Commit graph

3560 commits

Author SHA1 Message Date
Mateo Wang
2e35ae1065
Merge pull request #42049 from BerriAI/litellm_mantle_native_anthropic_messages
feat(bedrock_mantle): serve /v1/messages for Claude models on Mantle's native Anthropic Messages API
2026-09-21 12:52:16 -07:00
Mateo Wang
e7e4df9098
Merge pull request #42041 from BerriAI/litellm_azure_ai_gpt5_tools_responses_bridge
fix(azure_ai): bridge gpt-5.4+ function tools with reasoning to the Foundry Responses API
2026-09-21 12:21:02 -07:00
Mateo Wang
9a90adad32
Merge pull request #42275 from BerriAI/litellm_claude_platform_messages_beta_passthrough
fix(bedrock): forward anthropic-beta headers verbatim on the Claude platform messages path
2026-09-21 12:01:39 -07:00
mateo-berri
4eed951e6f Merge commit '36b8be7d81b' into litellm_mantle_native_anthropic_messages_b4dc
# Conflicts:
#	tests/test_litellm/llms/anthropic/experimental_pass_through/messages/test_anthropic_experimental_pass_through_messages_handler.py
2026-09-21 12:00:37 -07:00
kerry-berri
12379aa1e3
Merge pull request #42095 from BerriAI/litellm_fal_gpt_image_25_flux_dev_edits
feat(fal_ai): add gpt-image-2.5 flare/sunburst, flux/dev and image edits
2026-09-21 11:45:45 -07:00
mateo-berri
e51ccbc759 fix(bedrock): forward anthropic-beta headers verbatim on the Claude platform messages path 2026-09-21 11:39:26 -07:00
Yassin Kortam
e912ebe999
Merge pull request #42152 from BerriAI/litellm_claude_code_safeguards_passthrough
fix(anthropic): forward safeguards and anthropic-beta unchanged on native /v1/messages
2026-09-21 10:12:44 -05:00
Yassin Kortam
1ac4d7ae04 fix(anthropic): type safeguards and safeguard_results as the arrays Anthropic sends
Driving a real Claude Code 2.1.278 through the proxy, and a direct call to
api.anthropic.com, both show these two fields are JSON arrays on the wire rather
than objects. The request carries safeguards as
[{"type": "dangerous_tool_use", "classifier_context": {...}}] under beta
dangerous-tool-use-2026-09-03, and the 200 comes back with safeguard_results as
[{"type": "dangerous_tool_use", "status": {"type": "available", "tool_uses": {...}}}].

No runtime change: the request filter matches on TypedDict keys and never inspects
the value. The test fixtures move to the captured shapes so the regression tests
pin what the client and the provider actually exchange.
2026-09-21 09:55:09 -05:00
Devin AI
30adc1b2b9 Merge remote-tracking branch 'origin/main' into litellm_azure_ai_mai_image_2_5_pro 2026-09-21 13:20:20 +00:00
yuneng-jiang
7c4b805ca0
Merge pull request #42145 from BerriAI/litellm_migrate_tests_p13
test: migrate legacy provider tests to tests/unit (wave 2, phase 13)
2026-09-20 10:50:18 -07:00
yassin
b59028d525 fix(anthropic): strip safeguards on the adapter path and type it on streaming chunks
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 17:37:56 +00:00
yassin
3ebd5add32 fix(anthropic): forward safeguards and anthropic-beta unchanged on native /v1/messages
Native Anthropic Messages requests derived their allowlist from
AnthropicMessagesRequestOptionalParams, which lacked safeguards, and the
shared beta-header filter dropped betas unknown to the provider mapping
even when the upstream is api.anthropic.com itself. Claude Code auto mode
then saw no safeguard_results and fell back to billed classifier calls

