litellm/litellm
Cursor Agent bc9a48d407 fix: MCP OAuth 2.0 UX gaps across admin and internal user flows
Fixes found by dogfooding the MCP OAuth 2.0 flow as both an admin and
an internal user:

1. Fix [object Object] error when creating MCP server
   - Use parseErrorMessage() in create_mcp_server.tsx catch handler
   - Fix deriveErrorMessage() in networking.tsx to always return a string
     instead of potentially returning an object

2. Pre-configured OAuth servers auto-select auth type
   - Add auth_type field to DiscoverableMCPServer type
   - Add auth_type='oauth2' to Atlassian and Linear in mcp_registry.json
   - Pre-fill auth_type in create form when selecting from catalog
   - Use requestAnimationFrame to defer setting after transport dropdown mounts

3. Backend: drop tool_choice when MCP resolves no tools
   - In chat_completions_handler.py, remove tool_choice from kwargs when
     all_tools is empty after MCP resolution, preventing 400 errors from
     providers that reject tool_choice without tools

4. Chat UI: OAuth-aware MCP server management
   - MCPAppsPanel: show lock icon for OAuth servers in grid, show
     'Authorization required' banner + 'Authorize' button in detail view,
     and initiate PKCE OAuth flow via existing proxy endpoints
   - MCPConnectPicker: show lock icon next to OAuth server names
   - Store user OAuth tokens in sessionStorage for the session

Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
2026-03-07 03:37:30 +00:00
..
a2a_protocol Merge pull request #22888 from BerriAI/litellm_a2a-custom-headers 2026-03-06 18:24:21 +05:30
anthropic_interface fix: prompt registry 2026-02-18 00:34:54 +05:30
assistants
batch_completion fix: prompt registry 2026-02-18 00:34:54 +05:30
batches fix(mypy): resolve type errors across 9 files 2026-03-05 06:58:20 -03:00
caching fix(caching): check REDIS_CLUSTER_NODES env var in Cache and Router class selection (#22790) 2026-03-06 17:31:30 -08:00
completion_extras Merge remote-tracking branch 'upstream/main' into pr-22553 2026-03-03 09:48:39 +00:00
containers fix: prompt registry 2026-02-18 00:34:54 +05:30
endpoints/speech/speech_to_completion_bridge
evals fix: prompt registry 2026-02-18 00:34:54 +05:30
experimental_mcp_client added configurable env for mcp timeouts (#22287) 2026-03-02 13:13:41 -08:00
files Merge pull request #22765 from BerriAI/main 2026-03-04 17:40:42 +05:30
fine_tuning Update litellm/fine_tuning/main.py 2026-03-05 06:45:31 -03:00
google_genai fix: prompt registry 2026-02-18 00:34:54 +05:30
images Merge branch 'litellm_oss_staging_02_27_2026' of https://github.com/BerriAI/litellm into litellm_oss_staging_02_27_2026 2026-02-28 09:54:56 -03:00
integrations fix: downgrade WebSearch logs from info to debug to reduce production noise 2026-03-05 18:58:40 +01:00
interactions fix: prompt registry 2026-02-18 00:34:54 +05:30
litellm_core_utils Merge pull request #22866 from mubashir1osmani/feat/bedrock-mantle-provider-clean 2026-03-05 18:24:00 +05:30
llms Merge pull request #22981 from BerriAI/litellm_reasoning-effort-dict-normalization 2026-03-07 00:37:07 +05:30
ocr Enable local file support for OCR (#22133) 2026-02-27 10:50:02 -08:00
passthrough fix(passthrough): propagate Azure 429/5xx errors in async streaming instead of silent HTTP 200 (#22913) 2026-03-05 10:12:43 -08:00
proxy fix: MCP OAuth 2.0 UX gaps across admin and internal user flows 2026-03-07 03:37:30 +00:00
proxy_auth fix: prompt registry 2026-02-18 00:34:54 +05:30
rag fix: prompt registry 2026-02-18 00:34:54 +05:30
realtime_api fix(azure): forward realtime_protocol from config and relax api_version check for GA path (#22369) 2026-03-02 19:21:27 +05:30
rerank_api fix(bedrock): pass timeout param to bedrock rerank http client (#22021) 2026-02-24 09:32:11 -08:00
responses fix: MCP OAuth 2.0 UX gaps across admin and internal user flows 2026-03-07 03:37:30 +00:00
router_strategy fix: complexity_router crashes on list-format message content (OpenAI multi-part messages) (#22761) 2026-03-04 16:18:49 -08:00
router_utils Fix encrypted content streaming affinity issue 2026-03-03 18:37:22 +05:30
search
secret_managers feat: Hashicorp Vault config override backend endpoints 2026-03-05 16:57:08 -08:00
skills fix: prompt registry 2026-02-18 00:34:54 +05:30
types Merge pull request #22939 from BerriAI/litellm_hashicorp_vault_backend 2026-03-06 17:59:46 -08:00
vector_store_files
vector_stores
videos fix(ollama): thread api_base to get_model_info + graceful fallback (#21970) 2026-02-23 21:00:37 -08:00
__init__.py Merge pull request #22866 from mubashir1osmani/feat/bedrock-mantle-provider-clean 2026-03-05 18:24:00 +05:30
_lazy_imports.py fix: prompt registry 2026-02-18 00:34:54 +05:30
_lazy_imports_registry.py Merge pull request #22866 from mubashir1osmani/feat/bedrock-mantle-provider-clean 2026-03-05 18:24:00 +05:30
_logging.py fix: prompt registry 2026-02-18 00:34:54 +05:30
_redis.py fix: close leaked Redis connection pools on cache eviction and disconnect 2026-02-20 17:09:32 -08:00
_service_logger.py fix: prompt registry 2026-02-18 00:34:54 +05:30
_uuid.py
_version.py
anthropic_beta_headers_config.json fix: enable context-1m-2025-08-07 beta header for vertex_ai provider (#21867) 2026-02-21 20:12:23 -08:00
anthropic_beta_headers_manager.py fix: prompt registry 2026-02-18 00:34:54 +05:30
blog_posts.json fix(ollama): thread api_base to get_model_info + graceful fallback (#21970) 2026-02-23 21:00:37 -08:00
budget_manager.py
constants.py feat(spend-logs): add truncation note when error logs are truncated for DB storage (#22936) 2026-03-05 16:58:46 -08:00
cost.json
cost_calculator.py feat(azure_ai): add router flat cost when response contains actual model 2026-03-06 18:18:06 +05:30
exceptions.py Remove nit 2026-02-26 13:44:06 -08:00
main.py Merge pull request #22866 from mubashir1osmani/feat/bedrock-mantle-provider-clean 2026-03-05 18:24:00 +05:30
model_prices_and_context_window_backup.json feat: add Azure AI grok-4-1-fast model support (#22587) 2026-03-06 18:10:40 -08:00
mypy.ini
policy_templates_backup.json feat(add-new-block_code_execution-guardrail): prevent agent from executing code (#22154) 2026-02-25 22:02:14 -08:00
provider_endpoints_support_backup.json fix: add 12 missing endpoint keys to _ENDPOINT_METADATA, fix stale _schema keys in backup JSON 2026-02-26 19:18:17 -08:00
py.typed
router.py fix(caching): check REDIS_CLUSTER_NODES env var in Cache and Router class selection (#22790) 2026-03-06 17:31:30 -08:00
scheduler.py fix: prompt registry 2026-02-18 00:34:54 +05:30
timeout.py
utils.py feat(openai): add 272K tier pricing for GPT-5.4/5.4-pro 2026-03-06 22:26:14 +05:30