Record Qwen Case protocol blocker evidence

This commit is contained in:
Svrnty 2026-05-31 21:55:17 -04:00
parent ba712be2be
commit 82ffbacd2a
3 changed files with 71 additions and 9 deletions

View File

@ -22,11 +22,15 @@ The run proves that provider/model admission now reaches Case execution, but doe
not prove Stage 2. Case failed before producing a workspace diff because its not prove Stage 2. Case failed before producing a workspace diff because its
implementer agent result did not satisfy the Case result-envelope contract. implementer agent result did not satisfy the Case result-envelope contract.
The later admitted Qwen local run reproduced the same result-envelope failure
after Case process start. This makes the active blocker the Case agent-result
protocol seam, not model admission.
Acceptance: Acceptance:
- Real Case Stage 2 remains blocked until Case produces a Harness Evidence Interface pass report. - Real Case Stage 2 remains blocked until Case produces a Harness Evidence Interface pass report.
- The admitted provider/model pair remains `openai-codex` / `gpt-5.5`. - The admitted provider/model pair evidence includes `openai-codex` / `gpt-5.5` and `qwen-local` / `qwen3.6-35b-a3b`.
- The admission file remains `.sot/03-PROTOCOLS/CTO-CASE-MODEL-PROVIDER-ADMISSION.openai-codex-gpt-5.5.json`. - The admission files remain `.sot/03-PROTOCOLS/CTO-CASE-MODEL-PROVIDER-ADMISSION.openai-codex-gpt-5.5.json` and `.sot/03-PROTOCOLS/CTO-CASE-MODEL-PROVIDER-ADMISSION.qwen-local-qwen3.6-35b-a3b.json`.
- Evidence must show `case_process_started: true` before this blocker is accepted as the current blocker. - Evidence must show `case_process_started: true` before this blocker is accepted as the current blocker.
- Evidence must show `case_model_admission_status: admitted`. - Evidence must show `case_model_admission_status: admitted`.
- Evidence must show no target repository path was inspected or copied. - Evidence must show no target repository path was inspected or copied.
@ -63,14 +67,43 @@ Acceptance:
- Case stdout evidence: unattended mode auto-selected `Abort`. - Case stdout evidence: unattended mode auto-selected `Abort`.
- Result: Stage 2 is still blocked. - Result: Stage 2 is still blocked.
## Qwen Local Evidence - 2026-06-01
- Harness command class: real Case Stage 2 artificial fixture.
- Run artifact directory: `/home/svrnty/.hermes/profiles/cto-planb/harness-runs/20260601T015208Z-r1-string-slugify-2478256`.
- Case binary path used by harness: `/tmp/workos-case/dist/ca`.
- Case source pin for the built binary: `7959ac917cdeb0983b4aaa20bb9f42021747fed8`.
- Report status: `fail`.
- Backend: `case`.
- Backend exit code: `1`.
- Case process started: `true`.
- Case model provider: `qwen-local`.
- Case model: `qwen3.6-35b-a3b`.
- Case model admission status: `admitted`.
- Source admission status: `not_admitted`.
- No target inspection proof: `stage2-no-target-inspection.json`.
- Changed files: none.
- Patch artifact: `patch.diff`.
- Patch digest: `e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855`.
- Tests command: `python3 -m pytest -q`.
- Tests passed: `false`.
- Required events passed: `false`.
- Report blocker: `case engine failed with exit code 1`.
- Case stderr evidence: implementer failed with `AGENT_RESULT start delimiter not found`.
- Case stderr evidence: retry classified the failure as `agent-protocol-error`.
- Case stdout evidence: unattended mode auto-selected `Abort`.
- Result: Stage 2 is still blocked.
## Current Interpretation ## Current Interpretation
This is a protocol compatibility blocker, not a provider approval blocker. This is a protocol compatibility blocker, not a provider approval or model
admission blocker.
The admitted provider/model reached Case. Case then failed because the implementer Two admitted provider/model paths reached Case. Case then failed because the
agent did not return output framed by the Case `AGENT_RESULT` delimiter contract. implementer agent did not return output framed by the Case `AGENT_RESULT`
The evidence does not prove whether the defect is Case provider configuration, delimiter contract. The evidence does not prove whether the defect is Case
provider adapter behavior, Codex output framing, or harness invocation shape. provider configuration, provider adapter behavior, model output framing, or
harness invocation shape.
## Narrowed Interpretation - 2026-06-01 ## Narrowed Interpretation - 2026-06-01

