diff --git a/.github/workflows/test-unit-core-utils.yml b/.github/workflows/test-unit-core-utils.yml
deleted file mode 100644
index a01f09559c6..00000000000
--- a/.github/workflows/test-unit-core-utils.yml
+++ /dev/null
@@ -1,31 +0,0 @@
-name: "Unit Tests: Core Utilities"
-
-on:
-  pull_request:
-    branches:
-      - main
-      - litellm_internal_staging
-      - litellm_oss_staging
-      - "litellm_**"
-  push:
-    branches:
-      - main
-      - litellm_internal_staging
-
-permissions:
-  contents: read
-  id-token: write
-  pull-requests: write
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}
-  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
-
-jobs:
-  core-utils:
-    uses: ./.github/workflows/_test-unit-base.yml
-    with:
-      test-path: "tests/test_litellm/litellm_core_utils"
-      workers: 2
-      reruns: 1
-      artifact-name: core-utils
diff --git a/.github/workflows/test-unit-enterprise-routing.yml b/.github/workflows/test-unit-enterprise-routing.yml
deleted file mode 100644
index a64f00f4744..00000000000
--- a/.github/workflows/test-unit-enterprise-routing.yml
+++ /dev/null
@@ -1,35 +0,0 @@
-name: "Unit Tests: Enterprise, Google GenAI & Routing"
-
-on:
-  pull_request:
-    branches:
-      - main
-      - litellm_internal_staging
-      - litellm_oss_staging
-      - "litellm_**"
-  push:
-    branches:
-      - main
-      - litellm_internal_staging
-
-permissions:
-  contents: read
-  id-token: write
-  pull-requests: write
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}
-  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
-
-jobs:
-  enterprise-routing:
-    uses: ./.github/workflows/_test-unit-base.yml
-    with:
-      test-path: >-
-        tests/test_litellm/enterprise
-        tests/test_litellm/google_genai
-        tests/test_litellm/router_utils
-        tests/test_litellm/router_strategy
-      workers: 2
-      reruns: 2
-      artifact-name: enterprise-routing
diff --git a/.github/workflows/test-unit-integrations.yml b/.github/workflows/test-unit-integrations.yml
deleted file mode 100644
index 39752cf8e5d..00000000000
--- a/.github/workflows/test-unit-integrations.yml
+++ /dev/null
@@ -1,31 +0,0 @@
-name: "Unit Tests: Integrations (Callbacks & Logging)"
-
-on:
-  pull_request:
-    branches:
-      - main
-      - litellm_internal_staging
-      - litellm_oss_staging
-      - "litellm_**"
-  push:
-    branches:
-      - main
-      - litellm_internal_staging
-
-permissions:
-  contents: read
-  id-token: write
-  pull-requests: write
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}
-  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
-
-jobs:
-  integrations:
-    uses: ./.github/workflows/_test-unit-base.yml
-    with:
-      test-path: "tests/test_litellm/integrations"
-      workers: 2
-      reruns: 3
-      artifact-name: integrations
diff --git a/.github/workflows/test-unit-llm-providers.yml b/.github/workflows/test-unit-llm-providers.yml
deleted file mode 100644
index 4d1c921f723..00000000000
--- a/.github/workflows/test-unit-llm-providers.yml
+++ /dev/null
@@ -1,47 +0,0 @@
-name: "Unit Tests: LLM Provider Transformations"
-
-on:
-  pull_request:
-    branches:
-      - main
-      - litellm_internal_staging
-      - litellm_oss_staging
-      - "litellm_**"
-  push:
-    branches:
-      - main
-      - litellm_internal_staging
-
-permissions:
-  contents: read
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}
-  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
-
-jobs:
-  vertex-ai:
-    name: Vertex AI
-    permissions:
-      contents: read
-      id-token: write
-      pull-requests: write
-    uses: ./.github/workflows/_test-unit-base.yml
-    with:
-      test-path: "tests/test_litellm/llms/vertex_ai"
-      workers: 1
-      reruns: 2
-      artifact-name: llm-vertex-ai
-
-  other-providers:
-    name: All Other Providers
-    permissions:
-      contents: read
-      id-token: write
-      pull-requests: write
-    uses: ./.github/workflows/_test-unit-base.yml
-    with:
-      test-path: "tests/test_litellm/llms --ignore=tests/test_litellm/llms/vertex_ai"
-      workers: 2
-      reruns: 2
-      artifact-name: llm-other-providers
diff --git a/.github/workflows/test-unit-misc.yml b/.github/workflows/test-unit-misc.yml
deleted file mode 100644
index 123a31e23f7..00000000000
