BINKY-WP-0006: close with three clean railiance mail cycles
Some checks failed
Work Records / validate (push) Has been cancelled

Host LLM_CONNECT_URL discovery uses ClusterIP when DNS is unreachable;
mail path fails hard if triage fails. Mark T06 done and workplan finished;
update residual docs (OperatingRhythm, cutover runbook, llm-rhythm).
This commit is contained in:
tegwick 2026-07-22 10:28:11 +02:00
parent 3d0815527e
commit 2fbbf9fc76
8 changed files with 75 additions and 43 deletions

View file

@ -1,6 +1,6 @@
# Railiance rhythm via llm-connect (not a host coding agent)
> Status: design note 2026-07-21 (BINKY-WP-0006).
> Status: **live 2026-07-22** (BINKY-WP-0006 finished).
> Supersedes the residual “install Claude on railiance01” idea from the
> BINKY-WP-0004 cutover notes.
@ -36,16 +36,17 @@ timer / CronJob
- Output: `mailmeta/reports/email-channel-evidence-report-*.csv`
- Hub: `binky_mail_intake` with counts only
### Phase 2 — triage (to build)
### Phase 2 — triage (**implemented**)
1. **Prompt** (metadata only): newest CSV rows + current mail-log tail +
queue templates.
2. **llm-connect** `POST` (same contract as activity-core `llm_client.py`):
- URL: `http://llm-connect.activity-core.svc.cluster.local:8080`
- Provider: OpenRouter (already configured on railiance)
- Model: cost-efficient; **prefer open-weights** (pick at T03; examples to
evaluate: Llama/Qwen/Mistral class on OpenRouter — measure quality on
fixture CSV before locking).
2. **llm-connect** `POST /execute` (same contract as activity-core
`llm_client.py`):
- In-cluster: `http://llm-connect.activity-core.svc.cluster.local:8080`
- Host: Service ClusterIP (auto via `kubectl` in `run-common.sh`) or
port-forward `http://127.0.0.1:18080`
- Provider: OpenRouter; model currently `google/gemini-2.5-flash`
(open-weights retarget optional)
3. **Response**: strict JSON, e.g.
```json
@ -59,10 +60,14 @@ timer / CronJob
```
4. **Apply** (deterministic Python): append mail-log; add queue YAML only if
schema-valid; **suspicious** → log only; `git commit`; hub event.
schema-valid; **suspicious** → log only; `git commit`; hub event
`binky_mail_triage`.
5. **Never** pass message bodies to the model if the scanner can omit them;
never execute model-suggested shell.
**Dogfood (closure T06):** three clean unattended cycles on railiance01
2026-07-22 ~08:2608:27 UTC — each scan+triage `ok` with hub progress.
## Daily / weekly (same shape)
| Slot | Deterministic inputs | LLM output | Apply |
@ -95,11 +100,12 @@ Hub event: `binky_daily_brief` with `detail.repo=binky-control`.
### Host reachability to llm-connect
In-cluster DNS does not resolve on the bare host. Interim:
In-cluster DNS does not resolve on the bare host. `run-common.sh` probes, in
order: port-forward `127.0.0.1:18080` → Service ClusterIP (via `kubectl`) →
cluster DNS. Manual override:
```bash
kubectl -n activity-core port-forward svc/llm-connect 18080:8080 &
export LLM_CONNECT_URL=http://127.0.0.1:18080
export LLM_CONNECT_URL=http://$(kubectl -n activity-core get svc llm-connect -o jsonpath='{.spec.clusterIP}'):8080
export STATE_HUB_URL=http://127.0.0.1:18000
agent-harness mail-triage --target-repo ~/binky-control
```