feat(providerdb): add reasoning/search defaults #967

yyhhyyyyyy · 2025-10-10T08:59:15Z

add reasoning/search defaults

Summary by CodeRabbit

New Features
- Reasoning and Web Search now honor provider-defined default settings.
- Capability detection now reads official model fields for tool calls, reasoning, and search.
- Models expose an optional “default” flag for reasoning and search, improving default toggles.
- More consistent feature availability when selecting provider models.

coderabbitai · 2025-10-10T08:59:25Z

Note

Other AI code review bot(s) detected

CodeRabbit has detected other AI code review bot(s) in this pull request and will avoid duplicating their findings in the review comments. This may lead to a less comprehensive review.

Walkthrough

Updates provider model schemas to include optional default flags for reasoning and search, propagates those defaults from the provider DB sanitization, and adjusts presenter mappings to read display name, tool_call, and the new default-based reasoning/search flags when building model configs.

Changes

Cohort / File(s)	Summary of changes
Presenter: DB model mapping `src/main/presenter/configPresenter/index.ts`	Use `m.display_name` for model name; read `tool_call`, `reasoning?.supported`, and `search?.supported` directly from model (remove casts).
Presenter: config defaults `src/main/presenter/configPresenter/modelConfig.ts`	Derive `reasoning` and `enableSearch` from `provider.model.reasoning.default ?? false` and `provider.model.search.default ?? false` instead of `.supported`.
Schema: provider model types `src/shared/types/model-db.ts`	Add optional `default: boolean` to `ReasoningSchema` and `SearchSchema`; `getReasoning`/`getSearch` parse/emit `default`, widening `ProviderModel.reasoning` and `ProviderModel.search`.
Provider DB sanitization `scripts/fetch-provider-db.mjs`	Propagate `default` boolean for reasoning and search when sanitizing provider entries (copy `r.default` → `rs.default`, `s.default` → `so.default`).

Sequence Diagram(s)

sequenceDiagram
  autonumber
  participant UI as UI
  participant CP as ConfigPresenter
  participant S as Sanitizer (fetch-provider-db)
  participant DB as Provider DB

  UI->>CP: Request provider model config
  CP->>S: Ask for sanitized provider models
  S->>DB: Read raw provider JSON
  DB-->>S: Raw models (may include reasoning.default/search.default)
  S-->>CP: Sanitized ProviderModel { display_name, tool_call, reasoning?, search? }

  rect rgba(200,235,255,0.25)
    note right of CP: Mapping & defaults
    CP->>CP: name = model.display_name
    CP->>CP: functionCall = model.tool_call
    CP->>CP: reasoning.supported = model.reasoning?.supported
    CP->>CP: reasoning.default = model.reasoning?.default ?? false
    CP->>CP: search.supported = model.search?.supported
    CP->>CP: search.default = model.search?.default ?? false
    CP->>UI: finalConfig (reasoning/search derive from `.default`)
  end

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20–30 minutes

Possibly related PRs

refactor(provider-db): migrate model config to external DB #956 — Modifies provider DB integration and presenter mappings touching the same files and fields (display_name, reasoning/search flags).
feat(provider-db): support reasoning/search objects #964 — Adjusts reasoning/search handling and schema shapes; closely related to adding and consuming default flags.
fix: migration model config data from new default settings #923 — Updates config-presenter behavior for provider vs user model defaults; overlaps with default-flag usage.

Poem

I nibble defaults in moonlit code,
Flags tucked safe along the road.
Reasoning, search—now gently sown,
Clean names and fields all neatly known.
A rabbit cheers: hops, stamps, and grins—🐇✨

Pre-merge checks and finishing touches

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	You can run `@coderabbitai generate docstrings` to improve docstring coverage.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title Check	✅ Passed	The title concisely and accurately describes the primary change by indicating that default values for reasoning and search are being added to the provider database logic, matching the modifications across configPresenter, model config, types, and scripts.

✨ Finishing touches

📝 Generate docstrings

🧪 Generate unit tests (beta)

Create PR with unit tests
Post copyable unit tests in a comment
Commit unit tests in branch feat/providerdb-defaults

📜 Recent review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between b220973 and 44ce3ca.

📒 Files selected for processing (1)

scripts/fetch-provider-db.mjs (2 hunks)

🧰 Additional context used

📓 Path-based instructions (1)

scripts/**

📄 CodeRabbit inference engine (AGENTS.md)

Place build/signing/installer/runtime and commit-related scripts in scripts/

Files:

scripts/fetch-provider-db.mjs

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)

GitHub Check: build-check (x64)

🔇 Additional comments (2)

scripts/fetch-provider-db.mjs (2)

68-68: LGTM! Consistent with existing pattern.

