maximhq · akshaydeo · Mar 31, 2026 · Mar 31, 2026 · greptile-apps · Mar 31, 2026
@@ -453,10 +453,10 @@ VALUES (1, 'migration-test-hash-abc123def456', $now, $now)
 ON CONFLICT DO NOTHING;
 
 -- governance_budgets (reset_duration is a string like "1d", "1h", etc.)
-INSERT INTO governance_budgets (id, max_limit, current_usage, reset_duration, last_reset, config_hash, created_at, updated_at)
-VALUES 
-  ('budget-migration-test-1', 1000.00, 100.00, '1d', $now, 'budget-hash-001', $now, $now),
-  ('budget-migration-test-2', 5000.00, 250.00, '7d', $now, 'budget-hash-002', $now, $now)
+INSERT INTO governance_budgets (id, max_limit, current_usage, reset_duration, last_reset, config_hash, created_at, updated_at, calendar_aligned)
+VALUES
+  ('budget-migration-test-1', 1000.00, 100.00, '1d', $now, 'budget-hash-001', $now, $now, 0),
+  ('budget-migration-test-2', 5000.00, 250.00, '7d', $now, 'budget-hash-002', $now, $now, 1)
-  ('budget-migration-test-1', 1000.00, 100.00, '1d', $now, 'budget-hash-001', $now, $now, 0),
-  ('budget-migration-test-2', 5000.00, 250.00, '7d', $now, 'budget-hash-002', $now, $now, 1)
+  ('budget-migration-test-1', 1000.00, 100.00, '1d', $now, 'budget-hash-001', $now, $now, false),
+  ('budget-migration-test-2', 5000.00, 250.00, '7d', $now, 'budget-hash-002', $now, $now, true)
-  ('budget-migration-test-1', 1000.00, 100.00, '1d', $now, 'budget-hash-001', $now, $now, 0),
-  ('budget-migration-test-2', 5000.00, 250.00, '7d', $now, 'budget-hash-002', $now, $now, 1)
+  ('budget-migration-test-1', 1000.00, 100.00, '1d', $now, 'budget-hash-001', $now, $now, false),
+  ('budget-migration-test-2', 5000.00, 250.00, '7d', $now, 'budget-hash-002', $now, $now, true)
 ON CONFLICT DO NOTHING;
 
 -- governance_rate_limits (flexible duration format with token_* and request_* columns)

diff --git a/core/changelog.md b/core/changelog.md
@@ -0,0 +1,4 @@
+- fix: fixed timeout status code handling across all providers
+- fix: preserve cached provider metadata on cross-provider cache hits
+- fix: prevent reasoning text from leaking into Gemini response content
+- feat: added Anthropic beta headers support
diff --git a/core/version b/core/version
@@ -1 +1 @@
-1.4.15
+1.4.16
diff --git a/docs/media/aws-bedrock-anthropic-beta-headers.png b/docs/media/aws-bedrock-anthropic-beta-headers.png
diff --git a/docs/media/azure-setting-anthropic-beta-headers.png b/docs/media/azure-setting-anthropic-beta-headers.png
diff --git a/docs/media/vertex-ai-setting-anthropic-beta-headers.png b/docs/media/vertex-ai-setting-anthropic-beta-headers.png
diff --git a/docs/providers/supported-providers/azure.mdx b/docs/providers/supported-providers/azure.mdx
@@ -39,14 +39,18 @@ Azure is a cloud provider offering access to OpenAI and Anthropic models through
 
 ## Beta Headers
 
-For Anthropic models on Azure, Bifrost validates `anthropic-beta` headers. Azure supports most Anthropic beta features.
+For Anthropic models on Azure, Bifrost validates `anthropic-beta` headers and drops unsupported headers from the request. Azure supports most Anthropic beta features.
 
 **Supported**: `computer-use-*`, `structured-outputs-*`, `advanced-tool-use-*`, `mcp-client-*`, `prompt-caching-scope-*`, `compact-*`, `context-management-*`, `files-api-*`, `interleaved-thinking-*`, `skills-*`, `context-1m-*`, `redact-thinking-*`
 
 **Not supported**: `fast-mode-*`
 
 You can override these defaults per provider via the **Beta Headers** tab in provider configuration or via [`beta_header_overrides`](/quickstart/gateway/provider-configuration#beta-header-overrides). See the full support matrix in the [Anthropic provider docs](/providers/supported-providers/anthropic#beta-headers).
 
