Cacheable is now a strict subset of deliverable: salvaged streams,
content-less results and length/filter/unknown finishes are delivered
but never written, and the read path applies the same verdict to the
stored values before hit overrides (invalid stream_end or non-string
finish read as a miss; 1.3.9 fidelity entries fall back to the
completion's finish). Hits reset stream_end. The legacy
_has_completion_output helper is folded into _is_cacheable.
Red: 13 tests in tests/unit/test_cache.py failed before this change
(uncacheable results were written and replayed; new fields not reset).
Add faithful single-choice chat results, tool stream activity, error-frame retries, and isolated protocol caching.
Reject empty cached completions with the same value predicate as transport, add regression coverage, and adopt Apache-2.0.
Classify empty completions as transient per human ruling (fixes flaky
real-gateway smoke and prevents caching empty responses), rename the
factory injection parameter gate to breaker per the frozen design,
rewrite the probe-entry cleanup without except BaseException, declare
python-dotenv explicitly, add a mid-backoff cancellation test, and
record all implementation errata in the design and architecture docs.
iomgaa