- observe response model from terminal sourceEvent in Meta non-stream multi-event SSE responses
- record expected upstream model in UsageReporter to prevent false substitution warnings on Kimi canonical mappings
- use bounded stream observer to extract response models across image stream chunk boundaries
- add regression tests for Meta SSE non-stream, Kimi model mappings, and chunked image streams
- Introduced `MetaExecutor` to support native Meta (Muse Code) API operations, including `Execute`, `ExecuteStream`, and `CountTokens`.
- Added logic to handle Meta-specific `responses` endpoint, including request preparation, enriched authentication, header management, and response translation.
- Implemented token counting functionality with custom `CountTokens` logic.
- Updated `meta_executor` to process streamed and non-streamed responses, maintaining compatibility with the Codex schema.
- Added utility functions to handle events, errors, and enriched metadata common to Meta API requests.
- Extended `models.json` to include Meta's updated configuration with additional thinking levels like "minimal" and "max."
- Introduced comprehensive tests to validate Meta-specific execution, streaming, header assignments, and response formatting.
- Make optional config loading fail on malformed YAML or validation errors
- Separate DCA token expiry from minted API key expiry in Meta token storage
- Remove global runtime fallbacks from MetaExecutor to prevent cross-account bleed
- Deduplicate inflight DCA minting using singleflight.Group and persist refreshed keys
- Resolve Meta API key in management APICall tool and support DCA minting
- Align models.json with supported chat endpoints and valid thinking levels
- Expand unit tests covering DCA refresh, singleflight, multi-account isolation, and APICall
- Include Meta API key count in client load metrics and diff reporting
