Current issue state, recent activity, and per-issue timelines from the indexed issue data.
| Date | Opened | Closed | Comments | Events | Open Backlog |
|---|---|---|---|---|---|
| 2026-07-30 | 0 | 0 | 0 | 0 | 0 |
| 2026-07-29 | 19 | 8 | 43 | 115 | 55 |
| 2026-07-28 | 31 | 13 | 32 | 112 | 62 |
| 2026-07-27 | 22 | 9 | 28 | 71 | 42 |
| 2026-07-26 | 21 | 14 | 15 | 74 | 40 |
| 2026-07-25 | 13 | 19 | 35 | 84 | 69 |
| 2026-07-24 | 20 | 5 | 57 | 127 | 77 |
| 2026-07-23 | 28 | 46 | 125 | 232 | 95 |
| 2026-07-22 | 35 | 3 | 0 | 0 | 0 |
| 2026-07-21 | 16 | 16 | 37 | 97 | 62 |
| 2026-07-20 | 18 | 11 | 11 | 33 | 24 |
| 2026-07-19 | 12 | 11 | 17 | 45 | 22 |
| 2026-07-18 | 6 | 16 | 13 | 40 | 71 |
| 2026-07-17 | 25 | 16 | 0 | 0 | 0 |
Opened: 126
Closed: 68
Comments: 210
Events: 583
| Issue | Author | State | Labels | Comments | Reactions | Updated |
|---|---|---|---|---|---|---|
#35095 UI: show the model family logo in the models table, not just the provider's Opened 17 hours ago | ian75013 | open | llm translation | 0 | 0 | 17 hours ago |
#24640 [Bug]: response_format Ignored When Calling the Image Generation Endpoint Opened 4 months ago | dotmobo | closed - completed | bug proxy llm translation | 4 | 0 | 17 hours ago |
#35093 [Bug]: Inconsistency between panels in UI dashboard Opened 17 hours ago | bedroesb | open | bug ui-dashboard | 0 | 0 | 17 hours ago |
#16011 [Bug]: Max Parallel Requests do not limit parallel connection consistently Opened 9 months ago | subnet-dev | closed - completed | bug mlops user request llm translation | 11 | 2 | 17 hours ago |
#16021 [Bug]: OpenRouter cost information lost in streaming responses Opened 9 months ago | bbarwik | open | bug llm translation | 17 | 4 | 17 hours ago |
#35089 anthropic-request-id dropped on streaming /v1/messages (anthropic_messages call_type) Opened 18 hours ago | abrekhov | closed - completed | llm translation | 0 | 0 | 17 hours ago |
#33167 [Bug]: v1.92.0 downloads Prisma Binaries at startup Opened 16 days ago | TobiasGoerke | open | bug proxy | 4 | 7 | 19 hours ago |
#35084 [Bug]: Incomplete documentation on pure litellm_config.yaml based setup for proxy server Opened 20 hours ago | PrathamGBhat | open | bug docs | 0 | 0 | 20 hours ago |
#35081 Withdrawn — filed in error Opened 21 hours ago | yatias | closed - not_planned | No labels | 0 | 0 | 20 hours ago |
#35064 [Bug]: Cann't find in UI the enable background_health_checks option Opened 23 hours ago | delphiRo | open | bug | 2 | 0 | 21 hours ago |
#34105 [Bug]: Bedrock Converse silently drops `reasoning_effort` for non-Anthropic/Nova2/GPT-OSS models (e.g. Qwen3 on Bedrock) Opened 9 days ago | nikotan | open | bug proxy llm translation | 3 | 0 | 21 hours ago |
#31837 [Bug]: OpenAI Responses served service_tier=default is billed as priority when requested priority Opened 29 days ago | silencedoctor | open | llm translation SDK | 1 | 0 | 21 hours ago |
#35076 [Bug]: skip_user_budget_on_team_key: true does not work Opened 21 hours ago | lpo-pb1234 | open | bug proxy | 0 | 0 | 21 hours ago |
#35072 [Feature]: Support deployment-level cost discounts Opened 22 hours ago | silencedoctor | open | llm translation SDK | 1 | 0 | 22 hours ago |
#35071 [Bug]: Router Responses and Anthropic Messages ignore per-deployment retries and cooldown Opened 22 hours ago | silencedoctor | open | llm translation | 1 | 0 | 22 hours ago |
#35068 [Bug]: Failed proxy requests can lose call_type and router metadata in spend logs Opened 22 hours ago | silencedoctor | open | proxy | 1 | 0 | 22 hours ago |
#35066 [Bug]: SAP GenAI Hub Orchestration: `type: "file"` content parts rejected client-side, blocking native PDF input for Anthropic/Gemini Opened 23 hours ago | NicolaiMinter | open | bug llm translation SDK | 0 | 0 | 23 hours ago |
#26774 [Bug]: Unable to update budget on a virtual-key Opened 3 months ago | JovanVeljanoski | open | bug stale ui-dashboard | 2 | 0 | 23 hours ago |
#31694 [Bug]: Complexity Router disappears from `/v2/model/info` after updating DB model Opened 1 month ago | finxeng | open | bug proxy | 2 | 0 | 23 hours ago |
#35061 [Bug]: Anthropic /v1/messages with max_tokens=1 fails for GPT-5.x models, breaking Claude Code /model Opened 1 day ago | Alpha-Zark | open | bug proxy llm translation | 0 | 0 | 1 day ago |
#21115 request to update cloudflare workers ai provider implementation to reflect cloudflare’s expanded ai api Opened 6 months ago | prdai | open | No labels | 7 | 2 | 1 day ago |
#35056 feat(cloudflare): add Workers AI audio support Opened 1 day ago | prdai | open | potential-duplicate | 2 | 0 | 1 day ago |
#35055 feat(cloudflare): add Workers AI image support Opened 1 day ago | prdai | open | potential-duplicate | 2 | 0 | 1 day ago |
#35053 [Bug]: /v1/messages skips supports_sampling_params gating — temperature/top_p/top_k 400 on claude-sonnet-5/opus-4-7/4-8/opus-5 while /chat/completions 200s; fallbacks silently downgrade the model Opened 1 day ago | mihidumh | open | llm translation | 0 | 0 | 1 day ago |
#29518 [Bug]: /v1/messages adapter drops reasoning_content → thinking blocks for OpenAI-compatible chat-completions backends (streaming) Opened 2 months ago | sytianhe | closed - completed | proxy llm translation claude code | 3 | 1 | 1 day ago |
