Skip to content

removes from_memory for APIs - #3903

Merged
akshaydeo merged 1 commit into
devfrom
05-30-removes_from_memory_for_apis
May 30, 2026
Merged

removes from_memory for APIs#3903
akshaydeo merged 1 commit into
devfrom
05-30-removes_from_memory_for_apis

Conversation

@akshaydeo

@akshaydeo akshaydeo commented May 30, 2026

Copy link
Copy Markdown
Contributor

Summary

Removes the from_memory query parameter shortcut from all governance API endpoints and fixes a cache-poisoning risk in the filter data handler. Previously, callers could pass ?from_memory=true to bypass the database and read directly from the in-memory governance snapshot. This path is now removed entirely — all reads go through the ConfigStore — ensuring responses always reflect persisted state. Additionally, the filter data cache is now skipped for DAC-scoped requests to prevent scoped data from being served to unscoped callers (or vice versa).

Changes

  • Removed from_memory branch from getVirtualKeys, getVirtualKey, getTeams, getTeam, getCustomers, getCustomer, getBudgets, getRateLimits, getModelConfigs, getProviderGovernance, getRoutingRules, and getRoutingRule — all now unconditionally delegate to ConfigStore.
  • Replaced the in-memory VK name lookup in getMCPClientsPaginated with targeted GetVirtualKey calls per unique VK ID found in the fetched assignments, removing the dependency on governanceManager.GetGovernanceData.
  • Introduced shouldUseFilterDataCache to gate the shared filterdata cache on both an empty query string and the absence of a DAC query scope in the request context, preventing cross-scope cache hits.

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/handlers/...
  • Confirm that GET /api/governance/virtual-keys?from_memory=true returns the same DB-backed response as without the parameter.
  • Confirm that GET /api/logs/filterdata with a DAC-scoped request context does not return cached data from an unscoped request.
  • Confirm that GET /api/governance/routing-rules/{id} returns 404 for a missing rule and the correct rule for a valid ID.

Breaking changes

  • Yes
  • No

The from_memory=true query parameter is no longer honored on any governance endpoint. Clients relying on this parameter will continue to receive valid responses, but data will always be sourced from the database rather than the in-memory snapshot.

Security considerations

The filter data cache fix prevents a DAC-scoped request from populating or consuming the shared all-data cache, closing a potential data leakage path where one tenant's scope constraints could be bypassed by a cache hit populated under a different (or no) scope.

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

Release Notes

  • Bug Fixes

    • Governance API endpoints now consistently use database-backed responses for all requests, ensuring data consistency
    • Filter data caching now properly respects query scoping constraints
    • Virtual key enrichment improved with batch fetching for better reliability
  • Tests

    • Added test coverage for governance endpoint caching behavior and filter data caching logic

Review Change Stack

@CLAassistant

Copy link
Copy Markdown

CLA assistant check
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.
You have signed the CLA already but the status is still pending? Let us recheck it.

@coderabbitai

coderabbitai Bot commented May 30, 2026

Copy link
Copy Markdown
Contributor
📝 Walkthrough

Walkthrough

Removes from_memory=true in-memory bypass across governance GET handlers so all reads use ConfigStore; adds query-scope-aware gating for filterdata cache; updates MCP VK enrichment to batch-fetch VK names from ConfigStore; and adds tests for routing and cache behavior.

Changes

Governance Data Source & Caching Consolidation

Layer / File(s) Summary
Governance endpoints – remove in-memory bypass
transports/bifrost-http/handlers/governance.go
Removed from_memory=true checks across governance GET handlers (virtual-keys, virtual-keys/{vk_id}, teams, teams/{team_id}, customers, customers/{customer_id}, budgets, rate-limits, model-configs, providers, routing-rules, routing-rules/{rule_id}); all reads now use ConfigStore with existing pagination/filter behavior preserved; getRoutingRule always uses configStore.GetRoutingRule.
Governance tests – validate ConfigStore usage
transports/bifrost-http/handlers/governance_test.go
Mocks updated to record call counts. Added tests asserting from_memory=true routes through ConfigStore non-paginated and paginated paths with zero governance-manager calls.
Filter data cache – add query scope awareness
transports/bifrost-http/handlers/logging.go, transports/bifrost-http/handlers/logging_test.go
Added shouldUseFilterDataCache(ctx, query) requiring empty/whitespace query and no active query scope to enable cache. Updated /api/logs/filterdata and /api/mcp-logs/filterdata to use it. Added three tests covering unscoped empty queries, non-empty searches, and DAC-scoped contexts.
MCP clients – refactor virtual key name resolution
transports/bifrost-http/handlers/mcp.go
Changed getMCPClientsPaginated to deduplicate VK IDs on the current page and batch-fetch redacted virtual keys via ConfigStore to populate names; logs batch fetch errors and leaves names unset for missing keys.

Estimated code review effort

🎯 4 (Complex) | ⏱️ ~40 minutes

Suggested reviewers

  • danpiths
  • roroghost17

Poem

🐰 I bounced from cache into the store,

No more in-memory detours to explore.
Twelve handlers now read straight and sure,
Filterdata keeps scopes pure,
VK names fetched in one tidy tour. 🥕

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Docstring Coverage ⚠️ Warning Docstring coverage is 77.78% 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
Title check ✅ Passed The title 'removes from_memory for APIs' directly and concisely describes the main change: removal of the from_memory query parameter from governance API endpoints.
Description check ✅ Passed The description comprehensively covers all required sections: summary of purpose, detailed changes, type of change, affected areas, testing steps, breaking changes, security considerations, and checklist completion.
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.

✏️ 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 05-30-removes_from_memory_for_apis

Warning

There were issues while running some tools. Please review the errors and either fix the tool's configuration or disable the tool if it's a critical failure.

