realtime: correct model-aware wire mappings - #11
Conversation
|
@codex review |
There was a problem hiding this comment.
❌ OpenAI PR Review: FAIL
Conclusion: Not ready. 1 readiness blocker and 1 actionable finding must be resolved before merge.
Review checks
| Check | Result |
|---|---|
| PR format | ✅ PASS |
| Issue design | ✅ PASS |
| Code & plan conformance | ❌ FAIL |
Scope: 86cabc5c1b · fe8153366f..86cabc5c1b · full · 1 diff chunk
Usage: 1m 25s · 681,782 tokens · 83.2% cache hit · 13.346 credits
Blockers
code-reviewrealtime.go:855: Do not use the session ID as a request ID
Findings
1 inline finding published.
Summary
One actionable correctness finding remains in the complete PR.
Review metadata
- Commit:
86cabc5c1b - Range:
fe8153366f..86cabc5c1b - Mode:
full - Diff chunks:
1 - Model:
gpt-5.6-terra - Reasoning effort:
medium - Session:
repo-1169785363-pr-11-v2 - Generation:
0cbe93423e9e9abb1a66b7df4e339ade1bcca4317298a297dcbd9c1e1fc904a2 - Evidence:
0a69cddc6697cc4a92fa56edf1370db799783156377f443b2b78bb724df8e593
Totals
- Input:
674,442 - Cached input:
561,043 - Cache write:
113,348 - Output:
7,340 - Reasoning:
4,826 - Total:
681,782 - Estimated credits:
13.346 - Credit rate per 1M tokens:
62.5input /6.25cached /375output
Token and cache details
| Stage | Mode | Target | Time | Input | Cached | Hit | Output | Total | Credits |
|---|---|---|---|---|---|---|---|---|---|
pr |
deterministic |
format rules |
0s | 0 | 0 | 0.0% | 0 | 0 | 0.000 |
pr |
full |
pr |
5s | 21,832 | 10,567 | 48.4% | 298 | 22,130 | 0.882 |
issue |
full |
Issue #10 |
18s | 134,059 | 107,984 | 80.5% | 1,578 | 135,637 | 2.896 |
code |
full |
chunk 1/1 |
54s | 371,571 | 304,516 | 82.0% | 4,750 | 376,321 | 7.875 |
code |
full |
aggregate |
8s | 146,980 | 137,976 | 93.9% | 714 | 147,694 | 1.693 |
|
@codex review |
There was a problem hiding this comment.
✅ OpenAI PR Review: PASS
Conclusion: Ready from the OpenAI review perspective. PR format, linked Issue design, and code/plan conformance passed with no actionable findings.
Review checks
| Check | Result |
|---|---|
| PR format | ✅ PASS |
| Issue design | ✅ PASS |
| Code & plan conformance | ✅ PASS |
Scope: 1fd44b8226 · 86cabc5c1b..1fd44b8226 · incremental · 1 diff chunk
Usage: 16s · 398,867 tokens · 79.5% cache hit · 7.350 credits
Summary
No actionable findings remain after the incremental fix.
Review metadata
- Commit:
1fd44b8226 - Range:
86cabc5c1b..1fd44b8226 - Mode:
incremental - Diff chunks:
1 - Model:
gpt-5.6-terra - Reasoning effort:
medium - Session:
repo-1169785363-pr-11-v2 - Generation:
706ad8b864e41a6ca943976cc75f25c1281dcbc1679658feb17d6709be04d398 - Evidence:
cf7dc64c4e43ba54349e9ddc58d58027569d339e4d131abed70172ffdb3bde4c
Totals
- Input:
398,119 - Cached input:
316,675 - Cache write:
81,429 - Output:
748 - Reasoning:
94 - Total:
398,867 - Estimated credits:
7.350 - Credit rate per 1M tokens:
62.5input /6.25cached /375output
Token and cache details
| Stage | Mode | Target | Time | Input | Cached | Hit | Output | Total | Credits |
|---|---|---|---|---|---|---|---|---|---|
pr |
deterministic |
format rules |
0s | 0 | 0 | 0.0% | 0 | 0 | 0.000 |
pr |
reused |
cached evidence |
0s | 0 | 0 | 0.0% | 0 | 0 | 0.000 |
issue |
reused |
Issue #10 |
0s | 0 | 0 | 0.0% | 0 | 0 | 0.000 |
code |
incremental |
chunk 1/1 |
8s | 236,158 | 155,972 | 66.0% | 524 | 236,682 | 6.183 |
code |
incremental |
aggregate |
8s | 161,961 | 160,703 | 99.2% | 224 | 162,185 | 1.167 |
There was a problem hiding this comment.
✅ OpenAI PR Review: PASS
Conclusion: Ready from the OpenAI review perspective. PR format, linked Issue design, and code/plan conformance passed with no actionable findings.
Review checks
| Check | Result |
|---|---|
| PR format | ✅ PASS |
| Issue design | ✅ PASS |
| Code & plan conformance | ✅ PASS |
Scope: 0d0b88fa14 · 1fd44b8226..0d0b88fa14 · incremental · 1 diff chunk
Usage: 29s · 824,008 tokens · 77.3% cache hit · 16.479 credits
Summary
No actionable findings remain.
Review metadata
- Commit:
0d0b88fa14 - Range:
1fd44b8226..0d0b88fa14 - Mode:
incremental - Diff chunks:
1 - Model:
gpt-5.6-terra - Reasoning effort:
medium - Session:
repo-1169785363-pr-11-v2 - Generation:
390458f0955d08f763fdb7cf6532f36806782754a3a709a68d84b87c36739ed4 - Evidence:
bd93c7914012e3581c383282da1964c8b32cb1bc48f0f17acc12fffa90a59913
Totals
- Input:
821,750 - Cached input:
635,151 - Cache write:
186,572 - Output:
2,258 - Reasoning:
1,023 - Total:
824,008 - Estimated credits:
16.479 - Credit rate per 1M tokens:
62.5input /6.25cached /375output
Token and cache details
| Stage | Mode | Target | Time | Input | Cached | Hit | Output | Total | Credits |
|---|---|---|---|---|---|---|---|---|---|
pr |
deterministic |
format rules |
0s | 0 | 0 | 0.0% | 0 | 0 | 0.000 |
pr |
reused |
cached evidence |
0s | 0 | 0 | 0.0% | 0 | 0 | 0.000 |
issue |
incremental |
Issue #10 |
10s | 253,117 | 166,714 | 65.9% | 748 | 253,865 | 6.723 |
code |
incremental |
chunk 1/1 |
15s | 369,943 | 272,426 | 73.6% | 1,297 | 371,240 | 8.284 |
code |
incremental |
aggregate |
4s | 198,690 | 196,011 | 98.7% | 213 | 198,903 | 1.472 |
Closes #10
Summary
RealtimeConfig.Instructionsmapping and reject incompatible model/capability fieldsValidation
go test ./... -count=1go test ./... -race -count=1go build ./...go vet ./...git diff --checkInstructionsresponse assertion)Instructionsresponse assertion)GitHub Actions currently has no Doubao credential secret; live smoke was run locally without printing credentials.