Skip to content

feat: openai-compatible-strict-reasoning (1/2) - #1124

Open
myk1yt wants to merge 9 commits into
Zoo-Code-Org:mainfrom
myk1yt:pr/b05a-strict-reasoning-v2
Open

feat: openai-compatible-strict-reasoning (1/2)#1124
myk1yt wants to merge 9 commits into
Zoo-Code-Org:mainfrom
myk1yt:pr/b05a-strict-reasoning-v2

Conversation

@myk1yt

@myk1yt myk1yt commented Aug 4, 2026 •
edited
Loading

Copy link
Copy Markdown

Stack Position

  • Feature Branch: feat/openai-compatible-strict-reasoning (1/2) + fix/mimo-parallel-tool-call-policy (shared 1/2 root)
  • Stage: 1/2
  • Depends on: None

Description

image

Full Feature Description

  • Feature Branch: feat/openai-compatible-strict-reasoning
  • Feature Name: OpenAI-Compatible Strict Reasoning and Provider Cost
  • Purpose: Resolves the problem where, despite differing levels of strict JSON schema and reasoning effort support across OpenAI-compatible endpoints, request control is scattered per provider, and cost is calculated as zero or inaccurately due to usage field differences. Enables users to explicitly opt in to strict tool schema and extended reasoning effort on supported endpoints, and normalizes response usage according to provider contracts to consistently display actual cost.
  • Full Change Description: B05a adds provider settings contracts, cached settings UI, strict schema opt-in, reasoning effort values, and base request shaping. B17 normalizes conditional fields, cached tokens, missing/zero values, and price lookup for OpenAI, OpenAI-compatible, Anthropic Vertex, and Qwen family usage. B05a is also shared as the foundation for the MiMo chain, but in this chain B17 is a sibling outcome that does not depend on B12.
  • Impact Scope: Affects provider-settings.ts, base-openai-compatible-provider.ts, base-provider.ts, OpenAICompatible.tsx, openai.ts, openai-compatible.ts, anthropic-vertex.ts, qwen-code.ts.
  • Errors and Edge Cases: Strict mode is opt-in and does not change existing schemas when disabled. Strict/reasoning fields are not sent to unsupported providers. MCP schemas are not aggressively hardened. The settings UI only modifies cachedState before saving. Cost calculation treats missing fields as unknown or zero per provider contract and does not produce negative tokens. Cached input/output tokens and provider-specific price units are not double-counted. B17 does not change request payload or tool-call policy.
  • Testing Method: Run B05a's settings serialization, schema conversion, opt-in/omitted-field, request fixture, and UI/locale tests, and B17's provider-specific usage/cost fixtures. Manually compare requests with strict toggle off vs. on, and feed fixed usage fixtures into OpenAI-compatible and non-OpenAI providers, comparing against documented calculation formulas and costs.

Why Split Into 17 PRs

Instead of submitting this feature as a single unified PR, it was split into individual PRs because as code size grows, safely reviewing a PR becomes very difficult. The feature was broken into mutually exclusive individual PRs so that each can be reviewed independently.

What This PR Specifically Changes

Adds provider-neutral strict schema opt-in, reasoning effort setting, cached settings UI, and OpenAI-compatible base request shaping. Does not include MiMo-specific enforcement or provider cost calculation.

Included Files

  • packages/types/src/provider-settings.ts
  • src/api/providers/base-openai-compatible-provider.ts
  • src/api/providers/base-provider.ts
  • src/api/providers/openai.ts
  • webview-ui/src/components/settings/providers/OpenAICompatible.tsx
  • Related locale and direct tests

Exclusion Scope

  • MiMo-specific capability/stream enforcement
  • Tool-call retention policy
  • Provider cost normalization changes
  • All items in the common removal rules

Zoo (VP) added 7 commits August 2, 2026 10:02
Zoo (VP)
feat: add strict tool schema toggle and expand reasoning effort for O…
7865047 
…penAI Compatible provider

- Add openAiToolStrictMode boolean to provider settings (profile-scoped, default false)
- Add strict toggle checkbox in OpenAICompatible settings UI
- BaseProvider.convertToolsForOpenAI now accepts strictMode parameter
  - strictMode=true: strict:true + hardened schema
  - strictMode=false: strict:false + best-effort original schema
  - MCP tools: always strict:false regardless of setting
- Wire setting into all 4 openai.ts request paths
- Fix reasoning effort unsafe cast, add xhigh and max values
- Make parallel_tool_calls conditional on tools being present
Zoo (VP)
fix(i18n): add strictToolSchemas locale keys to modelInfo section
ca4ba42
Zoo (VP)
chore: remove session report files from branch
2f53771
Zoo (VP)
fix(i18n): add missing strictToolSchemas translations to all 17 locales
417768d
Zoo (VP)
fix(providers): strictMode passthrough, schema conversion, reasoning_…
23e3526 
…effort
Zoo (VP)
fix(i18n): remove duplicate strictToolSchemas keys in en settings locale
52c8414 
Merge debris left strictToolSchemas/strictToolSchemasDescription twice
in the modelInfo object; JSON.parse silently kept the last occurrence.
Add scripts/find-dup-json-keys.js to detect duplicate sibling keys;
scan of all 18 locales shows en was the only affected file.
Zoo (VP)
fix(i18n): document profile scope of strict tool schemas setting
587193d 
openAiToolStrictMode is honored by all OpenAI-protocol providers in a
profile, but the checkbox only exists under the OpenAI Compatible
section. Extend strictToolSchemasDescription to state the setting is
saved per profile and applies to other OpenAI-protocol providers.
Non-en locales hold untranslated English text for this key, so they
get the clarification appended as an English parenthetical.
@coderabbitai

