Commit graph

33581 commits

Author SHA1 Message Date
Yuneng Jiang
8c727b10b4
chore: fixes
Some checks failed
Unit Tests: Caching (Redis) / caching-redis (push) Has been cancelled
Unit Tests: Proxy DB Operations / proxy-db (auth-checks, tests/proxy_unit_tests/test_auth_checks.py tests/proxy_unit_tests/test_user_api_key_auth.py, 20, 8) (push) Has been cancelled
Unit Tests: Proxy DB Operations / proxy-db (key-generation, tests/proxy_unit_tests/test_key_generate_prisma.py, 30, 0) (push) Has been cancelled
Unit Tests: Proxy DB Operations / proxy-db (remaining, tests/proxy_unit_tests --ignore=tests/proxy_unit_tests/test_key_generate_prisma.py --ignore=tests/proxy_unit_tests/test_auth_checks.py --ignore=tests/proxy_unit_tests/test_user_api_key_auth.py, 20, 8) (push) Has been cancelled
Unit Tests: Security / security (push) Has been cancelled
2026-04-05 00:05:36 -07:00
Ishaan Jaffer
fd3bb51efc fix(agent-monitoring): replace return_system_files with execute + def_factorial 2026-02-25 11:56:48 -08:00
Ishaan Jaffer
5affd465bb fix: remove duplicate antd import in ToolPolicies.tsx 2026-02-25 11:46:02 -08:00
Ishaan Jaffer
426f01b456 fix(agent-monitoring): replace fetch_claims with return_system_files, align drift % to 87 2026-02-25 11:42:46 -08:00
Ishaan Jaffer
af6b117264 fix(agent-monitoring): move Drift Score column to right after Status 2026-02-25 11:40:25 -08:00
Ishaan Jaffer
dc02a6a607 feat(agent-monitoring): add drift score column + orange row highlight to log table 2026-02-25 11:39:44 -08:00
Ishaan Jaffer
b20e4369c6 fix(agent-monitoring): remove mock log table, keep only real SpendLogsTable 2026-02-25 11:37:05 -08:00
Ishaan Jaffer
040b366eac fix(agent-monitoring): restore real SpendLogsTable below drift-annotated log rows 2026-02-25 11:33:27 -08:00
Ishaan Jaffer
8c138c65c0 feat(agent-monitoring): simplify agent detail to drift card + annotated log table 2026-02-25 11:32:02 -08:00
Ishaan Jaffer
c0b4797ade fix(agent-monitoring): stack metric cards label/value vertically for proper alignment 2026-02-25 11:14:59 -08:00
Ishaan Jaffer
d8f63a73b6 fix(agent-monitoring): rewrite drift alert copy to sound less AI-generated 2026-02-25 11:13:52 -08:00
Ishaan Jaffer
1209b56c52 feat(agent-monitoring): add Agent Monitoring demo UI with drift detection and tool policy enforcement
- Add AgentMonitoring component with 3-view navigation (overview → agent table → agent detail)
- Claims Processing Agent detail: cosine similarity drift alert, observed behavior, guardrail CTA
- Tools Live Feed: remove policy column and red highlighting; New Tools Detected shows fetch_claims as trusted
- Logs section filtered by key_alias=Claims-agent with 30-day window + 2-day end offset for timezone alignment
- Add initialKeyAlias prop to SpendLogsTable for pre-filtered agent log views
- Wire agent-monitoring page into leftnav under Guardrails group
2026-02-25 11:13:19 -08:00
Sameer Kankute
47c24ef8ae
Merge pull request #22094 from BerriAI/litellm_bump_openai_25_02
