fix(image_edit): forward litellm_params to validate_environment for Vertex AI credentials

[Sameerlite]

Summary

Fixes Vertex AI image-edit failing with DefaultCredentialsError when credentials are passed via YAML config (e.g., Open WebUI).

• /images/generations with identical config works fine
• /images/edits ignores vertex_credentials / vertex_project kwargs
• Root cause: handlers don't forward litellm_params to validate_environment
  fixes [Bug]: Can't authenticate to vertex ai image generation models through v1/images/edits #21691

Changes

1. Widen BaseImageEditConfig.validate_environment signature to accept optional litellm_params and api_base
2. Forward both in sync/async image_edit_handler (matching image_generation_handler)
3. Fix VertexAIImagenImageEditConfig to read creds from litellm_params first (secondary bug)
4. Update all 14 image-edit config overrides to match new base signature

Validation

• Repro script confirms credentials now reach Vertex AI (429 rate-limit instead of DefaultCredentialsError)
• Image-edit tests: 66 passed
• No breaking changes (all new params are optional)

Before

After

[greptile-apps]

Greptile Summary

This PR fixes DefaultCredentialsError for Vertex AI image-edit by forwarding litellm_params (and api_base) to validate_environment in both the sync and async image_edit_handler, matching the existing pattern in image_generation_handler. It also updates VertexAIImagenImageEditConfig.validate_environment to read credentials from litellm_params first, and fixes get_complete_url to do the same for project/location — addressing the two root causes that kept credentials from reaching the Vertex AI auth layer.

All 14 provider-specific overrides receive the new optional parameters (fully backwards-compatible), and focused mock-only regression tests are added for the Vertex Imagen and Gemini configs.

Confidence Score: 5/5

Safe to merge — the fix is minimal and targeted, all new parameters are optional, and the previously flagged P1 issues are fully resolved.

Both root causes (handler not forwarding litellm_params, and validate_environment/get_complete_url ignoring it) are correctly fixed and mirror the existing image_generation pattern. No breaking changes. Mock-only regression tests are added. No remaining P1 issues.

No files require special attention.

Important Files Changed

Filename	Overview
litellm/llms/custom_httpx/llm_http_handler.py	Forwards litellm_params and api_base to validate_environment in both sync and async image_edit handlers — the primary fix for this PR.
litellm/llms/vertex_ai/image_edit/vertex_imagen_transformation.py	validate_environment now reads credentials from litellm_params first; get_complete_url now reads project/location from litellm_params — both of the previously flagged P1 issues are resolved.
litellm/llms/base_llm/image_edit/transformation.py	Base class signature widened with optional litellm_params and api_base; all 14 concrete subclasses updated to match — no breaking changes.
tests/test_litellm/images/test_image_edit_utils.py	Adds regression tests for credential forwarding; all tests use mocks (no real network calls), consistent with the repo's test-folder policy.

Sequence Diagram

sequenceDiagram
    participant C as Caller
    participant H as image_edit_handler (sync/async)
    participant VE as validate_environment
    participant GU as get_complete_url
    participant VA as Vertex AI API

    C->>H: image_edit(model, image, prompt, litellm_params)
    Note over H: BEFORE: litellm_params NOT forwarded
    Note over H: AFTER: litellm_params forwarded ✓

    H->>VE: validate_environment(..., litellm_params, api_base)
    VE->>VE: safe_get_vertex_ai_credentials(litellm_params)
    VE->>VE: safe_get_vertex_ai_project(litellm_params)
    VE-->>H: headers with Bearer token

    H->>GU: get_complete_url(model, api_base, litellm_params)
    GU->>GU: safe_get_vertex_ai_project(litellm_params)
    GU->>GU: safe_get_vertex_ai_location(litellm_params)
    GU-->>H: https://.../{project}/{location}/...

    H->>VA: POST with auth headers
    VA-->>H: ImageResponse
    H-->>C: ImageResponse

Loading

_{Reviews (4): Last reviewed commit: "Merge pull request #26258 from BerriAI/l..." | Re-trigger Greptile}

[gitguardian]

⚠️ GitGuardian has uncovered 1 secret following the scan of your pull request.

Please consider investigating the findings and remediating the incidents. Failure to do so may lead to compromising the associated services or software components.

🔎 Detected hardcoded secret in your pull request

GitGuardian id	GitGuardian status	Secret	Commit	Filename
29203053	Triggered	Generic Password	221dc2f	.circleci/config.yml	View secret

🛠 Guidelines to remediate hardcoded secrets

1. Understand the implications of revoking this secret by investigating where it is used in your code.
2. Replace and store your secret safely. Learn here the best practices.
3. Revoke and rotate this secret.
4. If possible, rewrite git history. Rewriting git history is not a trivial act. You might completely break other contributing developers' workflow and you risk accidentally deleting legitimate data.

To avoid such incidents in the future consider

• following these best practices for managing and storing secrets including API keys and other credentials
• install secret detection on pre-commit to catch secret before it leaves your machine and ease remediation.

---

^{🦉 GitGuardian detects secrets in your source code to help developers and security teams secure the modern development process. You are seeing this because you or someone else with access to this repository has authorized GitGuardian to scan your pull request.}

[codecov]

Codecov Report

❌ Patch coverage is 87.50000% with 1 line in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
...rtex_ai/image_edit/vertex_imagen_transformation.py	87.50%	1 Missing ⚠️

📢 Thoughts on this report? Let us know!