stocktake 2026-11-11: 36 stale pages re-verified (0 stale); fallback chain rewritten 4/6 slots; CT333 'clawtest' naming claim corrected; nous 404 credits signature replaces refresh-token 401; estate shrank (VM 310 + CT601 gone)

- freshness: 36 stale / 93 fresh / 3 no-date -> 0 stale / 129 fresh / 3 no-date of 132 (same-day report regenerated after the corrections, per pattern 13)
- skills: 299 skills / 67 categories (count unchanged; generator arithmetic re-verified by hand against the live tree: 300 SKILL.md files - 1 nested duplicate = 299)
- runbooks/test-openrouter: live fallback chain rewritten (primary back to smart-route/custom:omni-101; mimo-v2.5, stepfun, qwen3.5/ollama-cloud out; guacano + kilo-reflection-beam-free in); ollama.com dropped from the URL test list; guacano/litellm noted as internal + key-gated
- comparisons/hermes-vs-nanobot: the 2026-10-20 'CT333 is zeroclaw in Proxmox naming' claim was itself wrong - pct list and hostname both return clawtest
- incidents/2026-10-22-nous: refresh-token failure gone from logs; new signature 404 insufficient_credits_for_paid_model from auxiliary.pulse_memory (ninth slot, back on nous, paid model) - open item revised
- incidents/2026-08-29-gmail: email crons now ok but root cause unfixed 74 days (himalaya message read still in fetch_newsletters.py; goimapnotify back up PID 441; monitor still paused)
- 30 further pages re-verified live and de-flagged with dated probe notes (ct207 ingress, CT205 guanaco v0.8.15, CT270 nextcloud 33.0.2.2, headless stack, hermes-ui both hosts, systemd units + cgroup limits, terminal/tool_search/mnemosyne/custom_providers config blocks, ops profile still deleted, hosts/pve guest lists)
- log.md addendum + index.md date bump; no page deleted, no secrets written
This commit is contained in:
Hermes
2026-11-11 03:52:48 +08:00
parent 7ceaec1a2f
commit 341dda95dd
41 changed files with 579 additions and 102 deletions
+12 -2
View File
@@ -3,8 +3,8 @@ title: Agent Memory
type: concept
status: active
created: 2026-07-22
updated: 2026-10-20
verified_on: 2026-10-20
updated: 2026-11-11
verified_on: 2026-11-11
confidence: high
tags: [concept, memory]
sources: [raw/configs/hermes-config-sanitized.txt]
@@ -37,6 +37,16 @@ How an agent retains facts/context beyond a single conversation turn or session
> - `profile_isolation: true` — memories do not leak across Hermes profiles, which matters now that
> the `ops` profile has been deleted (see [[runbooks/multiplexer-setup]]).
> **Full `memory:` block re-read 2026-11-11 — every value unchanged.** `memory_enabled: true`,
> `provider: mnemosyne`, `memory_char_limit: 5000`, `user_profile_enabled: true`,
> `user_char_limit: 3000`, `flush_min_turns: 6`, `nudge_interval: 10`; Mnemosyne sub-block
> `auto_sleep: true`, `default_scope: session`, `vector_type: int8`, `sleep_threshold: 50`,
> `profile_isolation: true`, `shared_surface_path: data/shared/mnemosyne.db`,
> `shared_surface_read: true`, `sync_roles: [user]`, `ignore_patterns: []`,
> `skip_contexts: [cron, flush, subagent, background, skill_loop]`,
> `reflect: {disabled_for_cron: true, max_calls_per_session: 3}`. The cron-skip is still why
> scheduled jobs like this stocktake leave no Mnemosyne trace.
## Model
- Per-turn conversation content accumulates up to the char limit, then flushes to the Mnemosyne store every 6 turns (rather than every turn) — a batching tradeoff between write frequency and losing very recent context if the process dies mid-batch.
- `scope: session` means recall defaults to the current session rather than a global cross-session pool, unless explicitly widened.
+31 -7
View File
@@ -3,8 +3,8 @@ title: Model Routing
type: concept
status: active
created: 2026-07-22
updated: 2026-10-20
verified_on: 2026-10-20
updated: 2026-11-11
verified_on: 2026-11-11
confidence: high
tags: [routing, model, inference]
sources: [raw/configs/hermes-config-sanitized.txt, current-profile.md]
@@ -16,18 +16,42 @@ sources: [raw/configs/hermes-config-sanitized.txt, current-profile.md]
How Hermes selects providers, applies combos, and enforces context limits.
## Current Flow
- Main path: `custom:litellm` → `http://litellm:4000/v1`
- Default model: `freellmapi-auto`
- OmniRoute used for the **default chat path** (`custom:omni-101` / `smart-route`, since 2026-10-24 19:06) and for **all eight auxiliary slots** (`approval`, `compression`, `curator`, `mcp`, `profile_describer`, `skills_hub`, `title_generation`, `vision` — all `no-think/freeapi/auto` as of 2026-10-25 19:13)
- Main path: `custom:omni-101` / `smart-route` → `http://100.78.63.20:20128` (the OmniRoute node
`omniroute-1`), `api_mode: chat_completions`
- OmniRoute used for the **default chat path** (`custom:omni-101` / `smart-route`, since 2026-10-24 19:06) and for **nine auxiliary slots** (`approval`, `compression`, `curator`, `mcp`, `profile_describer`, `pulse_memory`, `skills_hub`, `title_generation`, `vision` — eight of them on `no-think/freeapi/auto`, plus `pulse_memory`; see the 2026-11-11 note below)
> **Auxiliary slots re-read 2026-11-11 — the set has grown from eight to nine.** Eight slots
> (`approval`, `compression`, `curator`, `mcp`, `profile_describer`, `skills_hub`,
> `title_generation`, `vision`) are unchanged: `provider: custom:omni-101`, `model:
> no-think/freeapi/auto`, each with a two-entry fallback chain
> (`no-think/freeapi/deepseek-v4-flash` → `no-think/kg/kilo-auto/free`, both on `custom:omni-101`).
