scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-20 00:11:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 75
litellm/litellm
History
Deepanshu 38ec960064 fix(proxy): fix key-hash/alias extraction at log time, trim comments, add Lua script tests 
Greptile/Bugbot findings from the first review round:
- extract_key_hash/extract_key_alias only checked the top-level metadata
  bucket, unlike order_tags_for_identity_resolution's _active_metadata_bucket
  helper. By async_log_success_event/async_log_failure_event time, metadata
  is only nested under litellm_params, so both silently returned None there,
  diverging from the value read at admission time. Fixed by routing both
  through _active_metadata_bucket, with regression tests for the nested case.
- Condensed the module's docstrings/comments to one concise line each,
  keeping the non-obvious behavior they document, matching the trimming
  already applied to litellm/types/router.py on the stacked PR #39900.
- Added real Redis execution coverage for both Lua scripts (admission,
  rejection, ttl refresh semantics, decrement floor) against a throwaway
  local redis-server, since fakeredis has no EVALSHA support without the
  optional lupa dependency.
2026-09-10 14:40:47 -04:00
..
a2a_protocol fix(bedrock): sign on a dedicated executor instead of the shared default one 2026-09-09 18:52:00 -07:00
anthropic_interface fix(anthropic_endpoints): return Anthropic type:error envelope for /v1/messages errors 2026-08-31 16:23:36 -07:00
assistants refactor(typing): replace Any with proven types in 89 more backend files 2026-09-02 23:08:42 +00:00
batch_completion
batches Merge pull request #39626 from BerriAI/litellm_batch_ui_logs 2026-09-08 15:19:25 -07:00
caching refactor: trim excessive source comments in tag rate limit types 2026-09-10 14:21:08 -04:00
completion_extras Merge pull request #40451 from BerriAI/litellm_responses_bridge_replay_encrypted_reasoning 2026-09-09 19:45:11 -07:00
compression refactor(typing): replace Any with proven types in 89 more backend files 2026-09-02 23:08:42 +00:00
containers Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_decrease_anys_opus5_r4 2026-09-02 23:32:10 +00:00
endpoints/speech/speech_to_completion_bridge refactor(speech): freeze httpx response header dicts (LIT002) 2026-08-31 21:12:53 -07:00
evals
experimental_mcp_client fix(mcp): respect optional discovery capabilities and quiet unsupported methods 2026-09-09 20:21:19 -07:00
files test(batches): use immutable expectations with explicit test doubles 2026-09-07 16:36:27 -07:00
fine_tuning refactor(typing): replace Any with proven types in 89 more backend files 2026-09-02 23:08:42 +00:00
google_genai refactor(types): replace Any with precise types across 73 modules 2026-09-01 11:05:02 +00:00
images refactor(typing): replace Any with proven types in 89 more backend files 2026-09-02 23:08:42 +00:00
integrations feat(pointfive): add pointfive to the dashboard logging integrations 2026-09-10 14:02:35 +03:00
interactions refactor(typing): replace Any with proven types in 42 more backend files 2026-09-02 15:35:01 +00:00
litellm_core_utils Merge pull request #38509 from yinonkahta-p5/litellm_pointfive_logger 2026-09-10 10:26:51 -07:00
llms Merge pull request #39237 from BerriAI/litellm_fix_dashscope_rerank_endpoint 2026-09-10 10:31:48 -07:00
models Merge pull request #39626 from BerriAI/litellm_batch_ui_logs 2026-09-08 15:19:25 -07:00
ocr test(ocr): add SDK callback E2E parity (#40061) 2026-09-07 11:23:12 -07:00
passthrough Merge origin/litellm_internal_staging into litellm_techdebt_20260901 2026-09-01 19:38:19 +00:00
proxy fix(proxy): fix key-hash/alias extraction at log time, trim comments, add Lua script tests 2026-09-10 14:40:47 -04:00
proxy_auth
rag chore: merge origin/litellm_internal_staging into litellm_decrease_anys_opus5_r4 2026-09-04 18:59:35 -07:00
