Skip to content

docs(create-agent-tui): sync with openrouter-web changes - #162

Open
devin-ai-integration[bot] wants to merge 1 commit into
mainfrom
devin/1786208665-update-create-agent-tui
Open

docs(create-agent-tui): sync with openrouter-web changes#162
devin-ai-integration[bot] wants to merge 1 commit into
mainfrom
devin/1786208665-update-create-agent-tui

Conversation

@devin-ai-integration

Copy link
Copy Markdown
Contributor

Summary

Source: openrouter-web #32317feat(web-search): support selectable Exa and Parallel modes.

That PR adds a public mode field to web-search configuration (web plugin prefs, chat-completions web-search config, Responses web-search tool, and the openrouter:web_search server tool), backed by a new WebSearchMode schema in projects/docs/openapi/openapi.yaml. Valid values are engine-specific:

  • Exa: instant, fast, auto (default), deep-lite, deep, deep-reasoning
  • Parallel: turbo (default), basic, advanced

A mode the selected engine doesn't support is ignored and the engine default applies, so the engine should be set explicitly alongside the mode.

The skill's server-tool checklist enumerates the configurable knobs of openrouter:web_search and listed only engine, max_results, domain filtering; this adds mode plus a one-paragraph note on values, defaults, and the engine-selection caveat.

Other candidates from the same 24h window were reviewed and need no change: the Seedance reference-input commit (#31977) only widens an OpenAPI description and changes runtime capability detection — openrouter-video never claimed the narrower Seedance-2.0-only rule; the fusion default changes (#32429, #32853) touch documented defaults for a surface no skill teaches. create-headless-agent lists the tool but teaches no configuration, so it is unaffected.

Link to Devin session: https://openrouter.devinenterprise.com/sessions/33d74573e39445308cc84b8158d6e273

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

@perry-the-pr-maintainer perry-the-pr-maintainer Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Perry's Review

Verdict: ✅ LGTM
Risk: 🟢 Low

Review details

Summary

Docs-only change syncing skills/create-agent-tui/SKILL.md with openrouter-web #32317, which adds a public mode field to web-search configuration. The PR adds mode to the Web Search server-tool config table and a one-paragraph note covering the engine-specific valid values, defaults, and the engine-selection caveat.

Diff analysis

  • Config table (engine, mode, max_results, domain filtering): correctly inserts mode between engine and max_results, matching the logical order (engine selection → mode/depth → result count → domain filter).
  • Mode paragraph: accurately documents the engine-native search depth values — Exa (instant, fast, auto (default), deep-lite, deep, deep-reasoning) and Parallel (turbo (default), basic, advanced). The caveat ("Set engine explicitly whenever setting mode — a mode the selected engine does not support is ignored and the engine's default applies") is clear and actionable. The cost note ("Deeper modes cost more per request") is a useful callout.

Blast radius

  • The change affects only the Web Search server-tool row and its accompanying paragraph. No code is changed — this is purely documentation for a scaffolding skill.
  • The related create-headless-agent skill lists the tool without a Config column, so it correctly needs no sync (as noted in the PR body).

CI

No CI checks configured for this PR.

Risk assessment

Risk: 🟢 Low

Dimension Severity Risk Reasoning
Implementation risk 🟩 Low Docs-only change; no code, no logic, no runtime behavior.
Premise risk 🟩 Low The source PR (#32317) is explicitly cited and the mode values match its description.
Estimated impact 🟩 Low Worst case: a scaffolded agent generates slightly inaccurate web-search config guidance; no runtime, data, or security impact.
Risk Factor Severity Risk Reasoning
Reversibility 🟩 Low A docs change is trivially reverted.
Detectability 🟩 Low Any inaccuracy surfaces immediately when a user configures mode on a scaffolded agent.
Blast radius 🟩 Low A single skill file; only affects agents scaffolded with this skill.
Data integrity None No persisted state is touched.
Financial exposure 🟩 Low The "deeper modes cost more" note is a general statement with no specific billing claim.
Security and privacy exposure None Nothing sensitive is reachable from this change.
Propagation None No downstream code reads this skill file.
Availability None The change cannot affect whether anything serves.
Recovery cost None A rollback completes the recovery.
Time to correct None A problem is corrected as soon as it is noticed.

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