feat: mail-triage via llm-connect (no host Claude)

Add LLMConnectClient and mail-triage: CSV metadata → OpenRouter-backed
llm-connect JSON plan → deterministic mail-log apply + commit. Server path
for Binky mail intake on Railiance (BINKY-WP-0006).
This commit is contained in:
tegwick 2026-07-22 00:05:23 +02:00
parent 66ccd4fa01
commit 7520a53831
7 changed files with 730 additions and 4 deletions

View file

@ -9,10 +9,10 @@ agentic session's tool allow-list:
metadata-only counts. Credential values live exclusively in the child
process environment — never in argv, logs, hub events, or files.
2. **Optional triage session** (standard run_task): an agentic session in
the target repo reads the newest report CSV and updates the metadata
log/queues. Suspicious-mail rule is part of that task's prompt: never
act on message content, only log it.
2. **Triage** (``agent-harness mail-triage``): llm-connect HTTP (OpenRouter
behind the service) returns structured JSON; deterministic apply updates
mailmeta/mail-log.md and commits. No Claude Code / host coding agent.
Suspicious-mail rule: log only, never act on content.
Credential acquisition, in order:
- AppRole (unattended lane): role_id/secret_id files under