🔧 golangci-lint (2.12.2)

level=error msg="[linters_context] typechecking error: pattern ./...: directory prefix . does not contain main module or its selected dependencies"


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

@akshaydeo
akshaydeo marked this pull request as ready for review May 30, 2026 11:38

Copy link
Copy Markdown
Contributor Author

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

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@transports/bifrost-http/handlers/governance_test.go`:
- Around line 1334-1359: The test
TestGetVirtualKeys_FromMemoryWithLimitUsesPaginatedConfigStore should also
assert the non-paginated path wasn't invoked: after calling
h.getVirtualKeys(ctx) add a check that the mock config store's non-paginated
call counter (e.g. store.getVirtualKeysCalls) is 0 so the test fails if both
GetVirtualKeys and GetVirtualKeysPaginated are called; modify the test to
include this negative-path assertion alongside the existing checks on
manager.getGovernanceDataCalls and store.getVirtualKeysPaginatedCalls.
🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

  • Push a commit to this branch (recommended)
  • Create a new PR with the fixes

ℹ️ Review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: ASSERTIVE

Plan: Pro

Run ID: 11cc5f8f-ffff-4f99-a024-9168f7fe9a37

📥 Commits

Reviewing files that changed from the base of the PR and between 67e57dd and 5e36679.

📒 Files selected for processing (5)
  • transports/bifrost-http/handlers/governance.go
  • transports/bifrost-http/handlers/governance_test.go
  • transports/bifrost-http/handlers/logging.go
  • transports/bifrost-http/handlers/logging_test.go
  • transports/bifrost-http/handlers/mcp.go

Comment thread transports/bifrost-http/handlers/governance_test.go
@greptile-apps

greptile-apps Bot commented May 30, 2026

Copy link
Copy Markdown
Contributor

Confidence Score: 5/5

Safe to merge — the changes are a targeted removal of a bypass path and a focused cache-gate fix with no modifications to write paths or error-handling contracts.

All 12 handler changes are pure deletions of the from_memory branch; the retained ConfigStore delegation paths are untouched. The shouldUseFilterDataCache guard is additive and cannot produce false positives because it only widens the no-cache condition. The MCP VK enrichment swap is logically equivalent for the happy path and degrades gracefully (logged error, empty VK names) on failure. New unit tests cover the critical invariants introduced by each of the three changes.

No files require special attention.

Important Files Changed

Filename Overview
transports/bifrost-http/handlers/governance.go Removes the from_memory query parameter branch from all 12 governance handlers; all reads now unconditionally delegate to ConfigStore. Clean diff with no regression in error-handling logic.
transports/bifrost-http/handlers/governance_test.go Adds call-count instrumentation to mocks and two new tests verifying that from_memory=true no longer routes to GetGovernanceData and instead hits the appropriate ConfigStore method.
transports/bifrost-http/handlers/logging.go Introduces shouldUseFilterDataCache to gate the shared filterdata cache on both an empty query string and the absence of a DAC query scope, preventing cross-scope cache poisoning. Applied consistently to both getAvailableFilterData and getMCPLogsFilterData.
transports/bifrost-http/handlers/logging_test.go New file with three focused unit tests covering empty-query, whitespace-only, non-empty-query, and scoped-context inputs for shouldUseFilterDataCache; complete coverage of the logic.
transports/bifrost-http/handlers/mcp.go Replaces in-memory VK name lookup (single governance snapshot read) with a deduplication pass over assignment VK IDs followed by a single GetRedactedVirtualKeys batch call, removing the dependency on governanceManager.GetGovernanceData.

Reviews (2): Last reviewed commit: "removes from_memory for APIs" | Re-trigger Greptile

Comment thread transports/bifrost-http/handlers/mcp.go
@akshaydeo
akshaydeo force-pushed the 05-30-removes_from_memory_for_apis branch from 5e36679 to 2d00bb7 Compare May 30, 2026 12:11

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@transports/bifrost-http/handlers/governance.go`:
- Around line 3263-3271: Add a regression test that exercises the DB-backed
single-rule lookup path which calls configStore.GetRoutingRule: create a test
hitting the same handler that sets from_memory=true and asserts a successful 200
response for a found rule, and a separate subtest where the mocked configStore
returns configstore.ErrNotFound to assert the handler returns a 404 and calls
SendError accordingly; also add a test where configStore returns a non-not-found
error to assert a 500 mapping. Ensure the tests validate request parsing
(query/body flags like from_memory), verify middleware ordering if applicable
(authentication/validation run before configStore lookup), and use the handler
function in governance.go and the configStore mock to target GetRoutingRule
behavior and SendError status mapping.
🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

  • Push a commit to this branch (recommended)
  • Create a new PR with the fixes

ℹ️ Review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: ASSERTIVE

Plan: Pro

Run ID: cf85fede-9475-475a-af15-4a1c36439428

📥 Commits

Reviewing files that changed from the base of the PR and between 5e36679 and 2d00bb7.

📒 Files selected for processing (5)
  • transports/bifrost-http/handlers/governance.go
  • transports/bifrost-http/handlers/governance_test.go
  • transports/bifrost-http/handlers/logging.go
  • transports/bifrost-http/handlers/logging_test.go
  • transports/bifrost-http/handlers/mcp.go

Comment thread transports/bifrost-http/handlers/governance.go

akshaydeo commented May 30, 2026

Copy link
Copy Markdown
Contributor Author

Merge activity

  • May 30, 12:42 PM UTC: A user started a stack merge that includes this pull request via Graphite.
  • May 30, 12:42 PM UTC: @akshaydeo merged this pull request with Graphite.

@akshaydeo
akshaydeo merged commit 2372f04 into dev May 30, 2026
14 of 15 checks passed
@akshaydeo
akshaydeo deleted the 05-30-removes_from_memory_for_apis branch May 30, 2026 12:42
@akshaydeo akshaydeo mentioned this pull request May 30, 2026
18 tasks
akshaydeo added a commit that referenced this pull request May 30, 2026
## Summary

This release (core v1.5.15, framework v1.3.15) fixes missing `Authorization` header forwarding on streaming requests for the Ollama and SGL providers, ensuring authenticated requests behave correctly during streaming.