+<Frame>
+  <img src="/media/azure-setting-anthropic-beta-headers.png" alt="Azure Beta Headers configuration tab showing supported and unsupported Anthropic beta features with override options" />
+</Frame>
+
 ---
 
 # 1. Chat Completions

diff --git a/docs/providers/supported-providers/bedrock.mdx b/docs/providers/supported-providers/bedrock.mdx
@@ -53,14 +53,19 @@ AWS Bedrock supports multiple model families (Claude, Nova, Mistral, Llama, Cohe
 
 ## Beta Headers
 
-For Claude models on Bedrock, Bifrost validates `anthropic-beta` headers to ensure only supported features are forwarded.
+For Claude models on Bedrock, Bifrost validates `anthropic-beta` headers and drops unsupported headers from the request.
 
 **Supported**: `computer-use-*`, `structured-outputs-*`, `compact-*`, `context-management-*`, `interleaved-thinking-*`, `context-1m-*`
 
 **Not supported**: `advanced-tool-use-*`, `mcp-client-*`, `prompt-caching-scope-*`, `files-api-*`, `skills-*`, `fast-mode-*`, `redact-thinking-*`
 
 You can override these defaults per provider via the **Beta Headers** tab in provider configuration or via [`beta_header_overrides`](/quickstart/gateway/provider-configuration#beta-header-overrides). See the full support matrix in the [Anthropic provider docs](/providers/supported-providers/anthropic#beta-headers).
 
+
+<Frame>
+        <img src="/media/aws-bedrock-anthropic-beta-headers.png" alt="AWS bedrock Beta Headers configuration tab showing supported and unsupported Anthropic beta features with override options" />
+</Frame>
+
 ---
 
 # 1. Chat Completions

diff --git a/docs/providers/supported-providers/vertex.mdx b/docs/providers/supported-providers/vertex.mdx
@@ -41,14 +41,18 @@ Vertex AI is Google's unified ML platform providing access to Google's Gemini mo
 
 ## Beta Headers
 
-For Anthropic models on Vertex AI, Bifrost validates `anthropic-beta` headers to ensure only supported features are forwarded. Unsupported headers are rejected with a clear error.
+For Anthropic models on Vertex AI, Bifrost validates `anthropic-beta` headers and drops unsupported headers from the request.
 
 **Supported**: `computer-use-*`, `compact-*`, `context-management-*`, `interleaved-thinking-*`, `context-1m-*`
 
 **Not supported**: `structured-outputs-*`, `advanced-tool-use-*`, `mcp-client-*`, `prompt-caching-scope-*`, `files-api-*`, `skills-*`, `fast-mode-*`, `redact-thinking-*`
 
 You can override these defaults per provider via the **Beta Headers** tab in provider configuration or via [`beta_header_overrides`](/quickstart/gateway/provider-configuration#beta-header-overrides). See the full support matrix in the [Anthropic provider docs](/providers/supported-providers/anthropic#beta-headers).
 
+<Frame>
+  <img src="/media/vertex-ai-setting-anthropic-beta-headers.png" alt="Vertex AI Beta Headers configuration tab showing supported and unsupported Anthropic beta features with override options" />
+</Frame>
+
 ---
 
