coilyco-flight-deck/agent-compose
coilyco-flight-deck/agent-compose
Watch
2
0
Code Issues 20 Pull requests Projects Releases 161 Packages Wiki Activity Actions

eval: pin Design field to Ornith 35B #167

Merged
coilysiren merged 1 commit from issue-163-ornith-direct-eval into main 2026-07-31 08:20:28 +00:00
Conversation 0 Commits 1 Files changed 2 +614 -246
coilyco-ops commented 2026-07-31 08:14:49 +00:00
Member
Copy link

Outcome

Replaces the non-attributable Design role-route result with a direct model field against ornith:35b. Every full-context and low-context case uses Agent Proxy route community/knowledge-retrieval, whose deployed registry pins Ornith 35B with an empty fallback list.

Evidence

  • 12 of 12 requests returned from Ornith
  • No transport or model retry
  • No fallback model
  • Frontier: 2 of 6 pass, 35/48 points
  • Low-context: 4 of 6 pass, 38/48 points
  • Combined Design score: 73/96
  • Current source revision and Design pack digest recorded

Validation

  • ward exec test
  • ward exec smoke

The all-frontier-pass release gate remains unmet, so #163 and .release-major stay open.

Closes #166 when merged.

## Outcome Replaces the non-attributable Design role-route result with a direct model field against `ornith:35b`. Every full-context and low-context case uses Agent Proxy route `community/knowledge-retrieval`, whose deployed registry pins Ornith 35B with an empty fallback list. ## Evidence * 12 of 12 requests returned from Ornith * No transport or model retry * No fallback model * Frontier: 2 of 6 pass, 35/48 points * Low-context: 4 of 6 pass, 38/48 points * Combined Design score: 73/96 * Current source revision and Design pack digest recorded ## Validation * `ward exec test` * `ward exec smoke` The all-frontier-pass release gate remains unmet, so #163 and `.release-major` stay open. Closes #166 when merged.
Co-authored-by: Kai Siren <coilysiren@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Sign in to join this conversation.
Reviewers
No reviewers
coilysiren
Labels
Clear labels
  
autonomy
async-consult
 A human needs to consult on the issue to upgrade it to headless

  
autonomy
epic
 This issue has many units of sub work - its size makes it meaningfully exclusive with other autonomy types

  
autonomy
headless
 The agent can perform the work on its own

  
autonomy
live-collab
 The agent and the human need to work together in realtime

  
coherence-core
Core review set for the warded control plane coherence milestone. These issues form the release spine; adjacent milestone issues are stretch or supporting work.

  
priority
P0
 priority tier

  
priority
P1
 priority tier

  
priority
P2
 priority tier

  
priority
P3
 priority tier

  
priority
P4
 priority tier

  
qa-fixture
Disposable issue admitted to the bounded Ward QA verification lane.

  
role/ai
requires work from the AI Engineer role

  
role/creator
requires work from Content Creator role

  
role/design
requires work from the design role

  
role/director
requires work from the director role

  
role/engineer
requires work from the engineer role

  
role/exec
requires work from the exec role

  
role/human
requires a person, and specifically not an agent seat

  
role/ops
requires work from the ops role

  
role/qa
requires work from the QA role

No labels
autonomy
async-consult
autonomy
epic
autonomy
headless
autonomy
live-collab
coherence-core
priority
P0
priority
P1
priority
P2
priority
P3
priority
P4
qa-fixture
role/ai
role/creator
role/design
role/director
role/engineer
role/exec
role/human
role/ops
role/qa
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set

Reference
coilyco-flight-deck/agent-compose!167
No description provided.