## Changes

- Ollama streaming text and chat completion requests now correctly forward the configured API key as an `Authorization: Bearer` header (#3906)
- SGL provider now sends the `Authorization` header on streaming requests (#3307) (thanks [@hensapir](https://github.com/hensapir)!)
- Governance and Logging APIs: removed the `from_memory` query parameter; virtual key and config list APIs now return consistent DB-backed results, with VK names batch-fetched in a single query (#3903)
- Bumped core to v1.5.15, framework to v1.3.15, transports to v1.5.7, and all dependent plugins to their respective patch versions

## Type of change

- [x] Bug fix
- [ ] Feature
- [ ] Refactor
- [ ] Documentation
- [ ] Chore/CI

## Affected areas

- [x] Core (Go)
- [x] Transports (HTTP)
- [x] Providers/Integrations
- [x] Plugins
- [ ] UI (React)
- [ ] Docs

## How to test

Validate that Ollama and SGL streaming requests include the `Authorization: Bearer` header when an API key is configured.

```sh
# Core/Transports
go version
go test ./...
```

Configure an Ollama or SGL provider with an API key and issue a streaming chat or text completion request. Inspect outbound request headers to confirm `Authorization: Bearer <key>` is present.

## Breaking changes

- [ ] Yes
- [x] No

## Related issues

Closes #3906
Closes #3307
Closes #3903

## Security considerations

These fixes ensure that API keys configured for Ollama and SGL providers are correctly forwarded on streaming requests. Previously, the `Authorization` header was silently dropped on streaming paths, meaning requests could reach upstream providers without authentication credentials.

## Checklist

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

<!-- This is an auto-generated comment: release notes by coderabbit.ai -->

## Summary by CodeRabbit

* **Bug Fixes**
  * Fixed authorization header handling for Ollama streaming requests.
  * Fixed authorization header forwarding for SGL provider streaming requests.
  * Improved consistency in virtual key and configuration list API responses by removing unnecessary query parameters.

* **Chores**
  * Updated component versions across the platform.

<!-- review_stack_entry_start -->

[![Review Change Stack](https://storage.googleapis.com/coderabbit_public_assets/review-stack-in-coderabbit-ui.svg)](https://app.coderabbit.ai/change-stack/maximhq/bifrost/pull/3907?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack)

<!-- review_stack_entry_end -->

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
akshaydeo added a commit that referenced this pull request May 30, 2026
This release (core v1.5.15, framework v1.3.15) fixes missing `Authorization` header forwarding on streaming requests for the Ollama and SGL providers, ensuring authenticated requests behave correctly during streaming.

- Ollama streaming text and chat completion requests now correctly forward the configured API key as an `Authorization: Bearer` header (#3906)
- SGL provider now sends the `Authorization` header on streaming requests (#3307) (thanks [@hensapir](https://github.com/hensapir)!)
- Governance and Logging APIs: removed the `from_memory` query parameter; virtual key and config list APIs now return consistent DB-backed results, with VK names batch-fetched in a single query (#3903)
- Bumped core to v1.5.15, framework to v1.3.15, transports to v1.5.7, and all dependent plugins to their respective patch versions

- [x] Bug fix
- [ ] Feature
- [ ] Refactor
- [ ] Documentation
- [ ] Chore/CI

- [x] Core (Go)
- [x] Transports (HTTP)
- [x] Providers/Integrations
- [x] Plugins
- [ ] UI (React)
- [ ] Docs

Validate that Ollama and SGL streaming requests include the `Authorization: Bearer` header when an API key is configured.

```sh
go version
go test ./...
```

Configure an Ollama or SGL provider with an API key and issue a streaming chat or text completion request. Inspect outbound request headers to confirm `Authorization: Bearer <key>` is present.

- [ ] Yes
- [x] No

Closes #3906
Closes #3307
Closes #3903

These fixes ensure that API keys configured for Ollama and SGL providers are correctly forwarded on streaming requests. Previously, the `Authorization` header was silently dropped on streaming paths, meaning requests could reach upstream providers without authentication credentials.

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

<!-- This is an auto-generated comment: release notes by coderabbit.ai -->

* **Bug Fixes**
  * Fixed authorization header handling for Ollama streaming requests.
  * Fixed authorization header forwarding for SGL provider streaming requests.
  * Improved consistency in virtual key and configuration list API responses by removing unnecessary query parameters.

* **Chores**
  * Updated component versions across the platform.

<!-- review_stack_entry_start -->

[![Review Change Stack](https://storage.googleapis.com/coderabbit_public_assets/review-stack-in-coderabbit-ui.svg)](https://app.coderabbit.ai/change-stack/maximhq/bifrost/pull/3907?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack)

<!-- review_stack_entry_end -->

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
@akshaydeo akshaydeo mentioned this pull request May 30, 2026
akshaydeo added a commit that referenced this pull request May 30, 2026
* removes from_memory for APIs

* docker scout fixes (#3900)

* test fixes for hardened runners (#3780)

* fix: SGL provider - send Authorization header on streaming requests (#3307)

* [fix]: SGL provider - send Authorization header on streaming requests

The streaming entry points (ChatCompletionStream, TextCompletionStream)
passed nil for the authHeader parameter to the shared OpenAI streaming
helpers, so no Authorization header was attached to outbound streaming
requests. SGLang servers configured with --api-key always require the
header and returned 401 on streaming while non-streaming requests
worked. The non-streaming OpenAI helper takes the Key directly and
builds the header itself; the streaming helper requires the caller to
build it. Mirror the vLLM pattern (core/providers/vllm/vllm.go) and
construct the auth header from key.Value when set.

Affected packages:
- core/providers/sgl/sgl.go - build authHeader for both streaming paths
- core/providers/sgl/chat_test.go - regression tests asserting the
  Authorization header reaches the upstream on chat and text streams
- core/changelog.md - changelog entry

* [fix]: SGL streaming tests - cancel drain goroutine on test completion

The drain goroutines spawned to consume streamChan in
TestChatCompletionStream_SetsAuthorizationHeader and
TestTextCompletionStream_SetsAuthorizationHeader had no cancellation
path: if the streaming pipeline failed to close the channel (e.g. on a
test timeout), the goroutines would leak into the test process.

