fbe5ae9e17
fixing flaky tests
2026-01-23 12:20:27 -08:00
8b5b343841
attempt fix flaky tests
2026-01-23 12:10:08 -08:00
12463809bd
Merge pull request #19638 from BerriAI/main
...
merge main in stagin 1 22 26
2026-01-23 14:54:17 +05:30
57d777bc69
Fix unsafe access to request attribute ( #19573 )
2026-01-22 10:58:29 -08:00
b729622bf5
Fix: generationConfig removal from tests
2026-01-22 19:00:37 +05:30
c8669cf8fa
Fix Azure RPM calculation formula ( #19513 )
...
* Fix Azure RPM calculation formula
* updated test
2026-01-21 21:03:23 -08:00
aeb38ffa9b
Merge pull request #19497 from BerriAI/main
...
merge main
2026-01-21 18:43:27 +05:30
a5ea08a0bf
Fix test_default_api_base failing because of chatgpt as provider
2026-01-21 09:32:38 +05:30
0b9f6b543f
Fixes test_aaabasic_gcs_logger
2026-01-21 08:58:16 +05:30
9e1275b76c
Merge branch 'main' into litellm_staging_01_19_2026
2026-01-20 19:19:36 +05:30
cd96c8cbb0
Fix:test_aaaaazure_tenant_id_auth
2026-01-20 17:39:08 +05:30
a4bfdf2427
Fix: total timeout is not respected
2026-01-20 09:37:43 +05:30
13d887a275
Fix queue persistence to Redis ( #19304 )
...
* Fix queue persistence to Redis
* add test
2026-01-19 19:01:34 -08:00
d30c25af21
feat(gemini): use responseJsonSchema for Gemini 2.0+ models ( #19314 )
...
* feat(gemini): add opt-in support for responseJsonSchema
Add support for Gemini's native responseJsonSchema parameter which uses
standard JSON Schema format instead of OpenAPI-style responseSchema.
Benefits of responseJsonSchema (Gemini 2.0+ only):
- Standard JSON Schema format (lowercase types)
- Supports additionalProperties for stricter validation
- Better compatibility with Pydantic's model_json_schema()
- No propertyOrdering required
Usage:
```python
response_format={
"type": "json_schema",
"json_schema": {"schema": {...}},
"use_json_schema": True # opt-in
}
```
This is backwards compatible - existing code continues to use
responseSchema by default.
Closes #16340
* docs: add documentation for use_json_schema parameter
Document the new use_json_schema option for Gemini 2.0+ models
in the JSON Mode documentation.
* refactor(gemini): use responseJsonSchema by default for Gemini 2.0+
Remove opt-in flag `use_json_schema` and automatically detect model version:
- Gemini 2.0+: uses responseJsonSchema (standard JSON Schema, supports additionalProperties)
- Gemini 1.5: uses responseSchema (OpenAPI format, legacy)
This follows LiteLLM's philosophy of abstracting provider differences -
users write the same code regardless of model version.
* test(vertex): update json_schema tests to accept both responseSchema formats
Gemini 2.x+ uses responseJsonSchema while Gemini 1.x uses responseSchema.
Update tests to accept both formats since litellm now auto-selects based
on model version.
2026-01-19 10:45:37 -08:00
6cd4b3603f
fix(router): prevent retrying 4xx client errors ( #19275 )
2026-01-19 05:18:35 -08:00
5812654bdd
test_router_fallbacks_with_custom_model_costs
2026-01-17 16:34:46 -08:00
09fb1581cb
Fix:add async_get_available_deployment_for_pass_through in code tests
2026-01-16 16:37:44 +05:30
dca42047b9
Merge pull request #19068 from BerriAI/litellm_responses_caching_support
...
[Fix] Add support for caching for responses API
2026-01-15 08:38:31 +05:30
52d3c9dcfc
Add retry policy support to responses API
2026-01-14 14:55:17 +05:30
333947e236
Add support for caching for responses API
2026-01-14 13:33:07 +05:30
e98c2e4425
Merge pull request #19012 from BerriAI/litellm_fix_model_deployment_routing
...
Fix: Model matching priority in configuration
2026-01-13 17:55:01 +05:30
d656f01bc9
Merge pull request #19009 from Dima-Mediator/fix-image-tokens-spend-logging
...
