2f09ad4a - Loosen error-fix ownership to device-level, add a one-shot decide dispatcher

[Danswar]

EN:
Loosens error-fix conclusion/implement-task ownership from session-exact to device-level, adds agent watch error-decide (a one-at-a-time dispatcher that starts a fresh, one-shot session per unresolved error, instead of relying on a single persistent session), and requires a brief field on error.fix conclusions.

DE:
Lockert die Besitz-Prüfung für error-fix-Konklusionen/Implement-Tasks von session-exakt auf Device-Ebene, fügt agent watch error-decide hinzu (ein Ein-nach-dem-anderen-Dispatcher, der pro offenem Fehler eine frische Einmal-Session startet, statt auf eine dauerhafte Session zu setzen), und macht ein brief-Feld auf error.fix-Konklusionen verpflichtend.

Details

Why

The existing error-fix skill's single-persistent-session model has no mechanism to auto-continue between queued items — each session does one thing, then sits idle until manually re-knocked. Rather than build that "keep it going" nudge, this drops the persistent session entirely: a fresh, uniquely-named session is started per error, does its one job (investigate, conclude), and stops.

What changed

• src/agent_cli/error_fix_act.py, src/agent_cli/errors.py: _error_seen, _lookup_implement_task, incident_closed, validate_conclusion all dropped their session_id parameter/filter, keeping only device-level (_origin_device_id) ownership checks. Necessary because a fresh one-shot session writes the conclusion under its own session id, different from the error.seen row's session id (the fixed scanning session named in error-fix.json).
• src/agent_cli/error_decide_act.py (new) + main.py: agent watch error-decide drains unconcluded error.seen rows oldest-first (by payload.first_seen), one at a time — starts a fresh runner session (skills error-fix, spine, review-loop, pr-review), knocks it directly (not via knock.deliver, which would target the wrong session), retries the knock's Enter keypress with an is_busy() confirmation (a freshly-started session isn't always ready for input immediately — found and fixed via a real end-to-end run, not just unit tests), polls for its conclusion with a timeout, stops the pane. Not wired into agent daemon in this revision.
• validate_conclusion now requires a brief field on error.fix (short text: what's broken, likely cause, where to look), matching the existing reason requirement on error.skip.
• DESIGN.md §21 and the error-fix skill's SKILL.md updated to match.

Verification

Full local suite: 700 passed, 1 pre-existing unrelated skip (missing optional agent_core package). Ran the actual dispatcher twice against a real, isolated Postgres store and a real grok session (not the repo's own store) — confirmed a real error.seen row gets picked up, investigated, and concluded with a real error.skip, and the session is cleanly stopped afterward.

[Danswar]

EN:
Superseded by #55 — this branch's commits didn't follow CONTRIBUTING.md's commit-message rules (session-id prefix, missing periods) and couldn't be fixed without a force-push outside the allowed case, so the same change was rebuilt on a fresh branch with clean commits instead.

DE:
Ersetzt durch #55 — die Commits dieses Branches folgten nicht den Commit-Message-Regeln aus CONTRIBUTING.md (Session-ID-Präfix, fehlende Punkte) und liessen sich nicht ohne einen nicht erlaubten Force-Push korrigieren, daher wurde dieselbe Änderung auf einem neuen Branch mit sauberen Commits neu aufgebaut.