Replace the inline `go func() { for range streamChan {} }()` with a
shared drainStream helper that selects on both the channel and a `done`
channel closed via t.Cleanup, so the goroutine always exits when the
test completes regardless of channel state.

Addresses Greptile review feedback on PR #3307.

---------

Co-authored-by: Akshay Deo <akshay@akshaydeo.com>

* ollama streaming auth header (#3906)

## Summary

Adds Bearer token authentication support to the Ollama provider's streaming endpoints. Previously, the streaming methods for text completion and chat completion always passed `nil` for the auth header, meaning API keys configured for Ollama were silently ignored during streaming requests.

## Issues

Closes #3905

## Changes

- When a non-empty key value is present, a `Bearer` token `Authorization` header is now constructed and passed to the OpenAI-compatible streaming handlers for both `TextCompletionStream` and `ChatCompletionStream`
- If no key is configured, the auth header remains `nil`, preserving backward compatibility with unauthenticated local Ollama instances

## Type of change

- [x] Bug fix
- [ ] Feature
- [ ] Refactor
- [ ] Documentation
- [ ] Chore/CI

## Affected areas

- [ ] Core (Go)
- [ ] Transports (HTTP)
- [x] Providers/Integrations
- [ ] Plugins
- [ ] UI (React)
- [ ] Docs

## How to test

Configure an Ollama provider with an API key (e.g., when using a hosted or authenticated Ollama instance) and issue a streaming chat or text completion request. Verify the `Authorization: Bearer <key>` header is included in the outgoing request.

```sh
go test ./core/providers/ollama/...
```

## Breaking changes

- [ ] Yes
- [x] No

## Related issues

## Security considerations

API keys are now correctly forwarded as Bearer tokens in streaming requests to Ollama. Ensure keys are stored and retrieved securely via the existing key management mechanism, as they will now be included in outbound HTTP headers for streaming calls.

## 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

<!-- This is an auto-generated comment: release notes by coderabbit.ai -->

## Summary by CodeRabbit

* **Bug Fixes**
  * Ollama streaming requests now support authentication via bearer tokens for both text and chat completions, enabling proper token-based authentication when API keys are provided.

<!-- review_stack_entry_start -->

[![Review Change Stack](https://storage.googleapis.com/coderabbit_public_assets/review-stack-in-coderabbit-ui.svg)](https://app.coderabbit.ai/change-stack/maximhq/bifrost/pull/3906?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack)

<!-- review_stack_entry_end -->

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

* 1.5.7 changelogs (#3907)

This release (core v1.5.15, framework v1.3.15) fixes missing `Authorization` header forwarding on streaming requests for the Ollama and SGL providers, ensuring authenticated requests behave correctly during streaming.

- Ollama streaming text and chat completion requests now correctly forward the configured API key as an `Authorization: Bearer` header (#3906)
- SGL provider now sends the `Authorization` header on streaming requests (#3307) (thanks [@hensapir](https://github.com/hensapir)!)
- Governance and Logging APIs: removed the `from_memory` query parameter; virtual key and config list APIs now return consistent DB-backed results, with VK names batch-fetched in a single query (#3903)
- Bumped core to v1.5.15, framework to v1.3.15, transports to v1.5.7, and all dependent plugins to their respective patch versions

- [x] Bug fix
- [ ] Feature
- [ ] Refactor
- [ ] Documentation
- [ ] Chore/CI

- [x] Core (Go)
- [x] Transports (HTTP)
- [x] Providers/Integrations
- [x] Plugins
- [ ] UI (React)
- [ ] Docs

Validate that Ollama and SGL streaming requests include the `Authorization: Bearer` header when an API key is configured.

```sh
go version
go test ./...
```

Configure an Ollama or SGL provider with an API key and issue a streaming chat or text completion request. Inspect outbound request headers to confirm `Authorization: Bearer <key>` is present.

- [ ] Yes
- [x] No

Closes #3906
Closes #3307
Closes #3903

These fixes ensure that API keys configured for Ollama and SGL providers are correctly forwarded on streaming requests. Previously, the `Authorization` header was silently dropped on streaming paths, meaning requests could reach upstream providers without authentication credentials.

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

<!-- This is an auto-generated comment: release notes by coderabbit.ai -->

* **Bug Fixes**
  * Fixed authorization header handling for Ollama streaming requests.
  * Fixed authorization header forwarding for SGL provider streaming requests.
  * Improved consistency in virtual key and configuration list API responses by removing unnecessary query parameters.

* **Chores**
  * Updated component versions across the platform.

<!-- review_stack_entry_start -->

[![Review Change Stack](https://storage.googleapis.com/coderabbit_public_assets/review-stack-in-coderabbit-ui.svg)](https://app.coderabbit.ai/change-stack/maximhq/bifrost/pull/3907?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack)

<!-- review_stack_entry_end -->

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

* changelogs (#3909)

## Summary

Remediates Docker Scout CVE findings by upgrading transitive `golang.org/x` dependencies and removing the standalone GNU `wget` package from Alpine runtime images, replacing it with the built-in busybox `wget` applet.

