Add base_path field to custom provider config#7558
Conversation
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: e3c69e9b2c
ℹ️ About Codex in GitHub
Codex has been enabled to automatically 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 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 9aed3005aa
ℹ️ About Codex in GitHub
Codex has been enabled to automatically 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 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
dprince
force-pushed
the
base_path
branch
2 times, most recently
from
f7dad47 to
ad589de
Compare
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: ad589de3c4
ℹ️ About Codex in GitHub
Codex has been enabled to automatically 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 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: dcb625d1cc
ℹ️ About Codex in GitHub
Codex has been enabled to automatically 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 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
dprince
force-pushed
the
base_path
branch
2 times, most recently
from
c1c6c26 to
58225f4
Compare
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 58225f4153
ℹ️ About Codex in GitHub
Codex has been enabled to automatically 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 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
Allow custom providers using the OpenAI engine to explicitly set the API path (e.g. "v1/responses" vs "v1/chat/completions") instead of relying on URL path parsing or the default. This enables pointing a custom provider at an OpenAI-compatible endpoint that serves the Responses API without needing to embed the path in the base_url. The new optional base_path field is threaded through the declarative provider config, CLI, and server routes. When set, it takes priority over both the URL-derived path and the model-name heuristic in should_use_responses_api(). Signed-off-by: Dan Prince <[email protected]>
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: bc8f180c6d
ℹ️ About Codex in GitHub
Codex has been enabled to automatically 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 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
* main: (46 commits) chore(deps): bump minimatch from 10.1.1 to 10.2.3 in /evals/open-model-gym/suite (#7498) chore(deps): bump swiper from 11.2.10 to 12.1.2 in /documentation (#7368) Better network failure error & antrhopic retry (#7595) feat: make the text bar persistent and add a queue for messages (#7560) fix: outdated clippy command in goosehints (#7590) chore(deps): bump hono from 4.11.7 to 4.12.1 in /evals/open-model-gym/mcp-harness (#7417) chore(deps-dev): bump ajv from 6.12.6 to 6.14.0 in /ui/desktop (#7437) chore(deps): bump ajv from 8.17.1 to 8.18.0 in /evals/open-model-gym/mcp-harness (#7491) chore(deps): bump hono from 4.12.0 to 4.12.2 in /ui/desktop (#7515) chore(deps-dev): bump rollup from 4.57.1 to 4.59.0 in /ui/desktop (#7522) chore(deps): bump minimatch in /ui/desktop (#7572) fix: validate configure probe for streaming providers (#7564) Dockerfile: add missing build/runtime dependencies (#7546) fix(claude-code): Permission routing for smart-approve (#7501) Add base_path field to custom provider config (#7558) fix(cli): avoid debug logging by default in CLI (#7569) fix: panic on corrupted permission.yaml instead of silently allowing all (#7432) (#7458) fix(openai): handle null reasoning effort in Responses API (#7469) Allow GOOSE_NODE_DIR override in batch file (#7422) feat: add analyze platform extension with tree-sitter AST parsing (#7542) ...
* origin/main: (27 commits)
feat: return structured {stdout, stderr} from shell tool with output schema (#7604)
Improve custom provider creation experience (#7541)
fix(scheduler): schedules added via CLI showing up in UI (#7594)
chore: openai reasoning model cleanup (#7529)
chore(deps): bump hono from 4.12.1 to 4.12.3 in /evals/open-model-gym/mcp-harness (#7585)
chore(deps): bump minimatch from 10.1.1 to 10.2.3 in /evals/open-model-gym/suite (#7498)
chore(deps): bump swiper from 11.2.10 to 12.1.2 in /documentation (#7368)
Better network failure error & antrhopic retry (#7595)
feat: make the text bar persistent and add a queue for messages (#7560)
fix: outdated clippy command in goosehints (#7590)
chore(deps): bump hono from 4.11.7 to 4.12.1 in /evals/open-model-gym/mcp-harness (#7417)
chore(deps-dev): bump ajv from 6.12.6 to 6.14.0 in /ui/desktop (#7437)
chore(deps): bump ajv from 8.17.1 to 8.18.0 in /evals/open-model-gym/mcp-harness (#7491)
chore(deps): bump hono from 4.12.0 to 4.12.2 in /ui/desktop (#7515)
chore(deps-dev): bump rollup from 4.57.1 to 4.59.0 in /ui/desktop (#7522)
chore(deps): bump minimatch in /ui/desktop (#7572)
fix: validate configure probe for streaming providers (#7564)
Dockerfile: add missing build/runtime dependencies (#7546)
fix(claude-code): Permission routing for smart-approve (#7501)
Add base_path field to custom provider config (#7558)
...
* main: (74 commits)
feat: return structured {stdout, stderr} from shell tool with output schema (#7604)
Improve custom provider creation experience (#7541)
fix(scheduler): schedules added via CLI showing up in UI (#7594)
chore: openai reasoning model cleanup (#7529)
chore(deps): bump hono from 4.12.1 to 4.12.3 in /evals/open-model-gym/mcp-harness (#7585)
chore(deps): bump minimatch from 10.1.1 to 10.2.3 in /evals/open-model-gym/suite (#7498)
chore(deps): bump swiper from 11.2.10 to 12.1.2 in /documentation (#7368)
Better network failure error & antrhopic retry (#7595)
feat: make the text bar persistent and add a queue for messages (#7560)
fix: outdated clippy command in goosehints (#7590)
chore(deps): bump hono from 4.11.7 to 4.12.1 in /evals/open-model-gym/mcp-harness (#7417)
chore(deps-dev): bump ajv from 6.12.6 to 6.14.0 in /ui/desktop (#7437)
chore(deps): bump ajv from 8.17.1 to 8.18.0 in /evals/open-model-gym/mcp-harness (#7491)
chore(deps): bump hono from 4.12.0 to 4.12.2 in /ui/desktop (#7515)
chore(deps-dev): bump rollup from 4.57.1 to 4.59.0 in /ui/desktop (#7522)
chore(deps): bump minimatch in /ui/desktop (#7572)
fix: validate configure probe for streaming providers (#7564)
Dockerfile: add missing build/runtime dependencies (#7546)
fix(claude-code): Permission routing for smart-approve (#7501)
Add base_path field to custom provider config (#7558)
...
Signed-off-by: Dan Prince <[email protected]>
2 participants
Summary
Allow custom providers using the OpenAI engine to explicitly set the API path (e.g. "v1/responses" vs "v1/chat/completions") instead of relying on URL path parsing or the default. This enables pointing a custom provider at an OpenAI-compatible endpoint that serves the Responses API without needing to embed the path in the base_url.
The new optional base_path field is threaded through the declarative provider config, CLI, and server routes. When set, it takes priority over both the URL-derived path and the model-name heuristic in should_use_responses_api().
Using a custom provider is preferred rather than using the openai provider directly and overriding OPENAI_BASE_PATH as doing the latter has other side effects (secondary LLM configuration etc) which isn't
always present.
A use case for this configuration would be using goose with lightspeed-core/lightspeed-stack. (the reason for this PR)
Type of Change
AI Assistance
Testing
Yes. Functionally tested against lightspeed-stack. Was able to use the /v1/responses API with a custom hosted offline/airgapped LLM hosted in this fastion with a goose custom provider configuration.