coderabbitai Bot commented Aug 4, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

Warning

Review limit reached

@myk1yt, you've reached your PR review limit, so we couldn't start this review.

Next review available in: 34 minutes

You've used all free OSS reviews for now. Wait for the free limit to reset to keep reviewing this public repository.

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details
⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro Plus

Run ID: 4ed617e3-7b1d-4355-9e9e-2e2f06cdfb99

📥 Commits

Reviewing files that changed from the base of the PR and between 7918f6b and 676f396.

📒 Files selected for processing (36)
  • codecov.yml
  • packages/types/src/__tests__/provider-settings.test.ts
  • packages/types/src/provider-settings.ts
  • scripts/find-dup-json-keys.js
  • src/api/providers/__tests__/base-provider.spec.ts
  • src/api/providers/__tests__/openai.spec.ts
  • src/api/providers/base-openai-compatible-provider.ts
  • src/api/providers/base-provider.ts
  • src/api/providers/deepseek.ts
  • src/api/providers/friendli.ts
  • src/api/providers/kenari.ts
  • src/api/providers/lite-llm.ts
  • src/api/providers/lm-studio.ts
  • src/api/providers/openai-compatible.ts
  • src/api/providers/openai.ts
  • src/api/providers/opencode-go.ts
  • src/api/providers/openrouter.ts
  • webview-ui/src/components/settings/providers/OpenAICompatible.tsx
  • webview-ui/src/i18n/locales/ca/settings.json
  • webview-ui/src/i18n/locales/de/settings.json
  • webview-ui/src/i18n/locales/en/settings.json
  • webview-ui/src/i18n/locales/es/settings.json
  • webview-ui/src/i18n/locales/fr/settings.json
  • webview-ui/src/i18n/locales/hi/settings.json
  • webview-ui/src/i18n/locales/id/settings.json
  • webview-ui/src/i18n/locales/it/settings.json
  • webview-ui/src/i18n/locales/ja/settings.json
  • webview-ui/src/i18n/locales/ko/settings.json
  • webview-ui/src/i18n/locales/nl/settings.json
  • webview-ui/src/i18n/locales/pl/settings.json
  • webview-ui/src/i18n/locales/pt-BR/settings.json
  • webview-ui/src/i18n/locales/ru/settings.json
  • webview-ui/src/i18n/locales/tr/settings.json
  • webview-ui/src/i18n/locales/vi/settings.json
  • webview-ui/src/i18n/locales/zh-CN/settings.json
  • webview-ui/src/i18n/locales/zh-TW/settings.json

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.

@codecov

codecov Bot commented Aug 4, 2026 •
edited
Loading

Copy link
Copy Markdown

Codecov Report

❌ Patch coverage is 83.33333% with 5 lines in your changes missing coverage. Please review.

Files with missing lines Patch % Lines
...c/api/providers/base-openai-compatible-provider.ts 33.33% 1 Missing and 1 partial ⚠️
src/api/providers/openai.ts 81.81% 1 Missing and 1 partial ⚠️
src/api/providers/openai-compatible.ts 0.00% 1 Missing ⚠️

📢 Thoughts on this report? Let us know!

@github-actions github-actions Bot added the awaiting-review PR changes are ready and waiting for maintainer re-review label Aug 4, 2026
@myk1yt
myk1yt force-pushed the pr/b05a-strict-reasoning-v2 branch 2 times, most recently from 2adc65a to 77e7207 Compare August 4, 2026 20:31
@myk1yt
myk1yt force-pushed the pr/b05a-strict-reasoning-v2 branch from 77e7207 to a3b22a7 Compare August 4, 2026 20:40
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@taltas taltas Awaiting requested review from taltas taltas is a code owner
@JamesRobert20 JamesRobert20 Awaiting requested review from JamesRobert20 JamesRobert20 is a code owner
@navedmerchant navedmerchant Awaiting requested review from navedmerchant navedmerchant is a code owner
@hannesrudolph hannesrudolph Awaiting requested review from hannesrudolph hannesrudolph is a code owner
@edelauna edelauna Awaiting requested review from edelauna edelauna is a code owner

At least 1 approving review is required to merge this pull request.

Assignees

No one assigned

Labels

awaiting-review PR changes are ready and waiting for maintainer re-review

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@myk1yt