## Changes

- Bumped `golang.org/x` transitive dependencies (`crypto`, `net`, `sys`, `text`, `term`) across all modules to clear 20 Docker Scout advisories (severity up to 10.0), verified clean with `govulncheck`
- Removed standalone `wget` package from Alpine runtime images in `Dockerfile` and `Dockerfile.local`, eliminating CVE-2025-69194 (CVSS 8.8)
- Updated `HEALTHCHECK` command from `wget --no-verbose --tries=1` to `wget -q` to use busybox-compatible flags with no functional change in behavior

## Type of change

- [ ] Bug fix
- [ ] Feature
- [ ] Refactor
- [ ] Documentation
- [x] Chore/CI

## Affected areas

- [x] Core (Go)
- [x] Transports (HTTP)
- [ ] Providers/Integrations
- [x] Plugins
- [ ] UI (React)
- [ ] Docs

## How to test

```sh
# Verify no vulnerabilities remain
govulncheck ./...

# Build Docker image and confirm wget healthcheck works
docker build -f transports/Dockerfile -t gateway-test .
docker run --rm gateway-test
```

## Breaking changes

- [ ] Yes
- [x] No

## Related issues

Closes #3900

## Security considerations

- Clears 20 Docker Scout CVE advisories on `golang.org/x` packages, with severities up to 10.0
- Removes CVE-2025-69194 (CVSS 8.8) by eliminating the standalone GNU `wget` package; busybox `wget` is used instead and is not affected by this CVE

## Checklist

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

---------

Co-authored-by: Hen Sapir <hen@sapir.me>
akshaydeo added a commit that referenced this pull request May 30, 2026
This release (core v1.5.15, framework v1.3.15) fixes missing `Authorization` header forwarding on streaming requests for the Ollama and SGL providers, ensuring authenticated requests behave correctly during streaming.

- Ollama streaming text and chat completion requests now correctly forward the configured API key as an `Authorization: Bearer` header (#3906)
- SGL provider now sends the `Authorization` header on streaming requests (#3307) (thanks [@hensapir](https://github.com/hensapir)!)
- Governance and Logging APIs: removed the `from_memory` query parameter; virtual key and config list APIs now return consistent DB-backed results, with VK names batch-fetched in a single query (#3903)
- Bumped core to v1.5.15, framework to v1.3.15, transports to v1.5.7, and all dependent plugins to their respective patch versions

- [x] Bug fix
- [ ] Feature
- [ ] Refactor
- [ ] Documentation
- [ ] Chore/CI

- [x] Core (Go)
- [x] Transports (HTTP)
- [x] Providers/Integrations
- [x] Plugins
- [ ] UI (React)
- [ ] Docs

Validate that Ollama and SGL streaming requests include the `Authorization: Bearer` header when an API key is configured.

```sh
go version
go test ./...
```

Configure an Ollama or SGL provider with an API key and issue a streaming chat or text completion request. Inspect outbound request headers to confirm `Authorization: Bearer <key>` is present.

- [ ] Yes
- [x] No

Closes #3906
Closes #3307
Closes #3903

These fixes ensure that API keys configured for Ollama and SGL providers are correctly forwarded on streaming requests. Previously, the `Authorization` header was silently dropped on streaming paths, meaning requests could reach upstream providers without authentication credentials.

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

<!-- This is an auto-generated comment: release notes by coderabbit.ai -->

* **Bug Fixes**
  * Fixed authorization header handling for Ollama streaming requests.
  * Fixed authorization header forwarding for SGL provider streaming requests.
  * Improved consistency in virtual key and configuration list API responses by removing unnecessary query parameters.

* **Chores**
  * Updated component versions across the platform.

<!-- review_stack_entry_start -->

[![Review Change Stack](https://storage.googleapis.com/coderabbit_public_assets/review-stack-in-coderabbit-ui.svg)](https://app.coderabbit.ai/change-stack/maximhq/bifrost/pull/3907?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack)

<!-- review_stack_entry_end -->

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
akshaydeo added a commit that referenced this pull request May 30, 2026
* docker scout fixes (#3900)

* 1.5.7 changelogs (#3907)

This release (core v1.5.15, framework v1.3.15) fixes missing `Authorization` header forwarding on streaming requests for the Ollama and SGL providers, ensuring authenticated requests behave correctly during streaming.

- Ollama streaming text and chat completion requests now correctly forward the configured API key as an `Authorization: Bearer` header (#3906)
- SGL provider now sends the `Authorization` header on streaming requests (#3307) (thanks [@hensapir](https://github.com/hensapir)!)
- Governance and Logging APIs: removed the `from_memory` query parameter; virtual key and config list APIs now return consistent DB-backed results, with VK names batch-fetched in a single query (#3903)
- Bumped core to v1.5.15, framework to v1.3.15, transports to v1.5.7, and all dependent plugins to their respective patch versions

- [x] Bug fix
- [ ] Feature
- [ ] Refactor
- [ ] Documentation
- [ ] Chore/CI

- [x] Core (Go)
- [x] Transports (HTTP)
- [x] Providers/Integrations
- [x] Plugins
- [ ] UI (React)
- [ ] Docs

Validate that Ollama and SGL streaming requests include the `Authorization: Bearer` header when an API key is configured.

```sh
go version
go test ./...
```

Configure an Ollama or SGL provider with an API key and issue a streaming chat or text completion request. Inspect outbound request headers to confirm `Authorization: Bearer <key>` is present.

- [ ] Yes
- [x] No

Closes #3906
Closes #3307
Closes #3903

These fixes ensure that API keys configured for Ollama and SGL providers are correctly forwarded on streaming requests. Previously, the `Authorization` header was silently dropped on streaming paths, meaning requests could reach upstream providers without authentication credentials.

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

<!-- This is an auto-generated comment: release notes by coderabbit.ai -->

* **Bug Fixes**
  * Fixed authorization header handling for Ollama streaming requests.
  * Fixed authorization header forwarding for SGL provider streaming requests.
  * Improved consistency in virtual key and configuration list API responses by removing unnecessary query parameters.

* **Chores**
  * Updated component versions across the platform.

<!-- review_stack_entry_start -->

[![Review Change Stack](https://storage.googleapis.com/coderabbit_public_assets/review-stack-in-coderabbit-ui.svg)](https://app.coderabbit.ai/change-stack/maximhq/bifrost/pull/3907?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack)

<!-- review_stack_entry_end -->

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

* changelogs (#3909)

## Summary

Remediates Docker Scout CVE findings by upgrading transitive `golang.org/x` dependencies and removing the standalone GNU `wget` package from Alpine runtime images, replacing it with the built-in busybox `wget` applet.