[chore] bump OpenAI package version
2026-02-25 18:46:10 +05:30
Sameer Kankute
05165779ac
Merge pull request #22081 from BerriAI/litellm_fix_bedrock_batch_health_check
Fix: Test connect failing for bedrock batches mode
2026-02-25 18:46:01 +05:30
Sameer Kankute
ebe35aad9a
Merge pull request #22080 from BerriAI/litellm_vllm_response_fix
Fix None (TypeError: 'NoneType' object is not a mapping)
2026-02-25 18:45:54 +05:30
Sameer Kankute
ec3ae25a3a
Merge pull request #22070 from BerriAI/litellm_forward_auth_headers
[Feat]Add forward auth headers of provider
2026-02-25 18:45:38 +05:30
Harshit Jain
fbffa9a215
Merge pull request #22095 from Harshit28j/litellm_fix_RCE_issues
fix Unauthenticated RCE and Sandbox Escape in Custom Code Guardrail
2026-02-25 18:23:04 +05:30
Harshit28j
c3e32b450e Address CR feedback: fix auth dependency duplication, correct logger wording, clean imports 2026-02-25 18:02:12 +05:30
Harshit28j
e50b4486d0 fix Unauthenticated RCE and Sandbox Escape in Custom Code Guardrail 2026-02-25 17:57:32 +05:30
Sameer Kankute
ec9ec6b771 remove comment 2026-02-25 17:40:46 +05:30
Sameer Kankute
955b85015f Bump openai package 2026-02-25 17:40:41 +05:30
Harshit Jain
d2aeb3e513
Merge pull request #22084 from Harshit28j/litellm_presidio-non-json-response-handling
fix(guardrails): prevent presidio crash on non-json responses
2026-02-25 16:37:39 +05:30
Harshit28j
6a8052295b fix(guardrails): prevent presidio crash on non-json responses 2026-02-25 16:11:24 +05:30
Harshit Jain
66c49dbb9c
Merge pull request #22077 from Harshit28j/litellm_gemini_trace_id_missingv2
Litellm gemini trace id missingv2
2026-02-25 15:09:42 +05:30
Sameer Kankute
61f9222156 Fix: Test connect failing for bedrock batches mode 2026-02-25 15:03:27 +05:30
Sameer Kankute
45c87a714e Fix None (TypeError: 'NoneType' object is not a mapping) 2026-02-25 14:39:12 +05:30
Harshit Jain
23e84eb789 fix: Metadata / Trace ID Missing in S3 Streaming Callbacks 2026-02-25 14:16:42 +05:30
Harshit Jain
897b472011 fix: Metadata / Trace ID Missing in S3 Streaming Callbacks 2026-02-25 14:16:21 +05:30
Sameer Kankute
83afa310d6 Fix clean header logger 2026-02-25 12:31:35 +05:30
Sameer Kankute
0e806c83c1 Fix docs 2026-02-25 12:13:56 +05:30
Sameer Kankute
a43d6139c7 Fix docs 2026-02-25 12:13:07 +05:30
Sameer Kankute
1f8f66de69 add docs for Authentication Headers forwarding 2026-02-25 12:10:12 +05:30
Sameer Kankute
886f9d6a70 Add support for forwarding provider's auth headers 2026-02-25 12:08:25 +05:30
Krish Dholakia
00ab4d2067
feat: add new code execution dataset (#22065) 2026-02-24 20:58:23 -08:00
yuneng-jiang
ec7dc44e73
Merge pull request #22049 from BerriAI/litellm_spend_log_key_info
[Fix] Enrich Failure Spend Logs With Key/Team Metadata
2026-02-24 20:56:51 -08:00
shin-bot-litellm
b2c0bec5c5
fix(test): Update status enum values to match Google Interactions OpenAPI spec (#22061)
Google's Interactions API spec changed the status enum:
- Values are now lowercase (was uppercase)
- 'UNSPECIFIED' value was removed

