Repository navigation
feat(ai): allowlist prompt_cache_key sending per provider - #49121
Merged
Merged
Conversation
rekram1-node
enabled auto-merge (squash)
September 15, 2026 06:23
rekram1-node
disabled auto-merge
September 15, 2026 06:23
marwanvx
added a commit
to marwanvx/opencode
that referenced
this pull request
Sep 18, 2026
Drop the provider/URL detection fallback in favor of upstream's explicit per-provider mechanism (anomalyco#49121): the flag on the model compatibility is the single gate, default off. Native OpenAI, Azure, Cerebras, DeepInfra, Fireworks, Meta, Moonshot, and OpenRouter declare it; everything else omits the body key. Detection-based tests for OpenAI fixture, DeepSeek, and Zai are removed accordingly.
jinhuang712
pushed a commit
to jinhuang712/opencode
that referenced
this pull request
Sep 26, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Chat Completions omits prompt_cache_key unless compatibility.supportsPromptCacheKey is set (default off). Strict providers 400 on unknown body fields; header affinity (x-session-affinity, x-grok-conv-id) is unaffected.
Verified: ai typecheck + full suite (1385 pass), core typecheck + model-resolver tests, schema typecheck, oxlint clean.