fix: model extraction for azure passthrough

[TejasGhatte]

Summary

Azure OpenAI deployment-based routes encode the model identifier in the URL path as deployments/{deployment} rather than in the request body. Without recognising this path segment, model extraction would fail for Azure passthrough requests, causing the deployment name to be lost.

Changes

• Added "deployments" as a recognised path segment in extractModelFromPath, alongside "models" and "tunedModels", so that Azure OpenAI routes like /openai/deployments/my-gpt4o/chat/completions correctly resolve my-gpt4o as the model identifier.
• Added TestExtractModelFromPath covering GenAI (models/tunedModels with :action suffixes), Vertex fully-qualified publisher paths, Azure deployments/{deployment} paths, and edge cases with no model segment.
• Added TestExtractPassthroughModel verifying that the path-extracted value takes precedence over the body model, with the body model used as a fallback when the path contains no model segment — the expected behaviour for Azure deployment routes where the body typically omits "model".

Type of change

• Bug fix
• Feature
• Refactor
• Documentation
• Chore/CI

Affected areas

• Core (Go)
• Transports (HTTP)
• Providers/Integrations
• Plugins
• UI (React)
• Docs

How to test

go test ./transports/bifrost-http/integrations/...

The two new test functions TestExtractModelFromPath and TestExtractPassthroughModel directly exercise the changed logic. Confirm all cases pass, particularly:

• azure deployment chat: expects my-gpt4o extracted from /openai/deployments/my-gpt4o/chat/completions
• azure deployment path overrides empty body: expects my-gpt4o when body model is empty
• deployments with no trailing segment: expects "" when no deployment name follows the segment

Breaking changes

• Yes
• No

Related issues

Security considerations

None. This change only affects URL path parsing for model name extraction and introduces no new auth, secret handling, or external surface area.

Checklist

• I read docs/contributing/README.md and followed the guidelines
• I added/updated tests where appropriate
• I updated documentation where needed
• I verified builds succeed (Go and UI)
• I verified the CI pipeline passes locally if applicable

Summary by CodeRabbit

• Bug Fixes

  • Improved Azure OpenAI integration support.

• Tests

  • Added test coverage for model extraction and routing logic.

[coderabbitai]

📝 Walkthrough

Walkthrough

The PR extends the HTTP router's model extraction logic to recognize deployments as a model identifier segment for Azure OpenAI deployment-based routes alongside models and tunedModels. Comprehensive table-driven tests validate the extraction behavior across multiple provider path formats and fallback scenarios.

Changes

Model extraction from deployment paths

Layer / File(s)	Summary
Model extraction from deployment paths transports/bifrost-http/integrations/router.go, transports/bifrost-http/integrations/router_test.go	extractModelFromPath now recognizes deployments as a model identifier segment for Azure OpenAI routes. TestExtractModelFromPath validates extraction across Azure deployments, GenAI paths with actions, Vertex fully-qualified paths, and edge cases. TestExtractPassthroughModel validates path-derived model precedence with body model fallback.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Suggested reviewers

• akshaydeo
• Pratham-Mishra04

Poem

A rabbit hops through Azure's gates, 🐰
Finding models in deployments' fates,
With tests to guide each winding way,
The path extraction works today! ✨

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 75.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Description check	✅ Passed	The description includes all required sections with relevant details about the bug fix, changes, testing approach, and security considerations.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Title check	✅ Passed	The title accurately identifies the main change: adding support for 'deployments' in model extraction for Azure passthrough routes, which is the primary focus of the changeset.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

📝 Generate docstrings

• Create stacked PR
• Commit on current branch

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch 06-02-fix_model_extraction_for_azure_passthrough

---

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

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.

---

tejas ghatte seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[TejasGhatte]

• fix: model extraction for azure passthrough #3983 👈 (View in Graphite)
• dev

This stack of pull requests is managed by Graphite. Learn more about stacking.

[greptile-apps]

Confidence Score: 4/5

The change is narrowly scoped to URL path parsing with no auth, networking, or state side-effects; the only open item is a stale doc comment.

The logic change is a one-line addition to a pure string-parsing function with good table-driven test coverage. The extractPassthroughModel doc comment was not updated to mention the new Azure pattern, which is the only thing worth fixing before merging.

transports/bifrost-http/integrations/router.go — specifically the stale extractPassthroughModel doc comment

Important Files Changed

Filename	Overview
transports/bifrost-http/integrations/router.go	Adds "deployments" as a recognised path keyword in extractModelFromPath; existing logic (return first match, break on trailing keyword, strip :suffix) applies correctly to Azure deployment paths. Only the doc comment on extractPassthroughModel is stale.
transports/bifrost-http/integrations/router_test.go	Adds TestExtractModelFromPath (8 table-driven cases covering GenAI, Vertex, Azure, and edge cases) and TestExtractPassthroughModel (4 cases validating path-wins-over-body precedence and fallback). Coverage is thorough for the changed logic.

Comments Outside Diff (1)

1. transports/bifrost-http/integrations/router.go, line 2843-2845 (link)

   The extractPassthroughModel doc comment was not updated alongside extractModelFromPath, so the Azure deployments/{deployment} pattern is missing from the listed path patterns, making the comment misleading for future readers.

   Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!

_{Reviews (1): Last reviewed commit: "fix:model extraction for azure passthrou..." | Re-trigger Greptile}

[akshaydeo]

Merge activity

• Jun 2, 11:03 AM UTC: A user started a stack merge that includes this pull request via Graphite.
• Jun 2, 11:03 AM UTC: @akshaydeo merged this pull request with Graphite.