scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-18 04:44:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 125
litellm/litellm
History
Peter Boers 665c5afdbd
fix(a2a): suppress a terminal snapshot that repeats only the reply's tail 
Snapshot detection assumed a terminal snapshot extends everything already
emitted. That holds for an agent that only ever speaks for itself, but not for
one that delegates: it reports sub-agent progress into the same task before
answering, so its closing status-update and artifact-update carry just the
answer. That extends nothing, escapes the prefix test, and the reply renders
three times over - once from the deltas, once from the status-update and once
from the artifact.

Read text that merely repeats the tail of what has been delivered as a snapshot
as well. A whitespace-only event has an empty comparison key and would match any
tail, so it is excluded and still emitted as a delta.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-10-06 10:44:06 +02:00
..
_v2 feat(cache): select Rust caching through explicit cache objects (#43601) 2026-09-29 00:01:44 +00:00
a2a_protocol refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
anthropic_interface fix(proxy): send a real error event when a /v1/messages stream fails (#41826) 2026-09-25 15:36:35 -07:00
assistants refactor(types): replace Any with proven types in 5 files (#43304) 2026-09-27 01:28:02 -07:00
batch_completion
batches feat(anthropic): workload identity federation and pluggable identity sources (#44448) 2026-10-03 17:08:30 -07:00
caching perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
chat_completions refactor(rust): remove delivery routing abstraction (#43514) 2026-09-28 03:31:22 +00:00
completion_extras fix(responses): honor request cache controls on chat completions bridged to the Responses API (#44676) 2026-10-05 17:52:44 -07:00
compression merge: main into litellm_headroom_protect_cached_prefix 2026-09-15 04:12:28 +00:00
containers test: finish the non-proxy half of tests/test_litellm (#43281) 2026-09-25 22:43:41 -07:00
decisions refactor: clean up fresh tech debt from 2026-10-03 (#44484) 2026-10-04 01:31:23 -07:00
embeddings feat(embeddings): add native dispatch foundation (#42799) 2026-09-23 21:11:09 +00:00
endpoints/speech/speech_to_completion_bridge
evals
experimental_mcp_client fix(mcp): preserve upstream tool schemas and parameter headers (#44425) 2026-10-03 15:00:43 -07:00
files refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
fine_tuning
google_genai perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
harness perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
images fix(vertex_ai): apply regional endpoint uplift on image generation cost path (#44679) 2026-10-05 20:02:22 -07:00
integrations perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
interactions perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
litellm_core_utils perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
llms fix(a2a): suppress a terminal snapshot that repeats only the reply's tail 2026-10-06 10:44:06 +02:00
messages refactor(rust): remove delivery routing abstraction (#43514) 2026-09-28 03:31:22 +00:00
models perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
ocr refactor(ocr): remove the Python OCR execution path and require the Rust route (#43081) 2026-09-24 18:18:50 -07:00
passthrough fix(responses): fall back on pre-output stream drops, fail truncated streams, honor request_timeout (#43133) 2026-09-25 14:32:41 -07:00
proxy fix(proxy): resolve a2a/ models before router branches can claim them 2026-10-06 10:37:12 +02:00
proxy_auth refactor(types): replace Any with real types across 29 more backend files 2026-09-08 10:14:07 +00:00
rag perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
realtime_api refactor(types): replace Any with proven types in 13 files (#42937) 2026-09-24 09:02:02 -07:00
repositories refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
rerank_api feat(lint): add LIT013 flagging *-ok suppressions that suppress nothing and remove the 240 stale ones (#42793) 2026-09-23 17:50:09 -07:00
responses perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
router_strategy perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
router_utils fix(router): retry a /v1/messages stream the provider drops before the first content chunk (#44276) 2026-10-05 22:53:39 +00:00
rust_bridge perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
sandbox feat: add litellm.agent() to run claude code, codex, opencode and deep agents through the ai gateway (#43885) 2026-10-01 22:27:49 +00:00
search
secret_managers perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
skills
tracing fix(lens): reconstruct native coding agent conversations (#44711) 2026-10-05 17:51:05 -07:00
types perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
vector_store_files refactor(types): replace Any with real types across 54 more backend files 2026-09-08 12:41:07 +00:00
vector_stores refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
videos
__init__.py feat(prometheus): cap series per metric for every labeled metric (#44420) 2026-10-06 01:28:44 +00:00
_internal_context.py fix(otel): nest cache spans under their operation and name service spans by purpose (#44150) 2026-10-03 09:20:27 -07:00
_lazy_imports.py perf(proxy): stop prompt-cache eligibility from tokenizing the whole conversation (#44221) 2026-10-03 09:20:28 -07:00
_lazy_imports_registry.py feat(scaleway): add rerank support (#44160) 2026-10-02 21:20:05 -07:00
_logging.py chore(lint): remove the LIT002 mutable-construction rule (#43971) 2026-10-01 12:24:02 -07:00
_redis.py chore(lint): remove the LIT002 mutable-construction rule (#43971) 2026-10-01 12:24:02 -07:00
_redis_credential_provider.py fix(redis): accept every truthy flag and sign serverless ElastiCache caches 2026-09-10 10:13:03 -04:00
_service_logger.py fix(otel): nest cache spans under their operation and name service spans by purpose (#44150) 2026-10-03 09:20:27 -07:00
_uuid.py
_version.py
anthropic_beta_headers_config.json fix(providers): keep thinking display updates beta (#43969) 2026-10-01 17:42:02 -07:00
anthropic_beta_headers_manager.py refactor(types): move SpanAttributes, SpecialHeaders and AllowedModelRegion out of proxy._types (#44717) 2026-10-05 21:40:13 -07:00
blog_posts.json
budget_manager.py
constants.py perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
cost.json
cost_calculator.py perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
exceptions.py fix(spend): return 400 from /spend/calculate for a model with no pricing row (#42497) 2026-09-22 15:44:00 -07:00
main.py perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
model_prices_and_context_window_backup.json fix(vertex_ai): add regional endpoint uplift to gemini-3.1-flash-image (#44673) 2026-10-05 21:00:22 -07:00
policy_templates_backup.json fix(packaging): keep wheel paths under Windows MAX_PATH for Store Python (#43903) 2026-09-30 22:20:36 +00:00
provider_endpoints_support_backup.json feat: add Reka as an OpenAI-compatible provider (#44278) 2026-10-05 17:47:23 -07:00
py.typed
router.py fix(router): price a model group from the deployments that serve it (#44732) 2026-10-06 05:31:09 +00:00
scheduler.py perf(types): defer pydantic schema builds via shared LiteLLMBaseModel (#44720) 2026-10-05 22:10:08 -07:00
setup_wizard.py fix(model_prices): correct Claude Sonnet 5.5 capabilities and provider keys (#43587) 2026-09-28 19:12:31 +00:00
timeout.py
tool_loop.py feat(sdk): add run_tool_loop and arun_tool_loop helpers (#44381) 2026-10-03 20:10:30 -07:00
utils.py refactor(types): move SpanAttributes, SpecialHeaders and AllowedModelRegion out of proxy._types (#44717) 2026-10-05 21:40:13 -07:00