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 17:20:22 +00:00
kerry
342bde7a8d Merge remote-tracking branch 'origin/main' into litellm_fal_gpt_image_25_flux_dev_edits 2026-09-20 17:20:17 +00:00
kerry-berri
af1f46af1a
Merge pull request #41980 from BerriAI/litellm_fal_seedance_video
feat(fal_ai): add Seedance 2.5 / 2.0 video generation via fal queue API
2026-09-20 10:18:48 -07:00
yuneng
e1556ce32b test: migrate legacy provider tests to tests/unit (wave 2, phase 13)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 14:18:49 +00:00
yuneng
69133cc8cf Merge remote-tracking branch 'origin/main' into litellm_migrate_tests_p12 2026-09-20 13:44:19 +00:00
yuneng-jiang
ec93936668
Merge pull request #42132 from BerriAI/litellm_migrate_tests_p14
test: migrate phase 14 wave 2 provider tests to tests/unit
2026-09-20 06:43:34 -07:00
yuneng-jiang
e5b2cabae5
Merge pull request #42128 from BerriAI/litellm_migrate_tests_p11
test: migrate openai, openai_like and openrouter legacy tests to tests/unit
2026-09-20 06:43:22 -07:00
yuneng
1ca0a662f0 Merge remote-tracking branch 'origin/main' into litellm_migrate_tests_p11 2026-09-20 12:55:05 +00:00
yuneng
affd2d0c30 merge: bring main (unit package markers) into litellm_migrate_tests_p3 2026-09-20 12:55:05 +00:00
yuneng
432cf517ce Merge remote-tracking branch 'origin/main' into litellm_migrate_tests_p14 2026-09-20 12:54:59 +00:00
yuneng
ad0511ab64 Merge remote-tracking branch 'origin/main' into litellm_migrate_tests_p12 2026-09-20 12:54:55 +00:00
yuneng
ef6237b9f2 test: migrate phase 12 legacy llm provider tests to tests/unit
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 11:02:53 +00:00
yuneng
a69ca90ea5 test: migrate phase 14 wave 2 provider tests to tests/unit
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 11:01:40 +00:00
yuneng-jiang
bfc805b372
Merge pull request #42109 from BerriAI/litellm_migrate_tests_p5
test(llms): migrate phase 5 provider unit tests to tests/unit
2026-09-20 04:00:48 -07:00
yuneng-jiang
766f6fcd3a
Merge pull request #42112 from BerriAI/litellm_migrate_tests_p8
test: migrate wave 1 phase 8 legacy llm tests to tests/unit
2026-09-20 03:59:36 -07:00
yuneng-jiang
4852d71606
Merge pull request #42114 from BerriAI/litellm_migrate_tests_p7
test(llms): migrate phase 7 provider unit tests to tests/unit
2026-09-20 03:59:28 -07:00
yuneng
729a96e4ea test: migrate openai, openai_like and openrouter legacy tests to tests/unit
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 10:40:27 +00:00
kerry
c3193a8e32 merge: origin/main into litellm_fal_gpt_image_25_flux_dev_edits
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 10:15:52 +00:00
yuneng-jiang
9e39c751ed
Merge pull request #42117 from BerriAI/litellm_migrate_tests_p9
test: migrate phase 9 legacy llm provider tests to tests/unit
2026-09-20 03:13:33 -07:00
yuneng-jiang
e08df02ebe
Merge pull request #42115 from BerriAI/litellm_migrate_tests_p10
test: migrate nvidia, oci, ocr, oobabooga and openai legacy tests to tests/unit
2026-09-20 03:13:07 -07:00
yuneng-jiang
53ba9f389f
Merge pull request #42107 from BerriAI/litellm_migrate_tests_p6
test(llms): migrate phase 6 provider unit tests to tests/unit
2026-09-20 03:12:59 -07:00
yuneng-jiang
5ae5727eb0
Merge pull request #42110 from BerriAI/litellm_migrate_tests_p4
test(llms): migrate bedrock, baseten and base_llm batch tests to tests/unit
2026-09-20 03:12:49 -07:00
yuneng
fcabb626ac test(unit): migrate wave 1 phase 3 anthropic, apiserpent, azure and azure_ai legacy tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 08:19:05 +00:00
yuneng
ad523edb25 test: migrate phase 9 legacy llm provider tests to tests/unit 2026-09-20 08:13:11 +00:00
yuneng
443c9f8385 test: migrate nvidia, oci, ocr, oobabooga and openai legacy tests to tests/unit
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 08:09:49 +00:00
yuneng
d47008129c test(llms): migrate phase 7 provider unit tests to tests/unit
Move the wave 1 phase 7 batch (fireworks_ai, gemini, gigachat, github_copilot; 20 files) from tests/test_litellm to tests/unit after judging every test function under a behaviour mutation. Seven wiring or mock-echo tests that stayed green are deleted. The fireworks cost calculator tests get a local model_cost save/restore fixture since the tests/unit tree has no shared conftest for it

