fix(openai): honor OPENAI_BASE_URL when no provider config sets a baseUrl by sunapi386 · Pull Request #74427 · openclaw/openclaw

sunapi386 · 2026-04-29T14:58:50Z

Summary

The dynamic-model resolver in extensions/openai/openai-provider.ts hardcodes baseUrl: \"https://api.openai.com/v1\" for every default GPT entry. This silently overrides OPENAI_BASE_URL, so users running OpenClaw behind a LiteLLM/vLLM/local proxy get a 401 from api.openai.com even when the env var is set correctly — the discovered baseUrl wins via ?? discoveredModel.baseUrl in src/agents/pi-embedded-runner/model.ts:530.

The fix introduces resolveOpenAIDefaultBaseUrl() in extensions/openai/base-url.ts that returns process.env.OPENAI_BASE_URL (when non-empty) and falls back to https://api.openai.com/v1. The 5 hardcoded literals in the registry are replaced with the helper.

This mirrors the precedent of #55597 ("honor OPENAI_BASE_URL in whisper api skill") and matches what the OpenAI Node SDK already does — its constructor falls back to process.env.OPENAI_BASE_URL when baseURL is undefined.

Backwards compatibility

Provider-config baseUrl still takes precedence (the resolver consults providerConfig.baseUrl before discoveredModel.baseUrl at model.ts:530):

User has	Before	After
Nothing (default)	api.openai.com	api.openai.com (unchanged)
`models.providers.openai.baseUrl` in config	their config	their config (unchanged)
Only `OPENAI_BASE_URL` env var	api.openai.com (silent ignore)	env var honored
Both env var and config	config	config (unchanged)

No existing user is broken. Users who set the env var expecting it to work — like the OpenAI Node SDK's own behavior — now get the routing they expected.

Why not anthropic too

Anthropic's hardcoded fallback is in src/agents/anthropic-transport-stream.ts:474 rather than a model registry, and the discovery flow is shaped differently. Keeping this PR scoped to OpenAI to mirror the #55597 precedent and make review easy. Happy to follow up with an analogous Anthropic PR if this lands.

Test plan

Added unit coverage in extensions/openai/base-url.test.ts (env unset, empty, whitespace, custom URL).
pnpm test -- extensions/openai/base-url.test.ts passes (6 tests).
CI run on upstream main.

clawsweeper · 2026-04-29T15:03:39Z

Codex review: needs real behavior proof before merge. Reviewed May 30, 2026, 12:52 AM ET / 04:52 UTC.

Summary
Review failed before ClawSweeper could summarize the requested change.

PR surface: Source +16, Tests +11, Docs +1. Total +28 across 4 files.

Reproducibility: unclear. The review failed before ClawSweeper could establish a reproduction path.

Review metrics: none identified.

Merge readiness
Overall: 🌊 off-meta tidepool
Proof: 🌊 off-meta tidepool
Patch quality: 🌊 off-meta tidepool
Result: rating does not apply to this item.

Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch.

Risk before merge

[P1] No close action taken because the review did not complete.

Maintainer options:

Decide the mitigation before merge
Retry the Codex review after fixing the execution failure.
Pause or close
Do not merge this PR until maintainers decide whether the risk is worth taking.

Next step before merge

[P1] Review did not complete, so no work-lane recommendation was made.

Review details

Best possible solution:

Retry the Codex review after fixing the execution failure.

Do we have a high-confidence way to reproduce the issue?

Unclear. The review failed before ClawSweeper could establish a reproduction path.

Is this the best way to solve the issue?

Unclear. Retry the review first so ClawSweeper can evaluate the actual issue and fix direction.

AGENTS.md: unclear because the file could not be read completely.

Codex review notes: model gpt-5.5, reasoning high; reviewed against b9933b2ec119.

Label changes

Label changes:

add rating: 🌊 off-meta tidepool: Overall readiness is 🌊 off-meta tidepool; proof is 🌊 off-meta tidepool and patch quality is 🌊 off-meta tidepool.

Label justifications:

rating: 🌊 off-meta tidepool: Overall readiness is 🌊 off-meta tidepool; proof is 🌊 off-meta tidepool and patch quality is 🌊 off-meta tidepool.

Evidence reviewed

PR surface:

Source +16, Tests +11, Docs +1. Total +28 across 4 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	2	22	6	+16
Tests	1	11	0	+11
Docs	1	1	0	+1
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	4	34	6	+28

What I checked:

failure reason: codex execution failed.
codex failure detail: Codex review failed for this PR with exit 1.
codex stdout: Per-item Codex failure; continuing with the rest of the shard.

Likely related people:

unknown: Codex failed before it could trace repository history. (role: review did not complete; confidence: low)

What the crustacean ranks mean

🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
🌊 off-meta tidepool: rating does not apply to this item.

Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics.

How this review workflow works

ClawSweeper keeps one durable marker-backed review comment per issue or PR.
Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
Maintainers can also comment @clawsweeper review to request a fresh review only.
Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.