Fix image tokens spend logging for /images/generations
2026-01-13 15:03:37 +05:30
ecb3959c3c
Merge pull request #18208 from Chesars/fix/case-insensitive-model-cost-lookup
...
fix: case-insensitive model cost map lookup
2026-01-13 11:53:43 +05:30
dfece51f8c
Fix: Model matching priority in configuration
2026-01-13 11:44:48 +05:30
a57f1e2e08
test: remove flaky azure oidc embedding test
2026-01-13 10:34:01 +09:00
ab85eb8f43
Fix: gaurdrail moderation support with responses API
2026-01-12 17:27:13 +05:30
5873cd4a32
test_completion_bedrock_titan_null_response
2026-01-07 15:09:44 +05:30
269771a7c9
test_bedrock_httpx_streaming
2026-01-07 15:02:10 +05:30
645ca64780
a121 fixes
2026-01-07 15:00:49 +05:30
1d16a8526e
feat: allow configuring project name for OpenTelemetry service name
2026-01-07 14:20:10 +09:00
a7c39ccc12
fix(router): correct num_retries tracking in retry logic ( #18712 )
...
* fix(router): correct num_retries tracking in retry logic
- Fix off-by-one error in num_retries attribute when retries exhausted
- Correct remaining_retries calculation
- Add comprehensive tests for retry tracking edge cases
Fixes incorrect retry count in error messages and logging
* chore: trigger CI re-run
* chore: trigger CI tests again
2026-01-06 23:58:41 +05:30
ca14160375
Revert "fix: model eol"
...
This reverts commit 5aa1665d79
2026-01-06 16:49:30 +09:00
23713d1811
fix: anthropic claude-3-opus-20240229 EOL
2026-01-06 16:06:21 +09:00
5aa1665d79
fix: model eol
2026-01-06 15:47:37 +09:00
c8bb92afdc
Merge pull request #18579 from BerriAI/litellm_remove_prompt_chaching_header
...
Remove prompt caching headers as the support has been removed
2026-01-02 21:01:50 +05:30
dd96f91254
Add thought signature for non tool call requests
2026-01-02 12:31:31 +05:30
ca94990307
remove prompt caching headers as the support has been removed
2026-01-02 11:08:35 +05:30
0addab4f63
Add test for removal of thought signature
2025-12-23 14:56:42 +05:30
5534038e93
Fix CI: Revert security scan changes and add GitGuardian ignore rules ( #18358 )
2025-12-22 17:03:53 -08:00
09dcb38b4b
Revert "test_update_model_cost_map_url"
...
This reverts commit c9d61fcdba
2025-12-22 12:41:30 +05:30
c9d61fcdba
test_update_model_cost_map_url
2025-12-22 11:51:30 +05:30
148715541c
test compl openai orgs
2025-12-20 23:41:29 +05:30
b1090db927
test_openai_stream_options_call
2025-12-20 22:35:21 +05:30
6112160a16
Revert "[Fix] Security - Remove example API keys with high entropy ( #18255 )"
...
This reverts commit 24edbccf5c
2025-12-20 20:48:11 +05:30
c13b4c5514
test_aaapass_through_endpoint_pass_through_keys_langfuse
2025-12-20 14:36:59 +05:30
24edbccf5c
[Fix] Security - Remove example API keys with high entropy ( #18255 )
2025-12-19 10:09:50 -08:00
0c48826cdc
Revert "[Fix] CI/CD - local_testing & mapped tests ( #18222 )" ( #18223 )
...
This reverts commit dc7f500c47
2025-12-18 14:46:09 -08:00
dc7f500c47
[Fix] CI/CD - local_testing & mapped tests ( #18222 )
2025-12-18 14:34:48 -08:00
e08b4767e9
fix: case-insensitive model cost map lookup
...
Users were getting "does not support parameters: ['tools']" errors when
using lowercase model names (e.g., "qwen/qwen3-next-80b-a3b-thinking")
because the model cost map has mixed-case keys and the lookup was
case-sensitive.
Added _get_model_cost_key() helper that tries exact match first (O(1)),
then falls back to case-insensitive search if not found.
2025-12-18 17:25:43 -03:00
f353bb6dba
[Fix] CI/CD - litellm_mapped_tests_llms | litellm_mapped_tests_core | caching_unit_tests ( #18197 )
2025-12-18 08:49:23 -08:00
yuneng-jiang