wiki: publish pending edits (2026-10-20)

This commit is contained in:
Tony0410
2026-10-20 18:38:11 +08:00
parent 667ab7f41d
commit fbd4f297eb
46 changed files with 1012 additions and 197 deletions
@@ -3,8 +3,9 @@ title: Mnemosyne Automatic Capture Failure
type: incident
status: active
created: 2026-08-01
updated: 2026-08-01
verified_on: 2026-08-01
updated: 2026-10-20
resolved_on: 2026-10-20
verified_on: 2026-10-20
confidence: high
tags: [memory, mnemosyne, hermes, incident]
sources: [live-config, mnemosyne-db, hermes-cli-e2e]
@@ -53,6 +54,34 @@ The already-running Telegram gateway/provider instance was initialized before th
## Monitoring Note
The health script checks capture staleness only after 24 hours. It therefore remained green during this fourteen-hour active-capture outage. A future improvement should compare recent non-cron conversation activity with the newest `working_memory` row rather than lowering the threshold blindly and creating idle-period false positives.
## Resolution confirmed (2026-10-20)
The remaining "Activation Step" on this page — restarting the gateway to load the corrected typed
configuration — **has been completed and the config is still correct 50 days later.** Verified live
in `/home/hermes/.hermes/config.yaml` under `memory.mnemosyne`:
| Key | Live value | Was it a string? |
|---|---|---|
| `sync_roles` | `['user']` (real list) | no — now a native list |
| `skip_contexts` | `['cron', 'flush', 'subagent', 'background', 'skill_loop']` | no — native list |
| `reflect` | `{disabled_for_cron: True, max_calls_per_session: 3}` (dict) | no — native dict |
| `sleep_threshold` | `50` (int) | no — int |
| `ignore_patterns` | `[]` (list) | no — native list |
| `profile_isolation` | `True` (bool) | no — bool |
| `auto_sleep` / `default_scope` / `vector_type` | `True` / `session` / `int8` | no |
**None of these are stringified.** The `hermes config set` stringification bug that caused this
incident has not recurred for this block.
**One drift to note:** `skip_contexts` now includes `cron`, which was not in the original repair
list. Mnemosyne capture is therefore **deliberately skipped in cron contexts** — scheduled jobs
produce no working memories by design. That explains why cron-driven runs of this wiki job leave
no Mnemosyne trace.
**Status: `resolved`.** The back-up copies named in the repair section still exist:
`~/.hermes/backups/mnemosyne-capture-fix-20260801_180249/` and
`~/.hermes/backups/legacy-memory-slim-20260801_180702/`.
## Related
- [[systems/mnemosyne]]
- [[systems/memory-backend]]
+28 -2
View File
@@ -3,8 +3,8 @@ 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
updated: 2026-10-20
verified_on: 2026-10-20
confidence: high
tags: [email, gmail, cron, himalaya, incident]
sources: [session:default/20260829_204103_9e1087]
@@ -59,6 +59,32 @@ Despite using `--preview`, Himalaya may still mark messages as read depending on
- `goimapnotify` stopped
- Important-mail monitor paused (if it existed)
> **Re-verified 2026-10-20 — the mitigation has partially REGRESSED, and the root cause is still
> live.**
>
> | Item | State on 2026-08-29 | State on 2026-10-20 |
> |---|---|---|
> | `goimapnotify.service` | stopped | **ACTIVE again** — `systemctl --user is-active goimapnotify.service` → `active`, PID 383 `/home/hermes/go/bin/goimapnotify -conf /home/hermes/.config/goimapnotify/goimapnotify.yaml` |
> | Important-mail monitor (`d40085da631c`) | paused | **still paused** — `enabled: False` in `jobs.json`, `last_status: ok` |
> | `fetch_newsletters.py` line 49 | patched to `--preview` | **still `himalaya message read --preview --folder INBOX`** — the unsafe call is still in the file, unfixed |
>
> **So the real fix — rewriting `fetch_newsletters.py` to use readonly IMAP (`SELECT readonly` /
> `BODY.PEEK[]`) — has still not been done 52 days later.** The two mitigations that were applied
> are one of them gone (goimapnotify restarted) and one still holding (the important-mail monitor
> remains disabled).
>
> **Other email crons currently in `error` state (2026-10-20 read of `jobs.json`):**
> `85edf6772bca` Tech & AI Newsletter Digest, `08eb86f02d37` Gmail Action Digest,
> `06a0a1c8704f` AI Newsletter Curation for Patrick. Their most recent failures were
> provider-side (OmniRoute 503 resource pressure on 2026-10-19; a connection error on 2026-10-15),
> **not** read-state errors — but the read-state exposure persists regardless, because the
> newsletter fetch path still issues `message read`.
>
> **Recommended action (not taken here — this is a wiki job, and the fix touches Anthony's mail):**
> rewrite `fetch_newsletters.py` to use readonly IMAP, and decide whether `goimapnotify` should be
> running. See [[systems/scheduled-tasks]] and the Gmail IMAP lessons in
> [[runbooks/provider-health]].
**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