## Changes

- Bumped `golang.org/x` transitive dependencies (`crypto`, `net`, `sys`, `text`, `term`) across all modules to clear 20 Docker Scout advisories (severity up to 10.0), verified clean with `govulncheck`
- Removed standalone `wget` package from Alpine runtime images in `Dockerfile` and `Dockerfile.local`, eliminating CVE-2025-69194 (CVSS 8.8)
- Updated `HEALTHCHECK` command from `wget --no-verbose --tries=1` to `wget -q` to use busybox-compatible flags with no functional change in behavior

## Type of change

- [ ] Bug fix
- [ ] Feature
- [ ] Refactor
- [ ] Documentation
- [x] Chore/CI

## Affected areas

- [x] Core (Go)
- [x] Transports (HTTP)
- [ ] Providers/Integrations
- [x] Plugins
- [ ] UI (React)
- [ ] Docs

## How to test

```sh
# Verify no vulnerabilities remain
govulncheck ./...

# Build Docker image and confirm wget healthcheck works
docker build -f transports/Dockerfile -t gateway-test .
docker run --rm gateway-test
```

## Breaking changes

- [ ] Yes
- [x] No

## Related issues

Closes #3900

## Security considerations

- Clears 20 Docker Scout CVE advisories on `golang.org/x` packages, with severities up to 10.0
- Removes CVE-2025-69194 (CVSS 8.8) by eliminating the standalone GNU `wget` package; busybox `wget` is used instead and is not affected by this CVE

## Checklist

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

* enterprise changelog (#3912)

## Summary

Adds the Enterprise v1.4.6 changelog entry to the documentation site and registers it in the docs navigation.

## Changes

- Added `docs/changelogs/ent-v1.4.6.mdx` documenting the v1.4.6 release, which is a security and hardening release based on `transports/v1.5.7`. Key highlights include:
  - **DAC bypass fix**: `from_memory` query paths and shared filter-data caches were bypassing data-access scope enforcement, allowing scoped callers to observe virtual keys, teams, routing rules, and log dimensions belonging to other users. All read paths now apply the caller's DAC scope, and MCP clients no longer leak hidden virtual key IDs.
  - **DAC scope coverage expanded**: Added DAC wrappers for `GetVirtualKeys`, `GetRoutingRules`, `GetRoutingRulesByScope`, `GetRoutingRule`, and MCP virtual-key config lookups by client ID.
  - **DAC bypass regression suite**: New end-to-end Postman collection covering `from_memory` list endpoints, hidden virtual key/team detail access, log and MCP filter-data cache isolation, and MCP client assignment leakage.
  - **CVE remediation**: Updated `golang.org/x` packages (`crypto`, `net`, `sys`, `text`, `term`) clearing 20 advisories with severity up to 10.0, verified with `govulncheck`.
  - **Hardened container image**: Removed standalone GNU `wget` from the Alpine runtime image, eliminating CVE-2025-69194 (8.8); healthcheck now uses busybox `wget`.
  - **Ollama and SGL streaming auth fixes**: Both providers now correctly forward `Authorization: Bearer` headers on streaming requests.
  - **Governance model availability fix**: Access profile evaluation now correctly enforces model availability checks during budget constraint validation across managed and non-managed governance paths.
  - **Governance and Logging list API cleanup**: Removed the `from_memory` query parameter; list APIs now return consistent DB-backed results with batch-fetched virtual-key names.
- Registered `changelogs/ent-v1.4.6` as the first entry in the Enterprise changelogs section of `docs/docs.json`.

## Type of change

- [ ] Bug fix
- [ ] Feature
- [ ] Refactor
- [x] Documentation
- [ ] Chore/CI

## Affected areas

- [ ] Core (Go)
- [ ] Transports (HTTP)
- [ ] Providers/Integrations
- [ ] Plugins
- [ ] UI (React)
- [x] Docs

## How to test

Navigate to the Enterprise changelogs section of the documentation site and confirm that the v1.4.6 entry appears at the top of the list and renders correctly, including the breaking-change warning, feature/fix sections, and dependency tables.

## Breaking changes

- [x] Yes
- [ ] No

v1.4.0 introduced breaking changes. Upgraders should follow the [v1.4.0 Migration Guide](https://docs.example.com/enterprise/migration-guides/v1.4.0) before upgrading to v1.4.6.

## Security considerations

This release closes a DAC bypass that allowed scoped callers to read virtual keys, teams, routing rules, and log dimensions belonging to other users via `from_memory` query paths and shared filter-data caches. It also remediates 20 CVEs in `golang.org/x` dependencies (max severity 10.0) and removes a vulnerable `wget` binary (CVE-2025-69194, 8.8) from the container image.

## Checklist

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

<!-- This is an auto-generated comment: release notes by coderabbit.ai -->

## Summary by CodeRabbit

## Documentation

* Added Enterprise v1.4.6 release notes documenting a security-focused release with hardening improvements and critical updates.
* Updates include security remediation, governance and model validation enhancements, container image improvements, and authentication updates for supported streaming services.
* Removed deprecated parameter from governance and logging APIs.

<!-- review_stack_entry_start -->

[![Review Change Stack](https://storage.googleapis.com/coderabbit_public_assets/review-stack-in-coderabbit-ui.svg)](https://app.coderabbit.ai/change-stack/maximhq/bifrost/pull/3912?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack)

<!-- review_stack_entry_end -->

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
akshaydeo added a commit that referenced this pull request May 31, 2026
This release (core v1.5.15, framework v1.3.15) fixes missing `Authorization` header forwarding on streaming requests for the Ollama and SGL providers, ensuring authenticated requests behave correctly during streaming.

