Repository navigation
[pull] main from theopenco:main - #1
Merged
Merged
Conversation
## Summary Fixed prompt caching token reporting for AWS Bedrock streaming responses. The streaming metadata event handler was only passing `inputTokens` to `prompt_tokens`, ignoring `cacheReadInputTokens` and `cacheWriteInputTokens`. This caused cached token counts to always be zero for streaming requests (which Claude Code uses). ## Changes - Extract and sum all token types (`inputTokens`, `cacheReadInputTokens`, `cacheWriteInputTokens`) for `prompt_tokens` calculation - Include `prompt_tokens_details.cached_tokens` in streaming usage when cache hits are present ## Impact Cached tokens now properly report in streaming mode, allowing accurate billing discounts and cache hit visibility for Claude Code users on AWS Bedrock. 🤖 Generated with [Claude Code](https://claude.com/claude-code) <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit ## Release Notes * **Bug Fixes** * Improved token usage calculation for AWS Bedrock integration to accurately account for all token types, including cached tokens. * Enhanced token consumption visibility with detailed reporting of cached token usage. <!-- end of auto-generated comment: release notes by coderabbit.ai --> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
## Summary - Add OpenAI GPT-5.4 Mini ($0.75/$4.50 per 1M tokens) — strong mini model for coding, computer use, and subagents - Add OpenAI GPT-5.4 Nano ($0.20/$1.25 per 1M tokens) — cheapest GPT-5.4-class model for high-volume tasks Both models support 400K context, 128K max output, reasoning, vision, tools, web search, and structured outputs. ## Test plan - [x] E2E tests pass with `TEST_MODELS="openai/gpt-5.4-mini,openai/gpt-5.4-nano"` (80 passed) - [x] Prompt caching verified with cached tokens confirmed - [x] Build succeeds 🤖 Generated with [Claude Code](https://claude.com/claude-code) <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Added support for two new OpenAI models, gpt-5.4-mini and gpt-5.4-nano. Both models are available with published pricing, context size and max output limits, and enable advanced capabilities including streaming, vision, tools, web search, reasoning, and structured JSON output. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: romel lauron <romellauron@romels-MacBook-Pro.local> Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> Co-authored-by: Ismail Ghallou <ismai23l@hotmail.com>
) ## Summary - Removed the enterprise plan check from `logAuditEvent` so audit events are persisted for **all** organizations, regardless of plan - The enterprise gate remains on the `GET /audit-logs/:orgId` and `GET /audit-logs/:orgId/filters` API endpoints — non-enterprise orgs still get a 403 when trying to view logs - This means orgs that upgrade to enterprise later will already have their full audit history available immediately ## Test plan - [ ] Verify audit events are logged for non-enterprise orgs (insert into `audit_log` table) - [ ] Verify `GET /audit-logs/:orgId` still returns 403 for non-enterprise orgs - [ ] Verify `GET /audit-logs/:orgId/filters` still returns 403 for non-enterprise orgs - [ ] Verify enterprise orgs can still view audit logs as before 🤖 Generated with [Claude Code](https://claude.com/claude-code) <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Refactor** * Improved audit event logging to ensure all events are consistently captured and recorded. Simplified the logging function by removing plan-based filtering and relocating validation checks to the API layer, providing cleaner separation of concerns and ensuring comprehensive audit trail coverage for all scenarios. <!-- end of auto-generated comment: release notes by coderabbit.ai --> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
## Summary - Adds a green "All systems operational" status dot linking to https://status.llmgateway.io/ across UI, Playground, and Docs apps - **UI**: Added in the footer bottom bar alongside Privacy Policy and Terms of Use links - **Playground**: Added in the sidebar footer (chat, image, and skeleton sidebars) - **Docs**: Added via Fumadocs sidebar footer ## Test plan - [ ] Verify the green dot + "All systems operational" text renders in the UI footer - [ ] Verify it renders in the Playground sidebar footer - [ ] Verify it renders in the Docs sidebar footer - [ ] Confirm clicking the link opens https://status.llmgateway.io/ in a new tab 🤖 Generated with [Claude Code](https://claude.com/claude-code) <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Added a visual status indicator displaying "All systems operational" with an animated green indicator across multiple areas of the application. Users can now access the system status page directly from the interface to monitor real-time service health information. <!-- end of auto-generated comment: release notes by coderabbit.ai --> Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Introduced indexes to optimize queries related to model history and project hourly statistics.
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 subscribe to this conversation on GitHub.
Already have an account?
Sign in.
3 participants
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.
See Commits and Changes for more details.
Created by
pull[bot] (v2.0.0-alpha.4)
Can you help keep this open source service alive? 💖 Please sponsor : )