diff options
| author | Adam Malczewski <[email protected]> | 2026-06-05 17:38:57 +0900 |
|---|---|---|
| committer | Adam Malczewski <[email protected]> | 2026-06-05 17:38:57 +0900 |
| commit | 74986a54093f6492cc4420f5917e5215f42a8f89 (patch) | |
| tree | 6a3aa746b722f4071864d1812000d449801ed885 /packages/kernel/src/runtime | |
| parent | 5ae88d4e98b3b585526ab0534be8e4c12f1ac071 (diff) | |
| download | dispatch-74986a54093f6492cc4420f5917e5215f42a8f89.tar.gz dispatch-74986a54093f6492cc4420f5917e5215f42a8f89.zip | |
feat(observability): replace synthetic text-turn fixture with a real sanitized flash capture (D5)
Installed a real DISPATCH_RECORD_FIXTURE capture (200 text/event-stream, deepseek-v4-flash, finish_reason stop, reply 'Hello there friend') as src/__fixtures__/flash-text-turn.json, replacing the hand-authored one. Auth header masked (Bearer sk-…redacted…UN0); fixture re-verified secret-free before commit. Text-turn replay assertions updated to real values (inputTokens 665 / outputTokens 90); structural assertions kept (multi-chunk replay, getCapturedRequest deep-equals the outgoing request, finish/stop event, concatenated deltas). The provider's request-building + SSE parsing now run against genuine flash bytes.
Real-data finding (logged in tasks.md): flash reports cache tokens via DeepSeek's NESTED prompt_tokens_details.cached_tokens (384 cached of 665 prompt); the parser only maps the FLAT cache_read/creation form, so cache tokens don't surface — an observability gap vs the §3.1 cache-debugging goal. Deferred pending decision. 334 tests, typecheck + biome 0/0.
Diffstat (limited to 'packages/kernel/src/runtime')
0 files changed, 0 insertions, 0 deletions