- Ollama streaming text and chat completion requests now correctly forward the configured API key as an `Authorization: Bearer` header (#3906)
- SGL provider now sends the `Authorization` header on streaming requests (#3307) (thanks [@hensapir](https://github.com/hensapir)!)
- Governance and Logging APIs: removed the `from_memory` query parameter; virtual key and config list APIs now return consistent DB-backed results, with VK names batch-fetched in a single query (#3903)
- Bumped core to v1.5.15, framework to v1.3.15, transports to v1.5.7, and all dependent plugins to their respective patch versions

- [x] Bug fix
- [ ] Feature
- [ ] Refactor
- [ ] Documentation
- [ ] Chore/CI

- [x] Core (Go)
- [x] Transports (HTTP)
- [x] Providers/Integrations
- [x] Plugins
- [ ] UI (React)
- [ ] Docs

Validate that Ollama and SGL streaming requests include the `Authorization: Bearer` header when an API key is configured.

```sh
go version
go test ./...
```

Configure an Ollama or SGL provider with an API key and issue a streaming chat or text completion request. Inspect outbound request headers to confirm `Authorization: Bearer <key>` is present.

- [ ] Yes
- [x] No

Closes #3906
Closes #3307
Closes #3903

These fixes ensure that API keys configured for Ollama and SGL providers are correctly forwarded on streaming requests. Previously, the `Authorization` header was silently dropped on streaming paths, meaning requests could reach upstream providers without authentication credentials.

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

<!-- This is an auto-generated comment: release notes by coderabbit.ai -->

* **Bug Fixes**
  * Fixed authorization header handling for Ollama streaming requests.
  * Fixed authorization header forwarding for SGL provider streaming requests.
  * Improved consistency in virtual key and configuration list API responses by removing unnecessary query parameters.

* **Chores**
  * Updated component versions across the platform.

<!-- review_stack_entry_start -->

[![Review Change Stack](https://storage.googleapis.com/coderabbit_public_assets/review-stack-in-coderabbit-ui.svg)](https://app.coderabbit.ai/change-stack/maximhq/bifrost/pull/3907?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack)

<!-- review_stack_entry_end -->

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Purvi09 pushed a commit to Purvi09/bifrost that referenced this pull request May 31, 2026
This release (core v1.5.15, framework v1.3.15) fixes missing `Authorization` header forwarding on streaming requests for the Ollama and SGL providers, ensuring authenticated requests behave correctly during streaming.

- Ollama streaming text and chat completion requests now correctly forward the configured API key as an `Authorization: Bearer` header (maximhq#3906)
- SGL provider now sends the `Authorization` header on streaming requests (maximhq#3307) (thanks [@hensapir](https://github.com/hensapir)!)
- Governance and Logging APIs: removed the `from_memory` query parameter; virtual key and config list APIs now return consistent DB-backed results, with VK names batch-fetched in a single query (maximhq#3903)
- Bumped core to v1.5.15, framework to v1.3.15, transports to v1.5.7, and all dependent plugins to their respective patch versions

- [x] Bug fix
- [ ] Feature
- [ ] Refactor
- [ ] Documentation
- [ ] Chore/CI

- [x] Core (Go)
- [x] Transports (HTTP)
- [x] Providers/Integrations
- [x] Plugins
- [ ] UI (React)
- [ ] Docs

Validate that Ollama and SGL streaming requests include the `Authorization: Bearer` header when an API key is configured.

```sh
go version
go test ./...
```

Configure an Ollama or SGL provider with an API key and issue a streaming chat or text completion request. Inspect outbound request headers to confirm `Authorization: Bearer <key>` is present.

- [ ] Yes
- [x] No

Closes maximhq#3906
Closes maximhq#3307
Closes maximhq#3903

These fixes ensure that API keys configured for Ollama and SGL providers are correctly forwarded on streaming requests. Previously, the `Authorization` header was silently dropped on streaming paths, meaning requests could reach upstream providers without authentication credentials.

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

<!-- This is an auto-generated comment: release notes by coderabbit.ai -->

* **Bug Fixes**
  * Fixed authorization header handling for Ollama streaming requests.
  * Fixed authorization header forwarding for SGL provider streaming requests.
  * Improved consistency in virtual key and configuration list API responses by removing unnecessary query parameters.

* **Chores**
  * Updated component versions across the platform.

<!-- review_stack_entry_start -->

[![Review Change Stack](https://storage.googleapis.com/coderabbit_public_assets/review-stack-in-coderabbit-ui.svg)](https://app.coderabbit.ai/change-stack/maximhq/bifrost/pull/3907?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack)

<!-- review_stack_entry_end -->

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
akshaydeo added a commit that referenced this pull request Jun 1, 2026
This release (core v1.5.15, framework v1.3.15) fixes missing `Authorization` header forwarding on streaming requests for the Ollama and SGL providers, ensuring authenticated requests behave correctly during streaming.

- Ollama streaming text and chat completion requests now correctly forward the configured API key as an `Authorization: Bearer` header (#3906)
- SGL provider now sends the `Authorization` header on streaming requests (#3307) (thanks [@hensapir](https://github.com/hensapir)!)
- Governance and Logging APIs: removed the `from_memory` query parameter; virtual key and config list APIs now return consistent DB-backed results, with VK names batch-fetched in a single query (#3903)
- Bumped core to v1.5.15, framework to v1.3.15, transports to v1.5.7, and all dependent plugins to their respective patch versions

- [x] Bug fix
- [ ] Feature
- [ ] Refactor
- [ ] Documentation
- [ ] Chore/CI

- [x] Core (Go)
- [x] Transports (HTTP)
- [x] Providers/Integrations
- [x] Plugins
- [ ] UI (React)
- [ ] Docs

Validate that Ollama and SGL streaming requests include the `Authorization: Bearer` header when an API key is configured.

```sh
go version
go test ./...
```

Configure an Ollama or SGL provider with an API key and issue a streaming chat or text completion request. Inspect outbound request headers to confirm `Authorization: Bearer <key>` is present.