--- a/.github/workflows/test-unit-misc.yml
+++ /dev/null
@@ -1,53 +0,0 @@
-name: "Unit Tests: MCP, Secrets, Containers & Misc"
-
-on:
-  pull_request:
-    branches:
-      - main
-      - litellm_internal_staging
-      - litellm_oss_staging
-      - "litellm_**"
-  push:
-    branches:
-      - main
-      - litellm_internal_staging
-
-permissions:
-  contents: read
-  id-token: write
-  pull-requests: write
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}
-  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
-
-jobs:
-  misc:
-    uses: ./.github/workflows/_test-unit-base.yml
-    with:
-      test-path: >-
-        tests/test_litellm/batches
-        tests/test_litellm/secret_managers
-        tests/test_litellm/a2a_protocol
-        tests/test_litellm/anthropic_interface
-        tests/test_litellm/completion_extras
-        tests/test_litellm/compression
-        tests/test_litellm/containers
-        tests/test_litellm/experimental_mcp_client
-        tests/test_litellm/models
-        tests/test_litellm/repositories
-        tests/test_litellm/images
-        tests/test_litellm/interactions
-        tests/test_litellm/ocr
-        tests/test_litellm/passthrough
-        tests/test_litellm/rag
-        tests/test_litellm/realtime_api
-        tests/test_litellm/rerank_api
-        tests/test_litellm/sandbox
-        tests/test_litellm/test_router
-        tests/test_litellm/vector_stores
-        tests/test_litellm/videos
-        tests/test_litellm/test_*.py
-      workers: 2
-      reruns: 2
-      artifact-name: misc
diff --git a/.github/workflows/test-unit-proxy-auth.yml b/.github/workflows/test-unit-proxy-auth.yml
deleted file mode 100644
index c27fe16d611..00000000000
--- a/.github/workflows/test-unit-proxy-auth.yml
+++ /dev/null
@@ -1,31 +0,0 @@
-name: "Unit Tests: Proxy Auth & Key Management"
-
-on:
-  pull_request:
-    branches:
-      - main
-      - litellm_internal_staging
-      - litellm_oss_staging
-      - "litellm_**"
-  push:
-    branches:
-      - main
-      - litellm_internal_staging
-
-permissions:
-  contents: read
-  id-token: write
-  pull-requests: write
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}
-  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
-
-jobs:
-  proxy-auth:
-    uses: ./.github/workflows/_test-unit-base.yml
-    with:
-      test-path: "tests/test_litellm/proxy/auth tests/test_litellm/proxy/hooks tests/test_litellm/proxy/policy_engine tests/test_litellm/proxy/client"
-      workers: 2
-      reruns: 2
-      artifact-name: proxy-auth
diff --git a/.github/workflows/test-unit-proxy-endpoints.yml b/.github/workflows/test-unit-proxy-endpoints.yml
deleted file mode 100644
index 3d1d0fcd6c3..00000000000
--- a/.github/workflows/test-unit-proxy-endpoints.yml
+++ /dev/null
@@ -1,81 +0,0 @@
-name: "Unit Tests: Proxy API Endpoints"
-
-on:
-  pull_request:
-    branches:
-      - main
-      - litellm_internal_staging
-      - litellm_oss_staging
-      - "litellm_**"
-  push:
-    branches:
-      - main
-      - litellm_internal_staging
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}
-  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
-
-jobs:
-  proxy-endpoints:
-    permissions:
-      contents: read
-      id-token: write
-      pull-requests: write
-    uses: ./.github/workflows/_test-unit-base.yml
-    with:
-      test-path: >-
-        tests/test_litellm/proxy/analytics_endpoints
-        tests/test_litellm/proxy/management_endpoints
-        tests/test_litellm/proxy/memory
-        tests/test_litellm/proxy/guardrails
-        tests/test_litellm/proxy/management_helpers
-        tests/test_litellm/proxy/anthropic_endpoints
-        tests/test_litellm/proxy/google_endpoints
-        tests/test_litellm/proxy/openai_files_endpoint
-        tests/test_litellm/proxy/batches_endpoints
-        tests/test_litellm/proxy/fine_tuning_endpoints
-        tests/test_litellm/proxy/vector_store_files_endpoints
-        tests/test_litellm/proxy/video_endpoints
-        tests/test_litellm/proxy/response_api_endpoints
-        tests/test_litellm/proxy/image_endpoints
-        tests/test_litellm/proxy/ocr_endpoints
-        tests/test_litellm/proxy/vector_store_endpoints
-        tests/test_litellm/proxy/agent_endpoints
-        tests/test_litellm/proxy/a2a