Updated test to match the current spec from:
https://ai.google.dev/static/api/interactions.openapi.json
2026-02-24 20:26:11 -08:00
yuneng-jiang
aa48a7ec00 Allow DB fallback for failure metadata enrichment lookups
Accurate logging is more important than avoiding the rare DB lookup
on the async failure path. Remove check_cache_only=True so lookups
fall back to DB when the key/team is not in cache.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-24 19:43:55 -08:00
yuneng-jiang
7a8b3daff5 address greptile review feedback (greploop iteration 2)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-24 19:22:45 -08:00
yuneng-jiang
bf77a114cc address greptile review feedback (greploop iteration 1)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-24 19:10:01 -08:00
yuneng-jiang
8f118fbbce
Merge pull request #22053 from atapia27/healthcheck-typo-fix
removed extra comma typo
2026-02-24 19:06:53 -08:00
Ishaan Jaff
60bcb26dc8
feat(agents): assign virtual keys to agents (#22045)
* feat(agents): assign virtual keys to agents

- Add agent_id field to LiteLLM_VerificationToken (schema.prisma + _types.py)
- Pass agent_id through key generation endpoint so keys can be scoped to an agent
- Refactor Add Agent wizard to 3-step flow (Configure → Assign Key → Ready)
  - Configure: all agent fields, custom/other type with just name+description
  - Assign Key: create new key or reassign existing key to agent
  - URL is now optional for easy discovery
- Add "Agent" ownership option to Create Key modal on Virtual Keys page
  with agent selector dropdown
- Extract CreatedKeyDisplay into shared component, reused in both flows
- Add keyCreateForAgentCall networking helper
- Add test for agent_id key generation

* fix(agents): code quality fixes from self-review

- Fix test_generate_key_helper_fn_agent_id: remove bare except clause,
  use explicit assert mock_insert.called, use .kwargs for clean arg access
- Remove no-op conditional in handleNext (both branches were identical)
- Validate selectedExistingKey before calling keyUpdateCall
- Validate selectedAgentId before setting on formValues in create_key_button

* fix(ui): replace deprecated Tremor Button with Ant Design Button in CreatedKeyDisplay
2026-02-24 18:28:16 -08:00
Ishaan Jaff
4e84e4c607
fix(ui): show real tool names in logs for Anthropic format tools (#22048) 2026-02-24 18:16:04 -08:00
Alejandro Tapia
b1423bc8bf removed extra comma typo 2026-02-24 17:37:00 -08:00
yuneng-jiang
3f1554c099
Merge pull request #21071 from atapia27/feat/healthcheck-model_id-fix
healthcheck-model_id-fix
2026-02-24 17:15:07 -08:00
yuneng-jiang
f4e23c97fd [Fix] Enrich failure spend logs with key/team metadata
Failure spend logs were missing key metadata (key alias, user ID, team ID,
team alias) in two scenarios:

1. Auth errors (401 ProxyException): auth_exception_handler creates a
   minimal UserAPIKeyAuth with only api_key and request_route set — all
   other fields are null. The failure hook now looks up the full key object
   from cache/DB using the key hash to populate the missing fields.

2. Post-auth failures (provider errors, rate limits): key fields are
   present but team_alias is always null because LiteLLM_VerificationTokenView
   SQL view does not include team_alias. The failure hook now looks up the
   team object from cache to populate team_alias.

Both lookups are non-fatal and wrapped in try/except.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-24 17:14:37 -08:00
Alejandro Tapia
80c09295ad Merge upstream/main - resolve health check conflicts 2026-02-24 17:09:05 -08:00
yuneng-jiang
9837a1bd2a
Merge pull request #22047 from BerriAI/litellm_key_info_page_email
[Feature] UI - Virtual Keys: Add KeyInfoHeader component
2026-02-24 17:04:17 -08:00
ryan-crabbe
fa87291bd9
Merge pull request #20397 from ryan-crabbe/fix/openai-prompt-cache-params
fix: add prompt_cache_key and prompt_cache_retention support for OpenAI
2026-02-24 16:51:10 -08:00
yuneng-jiang
50ba6986ef [Feature] UI - Virtual Keys: Add KeyInfoHeader component with metadata display
Add a reusable KeyInfoHeader component to replace the inline header in KeyInfoView.
Extract LabeledField as a common component for labeled metadata display with copyable
support, default_user_id handling, and empty value placeholders.

- Migrate all icons from lucide-react/heroicons to @ant-design/icons
- Use antd native copyable with descriptive tooltips (Copy Key Alias, Copy Key ID, etc.)
- Show DefaultProxyAdminTag for default_user_id values
- Add canModifyKey, regenerateDisabled, regenerateTooltip props for permission gating
- Add tests for KeyInfoHeader (19 tests) and LabeledField (8 tests)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-02-24 16:46:26 -08:00
Ryan Crabbe
adafac1117 fix: add prompt_cache_key and prompt_cache_retention support for OpenAI
These params were silently dropped for Chat Completions because they
were missing from the supported params whitelist. Also adds
prompt_cache_retention to the Responses API TypedDict and fixes
misleading cache_control comments in OpenAI prompt caching docs.
2026-02-24 16:42:54 -08:00