- [ ] Yes
- [x] No

Closes #3906
Closes #3307
Closes #3903

These fixes ensure that API keys configured for Ollama and SGL providers are correctly forwarded on streaming requests. Previously, the `Authorization` header was silently dropped on streaming paths, meaning requests could reach upstream providers without authentication credentials.

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

<!-- This is an auto-generated comment: release notes by coderabbit.ai -->

* **Bug Fixes**
  * Fixed authorization header handling for Ollama streaming requests.
  * Fixed authorization header forwarding for SGL provider streaming requests.
  * Improved consistency in virtual key and configuration list API responses by removing unnecessary query parameters.

* **Chores**
  * Updated component versions across the platform.

<!-- review_stack_entry_start -->

[![Review Change Stack](https://storage.googleapis.com/coderabbit_public_assets/review-stack-in-coderabbit-ui.svg)](https://app.coderabbit.ai/change-stack/maximhq/bifrost/pull/3907?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack)

<!-- review_stack_entry_end -->

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
akshaydeo added a commit that referenced this pull request Jun 1, 2026
This release (core v1.5.15, framework v1.3.15) fixes missing `Authorization` header forwarding on streaming requests for the Ollama and SGL providers, ensuring authenticated requests behave correctly during streaming.

- Ollama streaming text and chat completion requests now correctly forward the configured API key as an `Authorization: Bearer` header (#3906)
- SGL provider now sends the `Authorization` header on streaming requests (#3307) (thanks [@hensapir](https://github.com/hensapir)!)
- Governance and Logging APIs: removed the `from_memory` query parameter; virtual key and config list APIs now return consistent DB-backed results, with VK names batch-fetched in a single query (#3903)
- Bumped core to v1.5.15, framework to v1.3.15, transports to v1.5.7, and all dependent plugins to their respective patch versions

- [x] Bug fix
- [ ] Feature
- [ ] Refactor
- [ ] Documentation
- [ ] Chore/CI

- [x] Core (Go)
- [x] Transports (HTTP)
- [x] Providers/Integrations
- [x] Plugins
- [ ] UI (React)
- [ ] Docs

Validate that Ollama and SGL streaming requests include the `Authorization: Bearer` header when an API key is configured.

```sh
go version
go test ./...
```

Configure an Ollama or SGL provider with an API key and issue a streaming chat or text completion request. Inspect outbound request headers to confirm `Authorization: Bearer <key>` is present.

- [ ] Yes
- [x] No

Closes #3906
Closes #3307
Closes #3903

These fixes ensure that API keys configured for Ollama and SGL providers are correctly forwarded on streaming requests. Previously, the `Authorization` header was silently dropped on streaming paths, meaning requests could reach upstream providers without authentication credentials.

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

<!-- This is an auto-generated comment: release notes by coderabbit.ai -->

* **Bug Fixes**
  * Fixed authorization header handling for Ollama streaming requests.
  * Fixed authorization header forwarding for SGL provider streaming requests.
  * Improved consistency in virtual key and configuration list API responses by removing unnecessary query parameters.

* **Chores**
  * Updated component versions across the platform.

<!-- review_stack_entry_start -->

[![Review Change Stack](https://storage.googleapis.com/coderabbit_public_assets/review-stack-in-coderabbit-ui.svg)](https://app.coderabbit.ai/change-stack/maximhq/bifrost/pull/3907?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack)

<!-- review_stack_entry_end -->

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Purvi09 pushed a commit to Purvi09/bifrost that referenced this pull request Jun 2, 2026
This release (core v1.5.15, framework v1.3.15) fixes missing `Authorization` header forwarding on streaming requests for the Ollama and SGL providers, ensuring authenticated requests behave correctly during streaming.

- Ollama streaming text and chat completion requests now correctly forward the configured API key as an `Authorization: Bearer` header (maximhq#3906)
- SGL provider now sends the `Authorization` header on streaming requests (maximhq#3307) (thanks [@hensapir](https://github.com/hensapir)!)
- Governance and Logging APIs: removed the `from_memory` query parameter; virtual key and config list APIs now return consistent DB-backed results, with VK names batch-fetched in a single query (maximhq#3903)
- Bumped core to v1.5.15, framework to v1.3.15, transports to v1.5.7, and all dependent plugins to their respective patch versions

- [x] Bug fix
- [ ] Feature
- [ ] Refactor
- [ ] Documentation
- [ ] Chore/CI

- [x] Core (Go)
- [x] Transports (HTTP)
- [x] Providers/Integrations
- [x] Plugins
- [ ] UI (React)
- [ ] Docs

Validate that Ollama and SGL streaming requests include the `Authorization: Bearer` header when an API key is configured.

```sh
go version
go test ./...
```

Configure an Ollama or SGL provider with an API key and issue a streaming chat or text completion request. Inspect outbound request headers to confirm `Authorization: Bearer <key>` is present.

- [ ] Yes
- [x] No

Closes maximhq#3906
Closes maximhq#3307
Closes maximhq#3903

These fixes ensure that API keys configured for Ollama and SGL providers are correctly forwarded on streaming requests. Previously, the `Authorization` header was silently dropped on streaming paths, meaning requests could reach upstream providers without authentication credentials.

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

<!-- This is an auto-generated comment: release notes by coderabbit.ai -->

* **Bug Fixes**
  * Fixed authorization header handling for Ollama streaming requests.
  * Fixed authorization header forwarding for SGL provider streaming requests.
  * Improved consistency in virtual key and configuration list API responses by removing unnecessary query parameters.

* **Chores**
  * Updated component versions across the platform.

<!-- review_stack_entry_start -->

[![Review Change Stack](https://storage.googleapis.com/coderabbit_public_assets/review-stack-in-coderabbit-ui.svg)](https://app.coderabbit.ai/change-stack/maximhq/bifrost/pull/3907?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack)

<!-- review_stack_entry_end -->

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
@akshaydeo akshaydeo mentioned this pull request Jun 7, 2026
17 tasks
@coderabbitai coderabbitai Bot mentioned this pull request Jul 1, 2026
9 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants