Kevin Codex c13842e91c fix(test): autoCompact floor assertion is flag-sensitive (#816) ...

The test "never returns negative even for unknown 3P models (issue #635)"
asserted that getEffectiveContextWindowSize() returns >= 33_000 for an
unknown 3P model under the OpenAI shim. That specific number assumes
reservedTokensForSummary = 20_000 (MAX_OUTPUT_TOKENS_FOR_SUMMARY), which
holds only when the tengu_otk_slot_v1 GrowthBook flag is disabled.

When the flag is ON — which is the case in CI but not always locally —
getMaxOutputTokensForModel() caps the model's default output at
CAPPED_DEFAULT_MAX_TOKENS (8_000). Then reservedTokensForSummary = 8_000,
floor = 8_000 + 13_000 = 21_000, and the test fails with 21_000 < 33_000.

The test reliably passes locally and reliably fails in CI, manifesting as
the intermittent PR-check failure.

Fix: relax the lower bound to 21_000 (cap-enabled worst case), which is
still well above zero — preserving the anti-regression intent of
issue #635 (no infinite auto-compact from a negative effective window)
without binding the test to GrowthBook flag state.

Co-authored-by: OpenClaude <openclaude@gitlawb.com>

2026-04-22 09:37:57 +08:00

2.2 KiB

Raw Blame History

View Raw