jac/so-many-crows
1
0 Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

spec: repeated misses never touch trust; surfaced via the guard summary (section 13 q3 closed)

Browse Source
This commit is contained in:
Smokey committed 2026-10-27 23:55:26 -06:00
1 parent ab9bc53ccb
commit 5cfb038e7d
1 file changed
+2 -2
Download Patch File Download Diff File Expand all files Collapse all files
CHATROOM_SPEC.md
+2 -2
View File
@@ -107,7 +107,7 @@ Triggered only by the owner ("debate this," "have them argue"). The moderator po
## 10. Trust ladder in the chatroom [proposed]
- Trust is still earned per crow and per task type.
- Trust decides **when a crow may speak unprompted** (section 5) and **what needs owner approval.**
- A missed expectation is a nudge, not a penalty. [decided] Whether repeated misses should affect trust is open.
- A missed expectation is a nudge, not a penalty. [decided] Repeated misses **never** change trust directly. [decided 2026-10-27] The 3-loop guard already ends stalled work; its owner summary surfaces the pattern. Trust moves only on owner verdicts (approve/reject), so Jev can't silently demote a crow over a hard task.
## 11. What changes from today's prototype
| Today | Chatroom |
@@ -134,7 +134,7 @@ Each step: show it, adjust, then the next.
## 13. Open questions
1. Names for the assistant and COS crows (to be decided later).
2. ~~Can Jev score custom expectation labels?~~ Answered: yes, Jev takes custom questions (see `JEV_STRATEGIES.md`).
3. Should repeated misses ever affect trust?
3. ~~Should repeated misses ever affect trust?~~ Answered [decided 2026-10-27]: no — misses stay nudges; the 3-loop guard surfaces patterns to the owner in its summary; trust moves only on owner verdicts (section 10).
4. ~~Does the Sentry survive as a role, or fold into the COS?~~ Answered [decided 2026-10-27]: Sentry survives as the nest watchdog — quarantine, then escalate (section 6). Triage folds into dispatch.
5. ~~How does the message kind get tagged: the model's own header, the classifier, or both?~~ Answered [decided 2026-10-27]: **both, Jev first** — Jev's tag above its band stands; the crow's header is the fallback; disagreements log (section 4 rules).
6. What data does Jev need to score model choice well (flight-log stats per model and task type, owner approvals), and how much history before its scores are trusted?