Commit Graph

6017 Commits

Author SHA1 Message Date
Ryan Crabbe
9284395c1d
[Fix] Hide connector label on mobile, remove stale master key mention
Hide .connectorBranchLabeled on ≤768px so the "UI management only"
label doesn't render without its branch lines. Also remove "master key"
from doc text since the diagram intentionally omits that box.
2026-03-28 15:51:44 -07:00
Ryan Crabbe
d332c5b541
[Docs] Improve high availability control plane diagram clarity
Show each worker's DB and Redis as prominent infra boxes instead of
small chips, and clarify that the control plane is admin UI only —
not a router.
2026-03-28 15:29:02 -07:00
Yuneng Jiang
7851567091
[Fix] Scope documentation workflow to match CircleCI and add missing router settings
Revert path fixes for documentation tests that CircleCI never ran
(test_exception_types, test_general_setting_keys, test_readme_providers,
test_standard_logging_payload). Update the GHA workflow to run only the
4 tests CircleCI actually executed: test_env_keys, test_router_settings,
test_api_docs, test_circular_imports.

Add 2 missing router_settings keys (enable_health_check_routing,
health_check_staleness_threshold) and 27 missing general_settings keys
to config_settings.md so test_router_settings passes.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-28 11:23:53 -07:00
yuneng-jiang
1b111d23f3
Merge pull request #24688 from Sameerlite/litellm_litellm_team-model-group-name-routing-fix
fix(team-routing): preserve sibling deployment candidates for team public models
2026-03-27 12:00:34 -07:00
yuneng-jiang
b6506bf40f
Merge pull request #24610 from Sameerlite/litellm_lyria-3-cost-map-doc
feat(gemini): Lyria 3 preview models in cost map and docs
2026-03-27 10:10:03 -07:00
Krrish Dholakia
412fd469e2
Merge pull request #24692 from BerriAI/litellm_security_townhall_blog
Litellm security townhall blog
2026-03-27 10:00:54 -07:00
yuneng-jiang
3e7ee3e887
Merge pull request #24690 from Sameerlite/litellm_litellm_openai-reasoning-items-chat-completions
feat(openai): round-trip Responses API reasoning_items in chat completions
2026-03-27 09:54:23 -07:00
Krrish Dholakia
198a0e8438 docs: cleanup docs 2026-03-27 09:13:20 -07:00
Krrish Dholakia
ff63df25a2
Merge pull request #24663 from BerriAI/litellm_test_branch_03_26_2026_p1
Add zizmor to ci/cd
2026-03-27 08:59:07 -07:00
Krrish Dholakia
9c049ded65 docs: draft townhall doc
compressing slides into a deck
2026-03-27 08:35:38 -07:00
Sameer Kankute
7675488640
feat(router): add health-check-driven routing behind opt-in flag
Background health checks now feed deployment health state into the
router candidate-filtering pipeline. Unhealthy deployments are excluded
proactively instead of waiting for request failures to trigger cooldown.

Gated by `enable_health_check_routing: true` in general_settings.
Off by default — zero behavior change for existing users.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-27 20:57:08 +05:30
Sameer Kankute
cc73ae776a
feat(gemini): add Lyria 3 preview models to cost map and docs
Made-with: Cursor
2026-03-27 20:36:00 +05:30
Sameer Kankute
00a810e92d
feat(openai): round-trip Responses API reasoning_items in chat completions
Made-with: Cursor
2026-03-27 20:25:08 +05:30
yuneng-jiang
d3568efad0
Merge pull request #24611 from Sameerlite/Sameerlite/order-fallback2
feat(router): order-based fallback across deployment priority levels
2026-03-27 20:15:30 +05:30
Sameer Kankute
fb8d9c2e9a
Fix greptile reviews and mock test 2026-03-27 20:11:28 +05:30
Krrish Dholakia
88ed4f90ab docs(security_update_march_2026): publish safe versions - confirmed by veria labs 2026-03-27 05:51:01 -07:00
Krrish Dholakia
efd73a44f4 fix(index.md): test commit 2026-03-26 16:12:00 -07:00
Krrish Dholakia
8f425ec3ff fix: update ioc to include checkmarx.zone 2026-03-26 15:43:01 -07:00
yuneng-jiang
bdf4acc472
Merge pull request #24468 from BerriAI/litellm_opencode-drop-reasoningSummary-docs
docs(opencode): add guidance for dropping reasoningSummary param
2026-03-25 23:00:56 -07:00
Krrish Dholakia
df2a36dd27 docs: document new github + gitlab ci scripts 2026-03-25 20:17:10 -07:00
ryan-crabbe-berri
0d2b454cec
Merge pull request #24490 from BerriAI/litellm_ryan-march-23
Litellm ryan march 23
2026-03-25 16:04:12 -07:00
Ishaan Jaffer
a2f02aa139 docs: remove phone numbers from readme and docs 2026-03-25 12:40:40 -07:00
Krrish Dholakia
7d7045cbc1 fix: cleanup 2026-03-25 09:20:25 -07:00
Krrish Dholakia
10a48f7655 docs: add tldr 2026-03-24 19:43:13 -07:00
Ishaan Jaffer
f9d1f8cde6 docs: minor updates to security update blog post 2026-03-24 17:15:44 -07:00
Ryan Crabbe
eaa025ef7d docs: add security update blog post for March 2026 supply chain incident 2026-03-24 15:54:35 -07:00
ryan-crabbe
ffbe3896d2
Update docs/my-website/docs/proxy/multiple_admins.md
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
2026-03-23 22:54:08 -07:00
Ryan Crabbe
57c027a2dc docs: add audit log export to S3 documentation 2026-03-23 22:46:38 -07:00
Krish Dholakia
9343aeefca
Merge pull request #24413 from benlangfeld/patch-2
Correct documentation of completion_model
2026-03-23 22:42:03 -07:00
Sameer Kankute
80af635eb1 Fix docs 2026-03-24 09:44:04 +05:30
Sameer Kankute
4e6e566b4d docs(opencode): fix model prefix and clarify drop_params scope
- Use openai/gpt-5 prefix to match existing doc conventions
- Clarify that additional_drop_params must be added to every affected
  model entry, not just one

Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-24 09:42:59 +05:30
Sameer Kankute
17e6e7a4cc docs(opencode): add guidance for dropping reasoningSummary param
OpenCode sends a `reasoningSummary` Responses API param with chat
completion requests. Document how to use `additional_drop_params` to
drop it and avoid 400 errors from the OpenAI API.

Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-24 09:33:28 +05:30
Krrish Dholakia
742e176611 docs(reasoning_content.md): update guide 2026-03-23 17:23:14 -07:00
Ben Langfeld
847c12e4f5
Update docs/my-website/docs/proxy/config_settings.md
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
2026-03-23 11:06:09 -03:00
Ben Langfeld
5a846c2e64
Correct documentation of completion_model
See https://github.com/BerriAI/litellm/issues/21554
2026-03-23 10:59:18 -03:00
yuneng-jiang
e3d4c29d37
Merge pull request #24323 from BerriAI/litellm_ryan_march_20
litellm ryan march 20
2026-03-21 15:57:28 -07:00
Ryan Crabbe
f494ab513f docs: add High Availability Control Plane documentation
New docs page covering the HA control plane architecture where each
worker instance has its own DB, Redis, and master key. Includes a
React component diagram, setup configs, SSO notes, and local testing
instructions.
2026-03-21 15:31:49 -07:00
yuneng-jiang
72fba093c8 Merge remote-tracking branch 'origin/main' into litellm_dev_sameer_16_march_week 2026-03-21 15:11:29 -07:00
yuneng-jiang
10b0139bf8
Merge branch 'main' into litellm_oss_staging_03_05_2026 2026-03-21 14:58:11 -07:00
Krish Dholakia
f911d8d865
Merge pull request #23818 from BerriAI/litellm_oss_staging_03_17_2026
fix(fireworks): skip #transform=inline for base64 data URLs (#23729)
2026-03-21 14:54:39 -07:00
yuneng-jiang
262534a3a5
Merge branch 'main' into litellm_dev_sameer_16_march_week 2026-03-21 14:30:57 -07:00
yuneng-jiang
f41156aeb3
Merge branch 'main' into litellm_oss_staging_03_05_2026 2026-03-21 14:28:33 -07:00
Ishaan Jaff
2ea9e207bd
Litellm ishaan march 20 (#24303)
* feat(redis): add circuit breaker to RedisCache to fast-fail when Redis is down (#24181)

* feat(redis): add circuit breaker env var constants

* feat(redis): add RedisCircuitBreaker and apply guard decorator to all async ops

* fix(dual_cache): fall back to L1 instead of re-raising on Redis increment failures

* test(caching): add circuit breaker unit tests

* fix(redis): fast-fail concurrent HALF_OPEN probes — only one probe at a time

* fix(dual_cache): return None fallback when in_memory_cache is absent and Redis fails

* test(caching): add regression tests for HALF_OPEN concurrency and None fallback

* Fix blocking sync next in __anext__ (#24177)

* Fix blocking sync next

* Update tests/test_litellm/litellm_core_utils/test_streaming_handler.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* fix PEP 479 regression in __anext__ sync iterator exhaustion

asyncio.to_thread re-raises thread exceptions inside a coroutine, where
PEP 479 converts StopIteration to RuntimeError before any except clause
can catch it. Add _next_sync_or_exhausted() module-level helper that
catches StopIteration in the thread and returns a sentinel instead, then
raise StopAsyncIteration in the coroutine.