> **New: `pulse_memory`** — `provider: nous`, `model: anthropic/claude-haiku-4.5`, and it is the
> slot behind the live 404s recorded above: nous is out of credits for that **paid** model, so
> `pulse_memory` is failing right now (3 errors on 2026-11-10 18:02 and 19:19). Also live:
> `auxiliary.free_only: true`.
> **Live `model:` block re-read 2026-10-26 — the default has moved TWICE.**
> `model.default` is **`smart-route`** on provider **`custom:omni-101`**
> (`http://100.78.63.20:20128`), `api_mode: chat_completions`. It moved to `nous` /
> `meituan/longcat-2.5-preview:free` on 2026-10-20 22:01 and **back** on **2026-10-24 19:06:10**.
> A six-provider top-level `fallback_providers` chain is live again, headed by the **dead `nous`
> credential** (`Invalid refresh token` since 2026-10-22).
> A six-provider top-level `fallback_providers` chain is live again, headed by the **dead `nous`**
> credential (`Invalid refresh token` since 2026-10-22).
> → [[systems/current-profile]] · [[incidents/2026-10-22-nous-portal-refresh-token-invalid]]
>
> **Re-read 2026-11-11 — the model block is unchanged, but the `nous` failure signature has moved
> on.** `model.default` is still `smart-route` on `custom:omni-101`
> (`base_url: http://100.78.63.20:20128`, `api_mode: chat_completions`,
> `persist_switch_by_default: false`) and the six-entry `fallback_providers` chain is unchanged in
> membership and order (`nous` → `opencode-zen` → `custom:guacano` → `custom:litellm` →
> `kilocode` → `custom`). The **refresh-token failure is gone from the logs**: `~/.hermes/.env`
> has no `NOUS_API_KEY` and `~/.hermes/auth.json` is live, and no 401/refresh-token error appears
> in `~/.hermes/logs/errors.log`. What *does* appear (3×, most recent **2026-11-10 19:19:33**) is
> **404 `insufficient_credits_for_paid_model`** for `anthropic/claude-haiku-4.5` — a **paid**
> model. So `nous` is no longer dead-at-auth; it is **out of credits for paid models**. Free nous
> models (position 1 is `meituan/longcat-2.5-preview:free`) have not been observed failing. The
> slot actually hit by that paid model is **`auxiliary.pulse_memory`** — see the auxiliary note
> below, which is currently a broken slot.
>
> **The five `custom_providers` and their live base URLs:**
>
+8 -2
View File
@@ -3,8 +3,8 @@ title: Persistent Shells
type: concept
status: active
created: 2026-07-22
updated: 2026-10-20
verified_on: 2026-10-20
updated: 2026-11-11
verified_on: 2026-11-11
confidence: high
tags: [concept, terminal]
sources: [raw/configs/hermes-config-sanitized.txt]
@@ -31,6 +31,12 @@ A background shell session that survives across separate Hermes turns/requests,
> The container-* keys are inert while `backend: local` — the shell is not containerised on this
> box, so `container_memory`/`container_disk` describe a path that isn't taken.
> **`terminal:` block re-read 2026-11-11 — unchanged.** `backend: local`,
> `persistent_shell: true`, `timeout: 180`, `home_mode: auto`, `container_cpu: 1`,
> `container_memory: 5120`, `container_disk: 51200`, `container_persistent: true`,
> `lifetime_seconds: 300`, `docker_mount_cwd_to_workspace: false`, `docker_run_as_host_user: true`,
> `cwd: /home/hermes/workspace/`. The container-* keys are still inert while `backend: local`.
## Why it matters here
Enables multi-step CLI workflows (e.g. a long `git` operation, a build, a watch process) to be resumed across turns without Hermes re-establishing context each time. The tradeoff is a shell can be left in a bad state (stuck process, wrong directory) that silently affects the *next* turn — see [[runbooks/troubleshoot-tool-loop]] for the related tool-loop guardrails that catch some of this.
+7 -2
View File
@@ -3,8 +3,8 @@ title: Tool Calling
type: concept
status: active
created: 2026-07-22
updated: 2026-10-20
verified_on: 2026-10-20
updated: 2026-11-11
verified_on: 2026-11-11
confidence: high
tags: [concept, tool-calling]
sources: [raw/configs/hermes-config-sanitized.txt]
@@ -49,6 +49,11 @@ This is the mechanism behind [[runbooks/troubleshoot-tool-loop]] — that runboo
> (which watches *tool* calls) never fired. Two separate loop-detection mechanisms exist; do not
> assume one covers the other.
> **`tool_loop_guardrails` re-verified 2026-11-11 — unchanged.** `warnings_enabled: true`,
> `hard_stop_enabled: false`, `warn_after {exact_failure: 2, same_tool_failure: 3,
> idempotent_no_progress: 2}`, `hard_stop_after {exact_failure: 5, same_tool_failure: 8,
> idempotent_no_progress: 5}`. A genuinely stuck tool loop still only ever produces a warning.
## Related
- [[concepts/persistent-shells]]
- [[runbooks/troubleshoot-tool-loop]]