 2026-10-27 00:1x AWST *(superseded by the 2026-10-28 entry above)* (live `jobs.json` + `executions.db`) — a *planned* restart interrupted a live job, and the fleet got a loud failure instead of a silent one.** Window 2026-10-26 settled **169 `completed` / 3 `failed`**, and **all three failures are a single fault**: `ea79a2107e36` (Mnemosyne Health Monitor, 12:01 slot) plus two derivative Mnemosyne Watchdog reds → [[incidents/2026-10-26-planned-restart-orphaned-cron-run]]. 2026-10-25 settled **172 / 2**. **Fleet unchanged: 28 jobs — 25 enabled / 3 disabled** (`d40085da631c` Important-mail monitor, `f77b7e46bd09` Rhino AgentMail Inbox Watcher, `0a7f933d06e2` AgentMail Rhino Inbox Poll). **Non-clean `last_status` 5 → 4:** `c0a9fa314542` (GitHub Trending Radar) and `08eb86f02d37` (Gmail Action Digest) both cleared to `ok`, while `ea79a2107e36` joins as **`error`, streak 2**; `0e753e9720fd` (`error`) and `fad5a86979d4` + `066bb5191280` (`delivery_failed`) unchanged. **Unclosed incident rows 2 → 3:** both `ea79a2_*` rows — 14:33:37 *"Cron execution unverified; reconcile `admissions/724a69108b…json`"* and 14:35:59 *"lost its durable fire claim ownership"* — are still `alerted`, alongside `0e753e_e7f8194a7d06` (`detected` since 2026-10-01). **One row closed:** `c0a9fa_764558b5ae83` auto-closed **09:13:00** when the radar's 09:00 slot ran clean — **every row of the 2026-10-16 503 resource-pressure incident is now closed** → [[incidents/2026-10-16-omniroute-503-resource-pressure]]. **Pins unchanged:** 11 `custom:omni-101` / `smart-route`, 6 `custom:omni-101` / `free-stack`, 2 `custom:omni` / `smart-route`, 1 `custom:omni-101` / `deepseek-paid-smart`, 8 unpinned (global default still `custom:omni-101` / `smart-route`). **One gateway start on 2026-10-26** (14:35:18, after a planned `SIGTERM` at 14:33:35; teardown 54.06 s, `.clean_shutdown` marker **skipped**) → [[systems/hermes-agent]]. ⚠ **`fad5a86979d4`'s 03:08 slot completed but delivered `delivery_failed`** — *Thread 34795 not found*, so the digest fell back to the unthreaded chat; the gateway's own shutdown notice hit the same dead thread at 14:33:37. ⚠ **The radar's 07:00 slot closed `completed` at 09:10 but delivered “RUN INCOMPLETE — tool-call budget exhausted”** — no Notion writes, no cover letters — and the same morning its cover-letter PDF pipeline moved to Chromium-over-canonical-HTML with model `deepseek-paid-smart` → [[runbooks/job-radar]]. ⚠ **Off-cron, unchanged: Nous Portal credentials still invalid** → [[incidents/2026-10-22-nous-portal-refresh-token-invalid]]. **Sessions in window: 17** (15 `cron`, 1 `ios`, 1 `telegram`).
