Skip to content

docs(openrouter-models): sync with openrouter-web changes - #181

Open
devin-ai-integration[bot] wants to merge 2 commits into
mainfrom
devin/1788282306-update-openrouter-models
Open

devin-ai-integration[bot] wants to merge 2 commits into
mainfrom
devin/1788282306-update-openrouter-models

Conversation

@devin-ai-integration

Copy link
Copy Markdown
Contributor

Summary

The endpoints API now returns perf_last_30m_by_workload alongside the flat latency_last_30m / throughput_last_30m pair (openrouter-web #38818 defines the contract, #38821 exposes it on GET /api/v1/models/{author}/{slug}/endpoints, gated on the same auth as the existing perf fields). The skill only documented the flat fields, and for image and video endpoints those are the wrong metric — raw latency there measures request acknowledgement, while the workload entry reports end-to-end generation time.

Documents the field (keys: text_generation, image_generation, video_generation, embeddings, rerank, tts, stt, unknown; each { latency, throughput, request_count }, throughput null outside text generation, only served workloads present) and threads it through get-endpoints.ts so the script's output matches what the skill describes:

   supported_parameters: ep.supported_parameters,
+  perf_30m_by_workload: ep.perf_last_30m_by_workload ?? null,

Searched existing PRs; the three open openrouter-models PRs (#174, #178, #179) touch max_completion_tokens, throughput wording, and supports_tool_choice — no overlap.

Declined from the same window: output_modalities doc list correction (#38380, docs-only; skills already use speech/transcription/video), virtual tier-endpoint removal (#37137, no public shape change and no skill documents tiers on endpoints), video pre-submission rate limits (#38016, the video skill teaches no rate-limit or error-code surface), URL-safe base64 input references (#38465, tolerance-only), and error-ownership classification (#39069, internal instrumentation).

Link to Devin session: https://openrouter.devinenterprise.com/sessions/5186ff5d167d4b0bbaa0e09165ae77a4
Open in Devin Desktop: https://openrouter.devinenterprise.com/desktop/session/5186ff5d167d4b0bbaa0e09165ae77a4?variant=devin

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
@devin-ai-integration

Copy link
Copy Markdown
Contributor Author
Original prompt from Automation

You are the public skills sync pipeline. Your job is to scan PRs merged to main on OpenRouterTeam/openrouter-web in the last 24 hours, determine if any changes warrant updating the public agent skills in OpenRouterTeam/skills, and open PRs to the skills repo when updates are needed.

#``# Step 1: Identify relevant merged PRs

Clone both repos:

cd /home/ubuntu/repos/openrouter-web
git fetch origin main
git log --since='24 hours ago' --merges --first-parent origin/main --pretty=format:'%H|%s' --name-only

For each merged PR, collect the list of changed files. Only PRs that touch the paths in the mapping below are relevant. Skip bot commits (devin-ai-integration[bot], Devin AI, GitHub Actions Bot, openrouter[bot], opencode-agent[bot], OpenRouter SDK Bot, Claude, detail-app[bot], forge-the-devex-intern[bot], dependabot[bot]).

If no relevant PRs were merged, post a short message to the #devrel Slack channel (C08LQFVSC7Q) saying no skill-relevant changes were detected today, and exit.

#``# Step 2: Map changed files to affected skills

Use this mapping to determine which public skills are potentially affected:

openrouter-web paths Affected skill(s) in OpenRouterTeam/skills
sdks/typescript/, packages/llm-interfaces/ openrouter-typescript-sdk, openrouter-agent-migration
services/cfw-*/src/routes/*analytics*, analytics query/response schemas openrouter-analytics, openrouter-analytics-query, openrouter-analytics-schema
Generation routes, /api/v1/generation openrouter-generations
Image generation adapters, packages/image-generation/ openrouter-images
supabase/seeds/, model schemas, /api/v1/models route openrouter-models
OAuth/auth routes, PKCE flow code openrouter-oauth
STT adapters, services/cfw-stt-api/, /api/v1/audio/transcriptions openrouter-stt
TTS routes, /api/v1/audio/speech openrouter-tts
Video adapters, /api/v1/videos openrouter-video
``@`openr... (3383 chars truncated...)

@devin-ai-integration

Copy link
Copy Markdown
Contributor Author

🤖 Devin AI Engineer

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

  • Address comments on this PR that start with 'DevinAI' or '@devin'.
  • Look at CI failures and help fix them

Note: I can only respond to comments from users who have write access to this repository.

⚙️ Control Options:

  • Disable automatic comment, CI, and merge conflict monitoring

…orkload

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
@devin-ai-integration

Copy link
Copy Markdown
Contributor Author

Added the decisions workload key to the perf_last_30m_by_workload key list in 34a3c8a.

Source: openrouter-web#44843 adds decisions to PublicEndpointWorkloadPerformanceByWorkloadSchema and the public OpenAPI spec.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

0 participants