 # 1. Chat Completions

diff --git a/framework/changelog.md b/framework/changelog.md
@@ -0,0 +1,3 @@
+- feat: added /api/models/details endpoint with model capability metadata
+- fix: populate customer virtual_keys in governance APIs
+- fix: enterprise model catalog sync improvements
diff --git a/framework/version b/framework/version
@@ -1 +1 @@
-1.2.34
+1.2.35
diff --git a/plugins/governance/changelog.md b/plugins/governance/changelog.md
@@ -0,0 +1 @@
+- fix: populate customer virtual_keys in governance APIs
diff --git a/plugins/governance/version b/plugins/governance/version
@@ -1 +1 @@
-1.4.34
+1.4.35
diff --git a/plugins/jsonparser/changelog.md b/plugins/jsonparser/changelog.md
@@ -0,0 +1 @@
+- chore: upgraded core to v1.4.16 and framework to v1.2.35
diff --git a/plugins/jsonparser/version b/plugins/jsonparser/version
@@ -1 +1 @@
-1.4.33
+1.4.34
diff --git a/plugins/litellmcompat/changelog.md b/plugins/litellmcompat/changelog.md
@@ -0,0 +1 @@
+- chore: upgraded core to v1.4.16 and framework to v1.2.35
diff --git a/plugins/litellmcompat/version b/plugins/litellmcompat/version
@@ -1 +1 @@
-0.0.23
+0.0.24
diff --git a/plugins/logging/changelog.md b/plugins/logging/changelog.md
@@ -0,0 +1 @@
+- chore: upgraded core to v1.4.16 and framework to v1.2.35
diff --git a/plugins/logging/version b/plugins/logging/version
@@ -1 +1 @@
-1.4.34
+1.4.35
diff --git a/plugins/maxim/changelog.md b/plugins/maxim/changelog.md
@@ -0,0 +1 @@
+- chore: upgraded core to v1.4.16 and framework to v1.2.35
diff --git a/plugins/maxim/version b/plugins/maxim/version
@@ -1 +1 @@
-1.5.33
+1.5.34
diff --git a/plugins/mocker/changelog.md b/plugins/mocker/changelog.md
@@ -0,0 +1 @@
+- chore: upgraded core to v1.4.16 and framework to v1.2.35
diff --git a/plugins/mocker/version b/plugins/mocker/version
@@ -1 +1 @@
-1.4.33
+1.4.34
diff --git a/plugins/otel/changelog.md b/plugins/otel/changelog.md
@@ -0,0 +1 @@
+- chore: upgraded core to v1.4.16 and framework to v1.2.35
diff --git a/plugins/otel/version b/plugins/otel/version
@@ -1 +1 @@
-1.1.33
+1.1.34
diff --git a/plugins/semanticcache/changelog.md b/plugins/semanticcache/changelog.md
@@ -0,0 +1 @@
+- fix: preserve cached provider metadata on cross-provider cache hits
diff --git a/plugins/semanticcache/version b/plugins/semanticcache/version
@@ -1 +1 @@
-1.4.32
+1.4.33
diff --git a/plugins/telemetry/changelog.md b/plugins/telemetry/changelog.md
@@ -0,0 +1 @@
+- chore: upgraded core to v1.4.16 and framework to v1.2.35
diff --git a/plugins/telemetry/version b/plugins/telemetry/version
@@ -1 +1 @@
-1.4.34
+1.4.35
diff --git a/transports/changelog.md b/transports/changelog.md
@@ -0,0 +1,19 @@
+## ✨ Features
+
+- **Model Details API** — Added /api/models/details endpoint for model capability metadata
+- **Anthropic Beta Headers** — Support for Anthropic beta feature headers in requests
+
+## 🐞 Fixed
+
+- **Reasoning Content Leak** — Prevented reasoning text from leaking into Gemini response content
+- **Timeout Status Code** — Fixed timeout status code handling across all providers
+- **Cross-Provider Cache** — Preserved cached provider metadata on cross-provider cache hits
+- **Governance Virtual Keys** — Populated customer virtual_keys in governance APIs
+- **List Models Integration** — Removed default provider override on list models request in integrations
+- **Client Settings Headers** — Fixed Client settings UI to accept * as allowed headers
+
+## 🔧 Maintenance
+
+- **FIPS Docker Image** — Switched to FIPS-compliant base image for Docker builds
+- **Security Hardening** — Applied StepSecurity best practices to CI/CD pipeline (thanks [@step-security-bot](https://github.com/step-security-bot)!)
+- **Snyk Fixes** — Addressed Snyk vulnerability findings in Docker configuration
diff --git a/transports/version b/transports/version
@@ -1 +1 @@
-1.4.18
+1.4.19
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		- fix: populate customer virtual_keys in governance APIs
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		- chore: upgraded core to v1.4.16 and framework to v1.2.35
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		- fix: preserve cached provider metadata on cross-provider cache hits