View File

@ -4,7 +4,7 @@ status: draft
lifecycle_classification: sot lifecycle_classification: sot
owner: jp owner: jp
created: 2026-05-31 created: 2026-05-31
last_reviewed: 2026-05-31 last_reviewed: 2026-06-01
core_promotion_status: not-promoted core_promotion_status: not-promoted
route: cto route: cto
--- ---
@ -162,3 +162,19 @@ Acceptance:
- This admission does not approve real-repo, copied-repo, sandbox-repo, owned-repo, default-candidate, or Core promotion stages. - This admission does not approve real-repo, copied-repo, sandbox-repo, owned-repo, default-candidate, or Core promotion stages.
- `CTO-WORK-020` remains blocked until real Case Stage 2 produces a Harness Evidence Interface pass report using this admission file. - `CTO-WORK-020` remains blocked until real Case Stage 2 produces a Harness Evidence Interface pass report using this admission file.
- Real Case Stage 2 command must set `CTO_HARNESS_CASE_MODEL_ADMISSION_FILE` to this admission JSON path. - Real Case Stage 2 command must set `CTO_HARNESS_CASE_MODEL_ADMISSION_FILE` to this admission JSON path.
## Qwen Local Runtime Evidence - 2026-06-01
- Run artifact directory: `/home/svrnty/.hermes/profiles/cto-planb/harness-runs/20260601T015208Z-r1-string-slugify-2478256`.
- Report status: `fail`.
- Backend: `case`.
- Case process started: `true`.
- Case model provider: `qwen-local`.
- Case model: `qwen3.6-35b-a3b`.
- Case model admission status: `admitted`.
- The admitted Qwen local provider/model path reached Case execution.
- Case failed before producing a diff.
- Case stderr recorded `AGENT_RESULT start delimiter not found`.
- Case retry classified the failure as `agent-protocol-error`.
- `CTO-WORK-020` remains blocked because no real Case Stage 2 pass report exists.
- Current downstream blocker remains `CTO-WORK-028`.

View File

@ -4,7 +4,7 @@ status: draft
lifecycle_classification: sot lifecycle_classification: sot
owner: jp owner: jp
created: 2026-05-31 created: 2026-05-31
last_reviewed: 2026-05-31 last_reviewed: 2026-06-01
core_promotion_status: not-promoted core_promotion_status: not-promoted
route: cto route: cto
--- ---
@ -100,6 +100,19 @@ Validation Evidence:
- `CTO-WORK-016` remains blocked because no real Case Stage 2 pass report exists. - `CTO-WORK-016` remains blocked because no real Case Stage 2 pass report exists.
- Current downstream blocker is tracked by `CTO-WORK-028`. - Current downstream blocker is tracked by `CTO-WORK-028`.
## Qwen Local Provider Runtime Evidence - 2026-06-01
- Real Case Stage 2 run with `/tmp/workos-case/dist/ca` and admitted `qwen-local` / `qwen3.6-35b-a3b` produced report `/home/svrnty/.hermes/profiles/cto-planb/harness-runs/20260601T015208Z-r1-string-slugify-2478256/report.json`.
- Case process started after admission passed.
- Backend exit code was `1`.
- The harness recorded no changed files.
- The patch artifact was empty.
- Tests failed because the artificial fixture bug remained unchanged.
- Case stderr recorded `AGENT_RESULT start delimiter not found`.
- Case stderr classified the retry as `agent-protocol-error`.
- `CTO-WORK-016` remains blocked because no real Case Stage 2 pass report exists.
- Current downstream blocker remains `CTO-WORK-028`.
## CTO-WORK-018 - Case Model Provider Admission Gate ## CTO-WORK-018 - Case Model Provider Admission Gate
Status: validated. Status: validated.