-        tests/test_litellm/proxy/credential_endpoints
-        tests/test_litellm/proxy/discovery_endpoints
-        tests/test_litellm/proxy/health_endpoints
-        tests/test_litellm/proxy/shutdown
-        tests/test_litellm/proxy/public_endpoints
-        tests/test_litellm/proxy/prompts
-        tests/test_litellm/proxy/rag_endpoints
-        tests/test_litellm/proxy/realtime_endpoints
-        tests/test_litellm/proxy/ui_crud_endpoints
-        tests/test_litellm/proxy/config_resolvers
-        tests/test_litellm/proxy/utils
-      workers: 2
-      reruns: 2
-      artifact-name: proxy-endpoints
-
-  # Behavior-pinning tests for litellm/proxy/proxy_server.py. Owns its
-  # own job (not a path on the proxy-endpoints job above) so its budget
-  # is independent and its coverage artifact is uploaded separately.
-  # See: https://www.notion.so/36c43b8acdab81ee845fd5365128a2fc
-  proxy-server:
-    permissions:
-      contents: read
-      id-token: write
-      pull-requests: write
-    uses: ./.github/workflows/_test-unit-base.yml
-    with:
-      test-path: tests/test_litellm/proxy/proxy_server
-      workers: 4
-      reruns: 2
-      timeout-minutes: 60
-      job-timeout-minutes: 95
-      artifact-name: proxy-server
diff --git a/.github/workflows/test-unit-proxy-infra.yml b/.github/workflows/test-unit-proxy-infra.yml
deleted file mode 100644
index 83d95463cdf..00000000000
--- a/.github/workflows/test-unit-proxy-infra.yml
+++ /dev/null
@@ -1,42 +0,0 @@
-name: "Unit Tests: Proxy Infrastructure"
-
-on:
-  pull_request:
-    branches:
-      - main
-      - litellm_internal_staging
-      - litellm_oss_staging
-      - "litellm_**"
-  push:
-    branches:
-      - main
-      - litellm_internal_staging
-
-permissions:
-  contents: read
-  id-token: write
-  pull-requests: write
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}
-  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
-
-jobs:
-  proxy-infra:
-    uses: ./.github/workflows/_test-unit-base.yml
-    with:
-      test-path: >-
-        tests/test_litellm/proxy/db
-        tests/test_litellm/proxy/middleware
-        tests/test_litellm/proxy/spend_tracking
-        tests/test_litellm/proxy/pass_through_endpoints
-        tests/test_litellm/proxy/_experimental
-        tests/test_litellm/proxy/experimental
-        tests/test_litellm/proxy/common_utils
-        tests/test_litellm/proxy/enterprise_billing
-        tests/test_litellm/proxy/types_utils
-        tests/test_litellm/proxy/logging_endpoints
-        tests/test_litellm/proxy/test_*.py
-      workers: 2
-      reruns: 2
-      artifact-name: proxy-infra
diff --git a/.github/workflows/test-unit-responses-caching-types.yml b/.github/workflows/test-unit-responses-caching-types.yml
deleted file mode 100644
index 5b336452069..00000000000
--- a/.github/workflows/test-unit-responses-caching-types.yml
+++ /dev/null
@@ -1,31 +0,0 @@
-name: "Unit Tests: Responses, Caching & Types"
-
-on:
-  pull_request:
-    branches:
-      - main
-      - litellm_internal_staging
-      - litellm_oss_staging
-      - "litellm_**"
-  push:
-    branches:
-      - main
-      - litellm_internal_staging
-
-permissions:
-  contents: read
-  id-token: write
-  pull-requests: write
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}
-  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
-
-jobs:
-  responses-caching-types:
-    uses: ./.github/workflows/_test-unit-base.yml
-    with:
-      test-path: "tests/test_litellm/responses tests/test_litellm/caching tests/test_litellm/types"
-      workers: 2
-      reruns: 2
-      artifact-name: responses-caching-types
diff --git a/.github/workflows/test-unit.yml b/.github/workflows/test-unit.yml
new file mode 100644
index 00000000000..fbba9969c28
--- /dev/null
+++ b/.github/workflows/test-unit.yml
@@ -0,0 +1,219 @@
+name: "Unit Tests"
+
+on:
+  pull_request:
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_staging
+      - "litellm_**"
+  push:
+    branches:
+      - main
+      - litellm_internal_staging
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}
+  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
+
+# One caller for every tests/test_litellm shard, replacing the nine thin workflow
+# files that each wrapped a single call to _test-unit-base.yml. Adding a shard is
+# now one matrix entry rather than a new file.