Also rewrites the non-blocking test to use asyncio.gather() instead of
asyncio.create_task() (which returned None on Python 3.9 / pytest-asyncio
in CI), and adds an exhaustion regression test that drains the wrapper
fully and asserts no RuntimeError leaks out.

---------

Co-authored-by: Emerson Gomes <emerson.gomes@thalesgroup.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* feat: add git-subdir source type to claude-code/plugins API (#24223)

Support a third plugin source type `git-subdir` alongside the existing
`github` and `url` types, as documented in the official Claude Code
plugin marketplaces spec.

New format: {"source": "git-subdir", "url": "...", "path": "subdir/path"}

- Validates url and path fields are present and non-empty
- Rejects absolute paths, '..' segments, backslashes, and percent-encoded
  traversal sequences (including double-encoded variants via regex check)
- Extracts path validation into _validate_git_subdir_path() helper
- Updates Pydantic field description to document all three source types
- Adds isValidUrl() check for url/git-subdir source types in the UI form
- Adds "Git Subdir" option to the UI form with a required Path field
- Adds unit tests covering success, update, missing/empty fields,
  path traversal variants, and unknown source type

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>

* [FEAT] add extract_header and extract_footer to Mistral OCR supported params (#24213)

* docs: add git-subdir source type to claude-code plugin marketplace docs (#24289)

* fix(ui): swap J/K keyboard navigation in log details drawer (#24279) (#24286)

J should navigate down (next) and K should navigate up (previous),
matching vim/standard conventions.

* fix: use async_set_cache in user_api_key_auth hot path (#24302)

* fix: use async_set_cache in auth hot path to avoid blocking event loop

* test: assert no blocking set_cache call in _user_api_key_auth_builder

* test: broaden blocking call check to all sync DualCache methods

* test: fix regression test to actually catch blocking cache calls

* fix: ruff lint unused variable + UI build MessageManager error

- litellm/caching/redis_cache.py: remove unused variable 'e' in circuit
  breaker exception handler (F841)
- add_plugin_form.tsx: use MessageManager.error() instead of undefined
  message.error() for git URL validation

Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>

* docs: add REDIS_CIRCUIT_BREAKER env vars to config_settings reference

Add REDIS_CIRCUIT_BREAKER_FAILURE_THRESHOLD and
REDIS_CIRCUIT_BREAKER_RECOVERY_TIMEOUT to the environment variables
reference table so test_env_keys.py passes.

Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>

---------

Co-authored-by: Emerson Gomes <emerson.gomes@thalesgroup.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Vincenzo Barrea <manamana88@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Robert Kirscht <rkirscht242@gmail.com>
Co-authored-by: Imgyu Kim <kimimgo@gmail.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
2026-03-21 12:40:11 -07:00
Sameer Kankute
4f1e484a9b Merge branch 'main' into litellm_dev_sameer_16_march_week
Resolve conflicts in common_request_processing.py (keep main streaming,
post_call_success_hook try/finally, deferred logging; retain skip_pre_call_logic)
and utils.py (defer + internal-call skip + sync success callbacks for all calls).

Tighten _has_post_call_guardrails for event_hook=None; align deferred
guardrail test. Sync model_prices_and_context_window_backup.json.

Pyright: narrow ignores for passthrough StreamingResponse and post_call hook.
Made-with: Cursor
2026-03-22 00:29:38 +05:30
Krrish Dholakia
0091d048dc fix: make reasoning summary opt-in, fix missing injection path, narrow test exceptions
Address Greptile review feedback:
1. Replace opt-out `disable_default_reasoning_summary` with existing opt-in
   `reasoning_auto_summary` flag — avoids backwards-incompatible change where
   all users routing thinking-enabled requests would silently get a changed
   reasoning_effort shape (string -> dict) on upgrade.
2. Add default summary injection to `_translate_thinking_to_openai` — this path
   was the only one missing it, causing inconsistent behavior for
   litellm.completion() callers using the Anthropic adapter.
3. Narrow `except Exception` to `except (ValueError, TypeError, AttributeError)`
   in tests to avoid masking genuine failures.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 11:36:26 -07:00
Krish Dholakia
a5b7e49713
Merge branch 'main' into litellm_oss_staging_03_17_2026 2026-03-21 10:40:48 -07:00
Krish Dholakia
c350d08d66
Merge branch 'main' into litellm_oss_staging_03_05_2026 2026-03-21 10:31:50 -07:00
Krish Dholakia
c8a7d5d237
Merge branch 'main' into docs/prompt-caching-gemini-support 2026-03-21 10:28:39 -07:00
Cesar Garcia
a4f091c025
Merge pull request #24073 from Chesars/feat/gemini-context-circulation
feat(gemini): support context circulation for server-side tool combination
2026-03-20 23:29:30 -03:00
Sameer Kankute
a05824d9ba Fix code qa 2026-03-21 00:14:33 +05:30