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 08:08:12 +00:00
yuneng
4defed7f2e test: migrate wave 1 phase 8 legacy llm tests to tests/unit
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 08:03:54 +00:00
yuneng
02ccdbae90 test(llms): migrate bedrock, baseten and base_llm batch tests to tests/unit 2026-09-20 07:51:50 +00:00
yuneng
522c3e3ed6 test: migrate wave 1 phase 2 legacy unit tests to tests/unit
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 07:50:43 +00:00
yuneng
b450baa402 test(llms): migrate phase 5 provider unit tests to tests/unit
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 07:50:38 +00:00
yuneng
e1d2789d29 test(llms): migrate phase 6 provider unit tests to tests/unit
Migrate 18 provider test files from tests/test_litellm/llms to tests/unit/llms.
194 kept tests move as-is after mutation testing; 1 test deleted
(test_completion_datarobot_with_environment_variables, env-gated no-assert);
the fixture-only fal_ai cost calculator file is removed.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 07:50:30 +00:00
kerry
9f24699e4c fix(fal_ai): reject empty image lists in image edit requests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 05:44:56 +00:00
kerry
cc7dce6a21 fix(fal_ai): accept every FileTypes image input and derive gpt-image qualities from pricing rows
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 05:33:06 +00:00
kerry
62c215be19 fix(fal_ai): accept every FileTypes image input and derive gpt-image qualities from pricing metadata
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 05:31:27 +00:00
kerry
365dc9a3b5 feat(fal_ai): add gpt-image-2.5 flare/sunburst, flux/dev and image edits
Route openai/gpt-image-2.5/{flare,sunburst}/text-to-image through the existing GPT Image config with the xhigh and max quality tiers, add a dedicated fal-ai/flux/dev config, and add a Fal image-edit config so /v1/images/edits works for the gpt-image-2.5 and gpt-image-2 edit endpoints. Add flat and quality-by-size keyed pricing rows so spend is non-zero

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 05:14:15 +00:00
Mateo Wang
58065d46fd
Merge pull request #42071 from BerriAI/litellm_remove_dead_telemetry_flag 2026-09-19 21:48:02 -07:00
mateo-berri
19d77e2442 test(guardrails): type the recorder hook's request_data as a Mapping 2026-09-19 20:21:37 -07:00
kerry
66078f4834 Merge remote-tracking branch 'origin/main' into litellm_azure_ai_mai_image_2_5_pro
Some checks failed
LiteLLM Rust / rust-lint (push) Has been cancelled
LiteLLM Rust / rust-test (push) Has been cancelled
LiteLLM Rust / rust-wheel (push) Has been cancelled
Terraform Provider / gofmt, vet, build, test (push) Has been cancelled
Terraform Provider / Provider endpoints vs proxy OpenAPI schema (push) Has been cancelled
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-20 03:15:05 +00:00
mateo-berri
c13dcb0abf fix(proxy): forward a client's anthropic-beta and anthropic-version headers to bedrock_mantle 2026-09-19 20:11:14 -07:00