+#
+# `name` is the shard id and nothing else, so each check reports as
+# "<shard> / Run tests" exactly as it did when the shard had its own file. Those
+# strings are the branch ruleset's required contexts, so they are load-bearing:
+# renaming an entry renames a required check and the ruleset stops matching it.
+#
+# Every entry states its timeouts even when they equal the base workflow's
+# defaults. An absent matrix key renders as an empty string, which is not a
+# number, so a partially-specified entry would fail the call rather than fall
+# back to the default.
+#
+# tests/proxy_unit_tests keeps its own caller (test-unit-proxy-db.yml): it is
+# already a matrix and carries a shard-coverage guard that reads that file by
+# name. Folding it in here is a follow-up, together with generalising that guard
+# into assert_ci_coverage.py.
+jobs:
+  unit:
+    name: ${{ matrix.shard }}
+    permissions:
+      contents: read
+      id-token: write
+      pull-requests: write
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - shard: core-utils
+            artifact-name: core-utils
+            test-path: "tests/test_litellm/litellm_core_utils"
+            workers: 2
+            reruns: 1
+            timeout-minutes: 20
+            job-timeout-minutes: 55
+
+          - shard: enterprise-routing
+            artifact-name: enterprise-routing
+            test-path: >-
+              tests/test_litellm/enterprise
+              tests/test_litellm/google_genai
+              tests/test_litellm/router_utils
+              tests/test_litellm/router_strategy
+            workers: 2
+            reruns: 2
+            timeout-minutes: 20
+            job-timeout-minutes: 55
+
+          - shard: integrations
+            artifact-name: integrations
+            test-path: "tests/test_litellm/integrations"
+            workers: 2
+            reruns: 3
+            timeout-minutes: 20
+            job-timeout-minutes: 55
+
+          - shard: Vertex AI
+            artifact-name: llm-vertex-ai
+            test-path: "tests/test_litellm/llms/vertex_ai"
+            workers: 1
+            reruns: 2
+            timeout-minutes: 20
+            job-timeout-minutes: 55
+
+          - shard: All Other Providers
+            artifact-name: llm-other-providers
+            test-path: "tests/test_litellm/llms --ignore=tests/test_litellm/llms/vertex_ai"
+            workers: 2
+            reruns: 2
+            timeout-minutes: 20
+            job-timeout-minutes: 55
+
+          - shard: misc
+            artifact-name: misc
+            test-path: >-
+              tests/test_litellm/batches
+              tests/test_litellm/secret_managers
+              tests/test_litellm/a2a_protocol
+              tests/test_litellm/anthropic_interface
+              tests/test_litellm/completion_extras
+              tests/test_litellm/compression
+              tests/test_litellm/containers
+              tests/test_litellm/experimental_mcp_client
+              tests/test_litellm/models
+              tests/test_litellm/repositories
+              tests/test_litellm/images
+              tests/test_litellm/interactions
+              tests/test_litellm/ocr
+              tests/test_litellm/passthrough
+              tests/test_litellm/rag
+              tests/test_litellm/realtime_api
+              tests/test_litellm/rerank_api
+              tests/test_litellm/sandbox
+              tests/test_litellm/test_router
+              tests/test_litellm/vector_stores
+              tests/test_litellm/videos
+              tests/test_litellm/test_*.py
+            workers: 2
+            reruns: 2
+            timeout-minutes: 20
+            job-timeout-minutes: 55
+
+          - shard: proxy-auth
+            artifact-name: proxy-auth
+            test-path: >-
+              tests/test_litellm/proxy/auth