…eUrl The dynamic-model resolver in extensions/openai/openai-provider.ts hardcoded `baseUrl: "https://api.openai.com/v1"` for every default GPT entry. This means setting `OPENAI_BASE_URL` in env (e.g. when running OpenClaw behind a LiteLLM/vLLM/local-proxy) has no effect — the discovered baseUrl wins via the `?? discoveredModel.baseUrl` fallback in src/agents/pi-embedded-runner/model.ts and the agent calls api.openai.com directly with a stale or proxy-style key, returning 401. Adds `resolveOpenAIDefaultBaseUrl()` in base-url.ts that returns `process.env.OPENAI_BASE_URL` (when non-empty) and falls back to the hardcoded URL otherwise. Replaces the 5 hardcoded literals in the dynamic model registry with the helper. This mirrors the precedent set by openclaw#55597 (honor OPENAI_BASE_URL in whisper api skill) and matches what the OpenAI Node SDK already does — its constructor falls back to env when `baseURL` is undefined. Provider-config baseUrl still takes precedence (resolver consults `providerConfig.baseUrl` before `discoveredModel.baseUrl`), so this is fully backwards-compatible: users with explicit config see no change, users with only the env var now get the routing they expected.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

openclaw-barnacle · 2026-05-30T04:47:45Z

This pull request has been automatically marked as stale due to inactivity.
Please add updates or it will be closed.

Repairs a batch of narrow model/provider edge cases: - honor OpenAI and Anthropic base URL environment overrides when provider config does not set an explicit base URL - preserve OpenRouter Anthropic cache retention while stripping unsupported transport options - allow apply_patch for non-OpenAI providers when the tool config otherwise permits it - prune stale same-provider model selections from configure/model picker state - expose GitHub Copilot bundled thinking policy metadata to offline/provider-policy lookups - repair additive SQLite shared-state upgrades for existing databases - keep same-size rotated log readers from reusing stale content in CI tooling Proof: - GitHub PR checks green on exact head 4651490 - Crabbox delegated Blacksmith Testbox tbx_01kt3em5r9vd7g0bnykrff6jdk exited 0 - Focused local Vitest/oxlint/format proof recorded in PR body and land-ready comment Fixes #80347. Fixes #88357. Fixes #45269. Supersedes #74427, #74432, #79370, #79894, #80366, and #88359.

steipete · 2026-06-02T06:36:19Z

Thanks for the PR. I landed the current-source version of this fix in #89347 / commit 732d697, with exact-head CI and focused provider/model proof recorded there.

Closing this as superseded by the merged maintainer batch.

Repairs a batch of narrow model/provider edge cases: - honor OpenAI and Anthropic base URL environment overrides when provider config does not set an explicit base URL - preserve OpenRouter Anthropic cache retention while stripping unsupported transport options - allow apply_patch for non-OpenAI providers when the tool config otherwise permits it - prune stale same-provider model selections from configure/model picker state - expose GitHub Copilot bundled thinking policy metadata to offline/provider-policy lookups - repair additive SQLite shared-state upgrades for existing databases - keep same-size rotated log readers from reusing stale content in CI tooling Proof: - GitHub PR checks green on exact head 4651490 - Crabbox delegated Blacksmith Testbox tbx_01kt3em5r9vd7g0bnykrff6jdk exited 0 - Focused local Vitest/oxlint/format proof recorded in PR body and land-ready comment Fixes openclaw#80347. Fixes openclaw#88357. Fixes openclaw#45269. Supersedes openclaw#74427, openclaw#74432, openclaw#79370, openclaw#79894, openclaw#80366, and openclaw#88359.

openclaw-barnacle Bot added extensions: openai size: XS labels Apr 29, 2026

This was referenced Apr 29, 2026

fix(anthropic): honor ANTHROPIC_BASE_URL when no baseUrl is configured #74432

Closed

feat: dynamic catalog refresh from configured provider /v1/models #74481

Open

sunapi386 and others added 2 commits May 13, 2026 11:49

chore: add changelog entry for OPENAI_BASE_URL fix

c8e3224

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

sunapi386 force-pushed the fix/openai-base-url-env branch from a9867dd to c8e3224 Compare May 13, 2026 15:51

openclaw-barnacle Bot added the triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. label May 13, 2026

openclaw-barnacle Bot added the stale Marked as stale due to inactivity label May 30, 2026

clawsweeper Bot added the rating: 🌊 off-meta tidepool PR readiness rating does not apply to this item. label May 30, 2026

barnacle-openclaw Bot removed the stale Marked as stale due to inactivity label May 30, 2026

steipete mentioned this pull request Jun 2, 2026

fix: repair model provider edge cases #89347

Merged

steipete closed this Jun 2, 2026

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(openai): honor OPENAI_BASE_URL when no provider config sets a baseUrl#74427

fix(openai): honor OPENAI_BASE_URL when no provider config sets a baseUrl#74427
sunapi386 wants to merge 2 commits into
openclaw:mainfrom
aceteam-ai:fix/openai-base-url-env

sunapi386 commented Apr 29, 2026

Uh oh!

clawsweeper Bot commented Apr 29, 2026 •

edited

Loading

Uh oh!

openclaw-barnacle Bot commented May 30, 2026

Uh oh!

steipete commented Jun 2, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

sunapi386 commented Apr 29, 2026

Summary

Backwards compatibility

Why not anthropic too

Test plan

Uh oh!

clawsweeper Bot commented Apr 29, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

openclaw-barnacle Bot commented May 30, 2026

Uh oh!

steipete commented Jun 2, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

clawsweeper Bot commented Apr 29, 2026 •

edited

Loading