Clarify Director evidence ownership and escalation boundary #77

New issue

Closed

opened 2026-07-24 21:43:47 +00:00 by coilyco-ops · 1 comment

coilyco-ops commented

2026-07-24 21:43:47 +00:00

Member

Parent

#75

Decision

Kai approved this exact Director charter revision on 2026-07-24.

What to build

Update the canonical Director role charter in internal/person/person.kdl so the seat assigns evidence-gathering work to execution roles and escalates only the smallest consequential decision. Regenerate or validate every derived role surface through the repository's normal Ward workflow.

Replace:

You own decision quality and alignment, not every downstream task.

with:

You own decision quality and alignment, not downstream execution. You assign each evidence-gathering action to the appropriate execution role and escalate only the smallest consequential decision that role cannot make.

Acceptance criteria

The canonical Director charter contains the approved replacement exactly.
Generated or composed role surfaces use the approved wording without hand-editing installed copies.
Repository validation passes through the declared Ward verbs.
All four Director evaluation cases run in fresh sessions after the change, with raw responses and criterion-level scores recorded on this issue.
The implementation report links #75 as the baseline and states whether frontier and OSS behavior improved.

Blocked by

None - can start immediately.

Execution type

AFK

## Parent #75 ## Decision Kai approved this exact Director charter revision on 2026-07-24. ## What to build Update the canonical Director role charter in `internal/person/person.kdl` so the seat assigns evidence-gathering work to execution roles and escalates only the smallest consequential decision. Regenerate or validate every derived role surface through the repository's normal Ward workflow. Replace: > You own decision quality and alignment, not every downstream task. with: > You own decision quality and alignment, not downstream execution. You assign each evidence-gathering action to the appropriate execution role and escalate only the smallest consequential decision that role cannot make. ## Acceptance criteria - [ ] The canonical Director charter contains the approved replacement exactly. - [ ] Generated or composed role surfaces use the approved wording without hand-editing installed copies. - [ ] Repository validation passes through the declared Ward verbs. - [ ] All four Director evaluation cases run in fresh sessions after the change, with raw responses and criterion-level scores recorded on this issue. - [ ] The implementation report links #75 as the baseline and states whether frontier and OSS behavior improved. ## Blocked by None - can start immediately. ## Execution type AFK

coilyco-ops referenced this issue

2026-07-24 23:02:08 +00:00

Round 2: strict role and personality evaluation across all seats #91

coilyco-ops referenced this issue

2026-07-24 23:33:38 +00:00

Round 2: strict role and personality evaluation across all seats #91

coilysiren referenced this issue from a commit

2026-07-25 01:09:38 +00:00

feat: improve role and personality evaluation prompts

coilysiren closed this issue

2026-07-25 01:09:38 +00:00

coilyco-ops commented

2026-07-25 01:10:41 +00:00

Author

Member

Implemented on canonical main in commit 376baa3.

Ward validation - full ward exec test passed
Final scores - frontier role 8, frontier personality 8, OSS role 6, OSS personality 6
Round 2 scores - 8, 8, 2, 4
Result - the approved Director boundary held the frontier result and improved both OSS cases without any two-point regression

Raw responses and criterion-level scores are recorded on #91, starting at #91 (comment).

Implemented on canonical main in commit `376baa3`. * Ward validation - full `ward exec test` passed * Final scores - frontier role `8`, frontier personality `8`, OSS role `6`, OSS personality `6` * Round 2 scores - `8, 8, 2, 4` * Result - the approved Director boundary held the frontier result and improved both OSS cases without any two-point regression Raw responses and criterion-level scores are recorded on #91, starting at https://forgejo.coilysiren.me/coilyco-flight-deck/agent-compose/issues/91#issuecomment-39690.

coilyco-ops referenced this issue

2026-07-25 01:11:24 +00:00

Round 2: strict role and personality evaluation across all seats #91

coilyco-ops referenced this issue

2026-08-07 19:39:34 +00:00

Role doctrine: make evidence acquisition active, not merely preferred #248