+              tests/test_litellm/proxy/hooks
+              tests/test_litellm/proxy/policy_engine
+              tests/test_litellm/proxy/client
+            workers: 2
+            reruns: 2
+            timeout-minutes: 20
+            job-timeout-minutes: 55
+
+          - shard: proxy-endpoints
+            artifact-name: proxy-endpoints
+            test-path: >-
+              tests/test_litellm/proxy/analytics_endpoints
+              tests/test_litellm/proxy/management_endpoints
+              tests/test_litellm/proxy/memory
+              tests/test_litellm/proxy/guardrails
+              tests/test_litellm/proxy/management_helpers
+              tests/test_litellm/proxy/anthropic_endpoints
+              tests/test_litellm/proxy/google_endpoints
+              tests/test_litellm/proxy/openai_files_endpoint
+              tests/test_litellm/proxy/batches_endpoints
+              tests/test_litellm/proxy/fine_tuning_endpoints
+              tests/test_litellm/proxy/vector_store_files_endpoints
+              tests/test_litellm/proxy/video_endpoints
+              tests/test_litellm/proxy/response_api_endpoints
+              tests/test_litellm/proxy/image_endpoints
+              tests/test_litellm/proxy/ocr_endpoints
+              tests/test_litellm/proxy/vector_store_endpoints
+              tests/test_litellm/proxy/agent_endpoints
+              tests/test_litellm/proxy/a2a
+              tests/test_litellm/proxy/credential_endpoints
+              tests/test_litellm/proxy/discovery_endpoints
+              tests/test_litellm/proxy/health_endpoints
+              tests/test_litellm/proxy/shutdown
+              tests/test_litellm/proxy/public_endpoints
+              tests/test_litellm/proxy/prompts
+              tests/test_litellm/proxy/rag_endpoints
+              tests/test_litellm/proxy/realtime_endpoints
+              tests/test_litellm/proxy/ui_crud_endpoints
+              tests/test_litellm/proxy/config_resolvers
+              tests/test_litellm/proxy/utils
+            workers: 2
+            reruns: 2
+            timeout-minutes: 20
+            job-timeout-minutes: 55
+
+          - shard: proxy-server
+            artifact-name: proxy-server
+            test-path: "tests/test_litellm/proxy/proxy_server"
+            workers: 4
+            reruns: 2
+            timeout-minutes: 60
+            job-timeout-minutes: 95
+
+          - shard: proxy-infra
+            artifact-name: proxy-infra
+            test-path: >-
+              tests/test_litellm/proxy/db
+              tests/test_litellm/proxy/middleware
+              tests/test_litellm/proxy/spend_tracking
+              tests/test_litellm/proxy/pass_through_endpoints
+              tests/test_litellm/proxy/_experimental
+              tests/test_litellm/proxy/experimental
+              tests/test_litellm/proxy/common_utils
+              tests/test_litellm/proxy/enterprise_billing
+              tests/test_litellm/proxy/types_utils
+              tests/test_litellm/proxy/logging_endpoints
+              tests/test_litellm/proxy/test_*.py
+            workers: 2
+            reruns: 2
+            timeout-minutes: 20
+            job-timeout-minutes: 55
+
+          - shard: responses-caching-types
+            artifact-name: responses-caching-types
+            test-path: >-
+              tests/test_litellm/responses
+              tests/test_litellm/caching
+              tests/test_litellm/types
+            workers: 2
+            reruns: 2
+            timeout-minutes: 20
+            job-timeout-minutes: 55
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: ${{ matrix.test-path }}
+      workers: ${{ matrix.workers }}
+      reruns: ${{ matrix.reruns }}
+      timeout-minutes: ${{ matrix.timeout-minutes }}
+      job-timeout-minutes: ${{ matrix.job-timeout-minutes }}
+      artifact-name: ${{ matrix.artifact-name }}