- **Current as of 2026-10-26 00:1x AWST** *(superseded by the 2026-10-27 entry above)* **(live `jobs.json` + `executions.db`)** — **fleet is clean, but one job misbehaved badly and the global model default moved back.** Window 2026-10-25 settled **172 `completed` / 2 `failed`**; **both failures are `08eb86f02d37` (Gmail Action Digest)**, which also fired **six times that day** → [[incidents/2026-10-25-gmail-digest-runaway-and-refire]]. 2026-10-24 settled **168 / 0** (the 2026-10-25 entry read 167 — its day was still open). **Fleet unchanged: 28 jobs — 25 enabled / 3 disabled**; all 28 IDs still on this page. **Unclosed incident rows still 2** (`0e753e_e7f8194a7d06` `detected` since 2026-10-01; `c0a9fa_764558b5ae83` `alerted` since 2026-10-19) — **nothing opened or closed in-window, so neither 10-25 failure raised an incident row.** Non-clean `last_status` **4 → 5**: `08eb86f02d37` joins as **`delivery_queued`** with an **empty** `last_error` (never resolved to `ok`), alongside `0e753e9720fd` (`error`), `fad5a86979d4` + `066bb5191280` (`delivery_failed`) and `c0a9fa314542` (`error`, streak 1). **Pins unchanged:** 11 `custom:omni-101` / `smart-route`, 6 `custom:omni-101` / `free-stack`, 2 `custom:omni` / `smart-route`, 1 `deepseek-paid-smart`, 8 unpinned. ⚠ **Global default reverted to OmniRoute on 2026-10-24 19:06** (`custom:omni-101` / `smart-route`), so the 8 unpinned jobs are back on the same upstream as the pinned ones — **the fleet is a single path again** → [[systems/current-profile]]. ⚠ **Three gateway starts on 2026-10-25** (00:32:20, 18:30:04, 19:27:13; gateway pid 2476414 up since 19:26:33) — the five extra digest fires bracket the evening pair → [[systems/hermes-agent]]. ⚠ **Nous Portal credential still invalid** (`Invalid refresh token`) — context summaries unavailable on 10-25 (20 log lines); all 8 `auxiliary` slots were moved to `no-think/freeapi/auto` on `custom:omni-101` at 19:13 → [[incidents/2026-10-22-nous-portal-refresh-token-invalid]]. **Sessions in window: 21** (18 `cron` — 15 `smart-route`, 2 `free-stack`, 1 `deepseek-paid-smart`; 1 `desktop`; 1 `oneshot`; 1 `telegram`).
- **Current as of 2026-10-25 00:1x AWST (`jobs.json.updated_at 2026-10-25T00:12:26+08:00`) — a third consecutive clean cron day, and an off-cron fault that is not the fleet's.** Window 2026-10-24: **167 `completed` / 0 `failed`** (+ this audit `running`); **2026-10-23 settled at 170 / 0** (169 at the 10-24 audit). That makes **10-22 → 10-24 three clean days in a row**. **Fleet unchanged: 28 jobs — 25 enabled / 3 disabled.** **Unclosed incident rows still 2** and **nothing opened or closed in-window:** `c0a9fa_764558b5ae83` (`alerted` since 10-19, next slot Mon 10-26 09:00) and `0e753e_e7f8194a7d06` (`detected` since 10-01, next slot 11-01). **Non-clean `last_status` still 4:** `c0a9fa314542` (`error`, streak 1 — Mon 10-26), `0e753e9720fd` (`error`, 0 — 11-01), `fad5a86979d4` and `066bb5191280` (`delivery_failed` — Mon 10-26 / 11-01). **Pins unchanged:** 11 `custom:omni-101` / `smart-route`, 8 unpinned (global default), 6 `custom:omni-101` / `free-stack`, 2 `custom:omni` / `smart-route`, 1 `custom:omni-101` / `deepseek-paid-smart` (this audit). **14 sessions in the window: 11 `cron` + 3 `desktop`** — two of the `desktop` ones are the 12:53–12:56 call requests that the agent refused → [[incidents/2026-10-24-conduit-call-request-refused]]. ⚠ **New off-cron fault, open: the agent told Anthony it cannot make phone calls**, three times, with **zero tool calls**, while `conduit_call_user` was one `tool_search` away → same incident page. *(Superseded by the 2026-10-26 entry above.)*
+6 -2
View File
@@ -3,8 +3,8 @@ title: Installed Skills
type: system
status: active
created: 2026-07-22
updated: 2026-10-27
verified_on: 2026-10-27
updated: 2026-10-29
verified_on: 2026-10-29
confidence: high
tags: [skills, hermes]
sources: []
@@ -531,3 +531,7 @@ This page is auto-regenerated from the live skill inventory. Do not hand-edit.
## Yuanbao (1)
- `yuanbao` — # Yuanbao Group Interaction
## Recent stocktake runs
- **2026-10-28 03:00** — regenerated this index (**302 skills**, mtime 03:01:40) and wrote `raw/stocktake/freshness-20261028.txt` (**2 stale / 103 fresh / 4 no-date of 109 pages**), then **failed** before committing: `RuntimeError: [400] … duplicate field 'reasoning_content' at line 1 column 512203` (provider `custom:omni-101 / free-stack`). Incident `1a8e90_f57ab4cafab8` (`detected`, no alert). This index and the freshness file were left uncommitted and were committed by the 2026-10-29 wiki audit — see [[systems/scheduled-tasks]] and [[incidents/2026-10-28-job-radar-stage1-iteration-cap]].