The propagation of the default flag for reasoning is correctly implemented, mirroring the pattern used for the supported flag on line 67. The type check ensures only boolean values are copied.

88-88: LGTM! Consistent with existing pattern.

The propagation of the default flag for search is correctly implemented, mirroring the pattern used for the supported flag on line 87. The type check ensures only boolean values are copied.

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

yyhhyyyyyy · 2025-10-10T08:59:44Z

@codex review

chatgpt-codex-connector · 2025-10-10T08:59:48Z

To use Codex here, create a Codex account and connect to github.

zerob13 · 2025-10-10T09:00:53Z

@codex review

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting

@codex fix this CI failure
@codex address that feedback

chatgpt-codex-connector · 2025-10-10T09:03:36Z

src/main/presenter/configPresenter/modelConfig.ts

          temperature: 0.6,
          vision: isImageInputSupported(model),
          functionCall: model.tool_call ?? false,
-          reasoning: Boolean(model.reasoning?.supported),
+          reasoning: Boolean(model.reasoning?.default ?? false),
          type: ModelType.Chat,
          thinkingBudget: model.reasoning?.budget?.default ?? undefined,
-          enableSearch: Boolean(model.search?.supported),
+          enableSearch: Boolean(model.search?.default ?? false),
          forcedSearch: Boolean(model.search?.forced_search),


Restore fallback when reasoning/search default missing

ModelConfigHelper now initializes reasoning and enableSearch from model.reasoning?.default and model.search?.default. The provider database currently contains no default flags for these capabilities (e.g. rg -c '"default"' resources/model-db/providers.json only yields budget defaults), so both fields evaluate to false for every model even when supported is true. This regresses prior behavior where supported reasoning/search were enabled by default and effectively disables those features until the user toggles them manually. Consider falling back to the supported flag when default is undefined.

Useful? React with 👍 / 👎.

zerob13 · 2025-10-10T09:24:25Z

@codex review

chatgpt-codex-connector · 2025-10-10T09:28:28Z

Codex Review: Didn't find any major issues. Swish!

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting

@codex fix this CI failure
@codex address that feedback

feat(providerdb): add reasoning/search defaults

b220973

chatgpt-codex-connector bot reviewed Oct 10, 2025

View reviewed changes

fix(build): keep reasoning/search defaults

44ce3ca

zerob13 merged commit 5ab257e into dev Oct 10, 2025
2 checks passed

This was referenced Oct 11, 2025

feat(provider-db): support reasoning budget min/max #970

Merged

fix: sync tool-call defaults for provider configs #988

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat(providerdb): add reasoning/search defaults #967

feat(providerdb): add reasoning/search defaults #967

Uh oh!

yyhhyyyyyy commented Oct 10, 2025 •

edited by coderabbitai bot

Loading

Uh oh!

coderabbitai bot commented Oct 10, 2025 •

edited

Loading

Other AI code review bot(s) detected

Uh oh!

yyhhyyyyyy commented Oct 10, 2025

Uh oh!

chatgpt-codex-connector bot commented Oct 10, 2025

Uh oh!

zerob13 commented Oct 10, 2025

Uh oh!

chatgpt-codex-connector bot left a comment

Uh oh!

chatgpt-codex-connector bot Oct 10, 2025

Uh oh!

zerob13 commented Oct 10, 2025

Uh oh!

chatgpt-codex-connector bot commented Oct 10, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

feat(providerdb): add reasoning/search defaults #967

feat(providerdb): add reasoning/search defaults #967

Uh oh!

Conversation

yyhhyyyyyy commented Oct 10, 2025 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Uh oh!

coderabbitai bot commented Oct 10, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Other AI code review bot(s) detected

Walkthrough

Changes

Sequence Diagram(s)

Estimated code review effort

Possibly related PRs

Poem

Pre-merge checks and finishing touches

Uh oh!

yyhhyyyyyy commented Oct 10, 2025

Uh oh!

chatgpt-codex-connector bot commented Oct 10, 2025

Uh oh!

zerob13 commented Oct 10, 2025

Uh oh!

chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

chatgpt-codex-connector bot Oct 10, 2025

Choose a reason for hiding this comment

Uh oh!

zerob13 commented Oct 10, 2025

Uh oh!

chatgpt-codex-connector bot commented Oct 10, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

yyhhyyyyyy commented Oct 10, 2025 •

edited by coderabbitai bot

Loading

coderabbitai bot commented Oct 10, 2025 •

edited

Loading