realtime_api Merge pull request #39851 from BerriAI/litellm_fix_realtime_backend_close_hang 2026-09-05 09:51:15 -07:00
repositories fix(router): serialize heuristic tuning quota filters for Prisma 2026-09-07 10:08:19 -07:00
rerank_api fix(rerank): adopt declared authenticating providers in arerank instead of resolving them 2026-09-01 14:47:59 -07:00
responses Merge pull request #40462 from BerriAI/litellm_fix_responses_stream_named_tool_choice 2026-09-09 18:48:32 -07:00
router_strategy Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_lit_5546_count_tokens_offload 2026-09-09 18:18:17 -07:00
router_utils Merge pull request #39863 from BerriAI/litellm_lit_7022_azure_ai_passthrough_config 2026-09-09 20:56:57 -07:00
rust_bridge refactor(rust): remove per-request enablement arguments (#39928) 2026-09-07 10:43:45 -07:00
sandbox
search fix(search): forward search-tool params through the router, complete Parallel AI v1 param mapping (#37883) 2026-09-01 21:46:46 -07:00
secret_managers chore: merge origin/litellm_internal_staging into litellm_decrease_anys_opus5_r4 2026-09-04 18:59:35 -07:00
skills feat(skills): semantic search over the LiteLLM-hosted skill registry (#39401) 2026-09-07 12:28:38 -07:00
types fix: reject empty tag_id on TagRateLimitScope and TagRateLimitEntry 2026-09-10 14:21:08 -04:00
vector_store_files refactor(typing): replace Any with proven types in 42 more backend files 2026-09-02 15:35:01 +00:00
vector_stores Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_python_version_ci 2026-09-03 00:16:19 -07:00
videos
__init__.py feat(pointfive): add batching logger callback 2026-09-10 14:02:35 +03:00
_internal_context.py fix(proxy): price one cost estimate at one moment 2026-09-07 18:38:12 -07:00
_lazy_imports.py fix(lazy_imports): type import_map as Mapping to stay under the LIT001 budget 2026-09-05 16:12:45 -07:00
_lazy_imports_registry.py Revert "perf: lazy-load SDK symbols so import litellm stays under 60 MB RSS (…" 2026-09-05 16:07:09 -07:00
_logging.py fix(proxy): stop leaking internal exception details to clients (#39380) 2026-09-02 17:32:00 -07:00
_redis.py fix(redis): coerce env var string types and fix param discovery through decorator wrappers (#30644) 2026-08-31 20:51:31 -07:00
_redis_credential_provider.py refactor(typing): replace Any with proven types in 89 more backend files 2026-09-02 23:08:42 +00:00
_service_logger.py chore: merge origin/litellm_internal_staging into litellm_decrease_anys_opus5_r4 2026-09-04 18:59:35 -07:00
_uuid.py
_version.py
anthropic_beta_headers_config.json
anthropic_beta_headers_manager.py
blog_posts.json
budget_manager.py
constants.py fix(proxy): bound concurrent key and spend-counter DB lookups to stop prisma pool thrash (#40387) 2026-09-10 05:44:30 +00:00
cost.json
cost_calculator.py Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_cost_estimate_cache_tokens 2026-09-09 10:05:48 -07:00
exceptions.py fix(bedrock): keep x-amzn-RequestId on chat error responses (#40089) 2026-09-07 17:16:47 -07:00
main.py Merge branch 'litellm_internal_staging' into litellm_lit_7022_azure_ai_passthrough_config 2026-09-09 19:35:55 -07:00
model_prices_and_context_window_backup.json fix(model_prices): registry audit 2026-09-10, absorb open pricing PRs 2026-09-10 13:17:14 +00:00
policy_templates_backup.json
provider_endpoints_support_backup.json fix(ocr): send each provider a health-check document it accepts 2026-09-04 22:52:12 -07:00
py.typed
router.py Merge branch 'litellm_internal_staging' into litellm_lit_7022_azure_ai_passthrough_config 2026-09-09 19:35:55 -07:00
scheduler.py
setup_wizard.py feat(models): add Claude Fable 5.1 across Anthropic, Bedrock, Vertex AI, and Azure AI 2026-09-01 18:07:06 +00:00
timeout.py
utils.py Merge branch 'litellm_internal_staging' into litellm_lit_7022_azure_ai_passthrough_config 2026-09-09 19:35:55 -07:00