The gate at three call sites was calling _supports_factory with
custom_llm_provider=None, which relies on get_llm_provider inferring the
provider from the model string. For the invoke path, the model still
carries an 'invoke/' routing prefix (e.g. 'invoke/us.anthropic.claude-opus-4-6-v1')
that is not a known provider, so inference raises BadRequestError,
_supports_factory swallows it and returns False, and the user's
output_config.effort gets silently dropped before the Bedrock request.
Strip the routing prefix with the existing strip_bedrock_routing_prefix
helper and pass custom_llm_provider='bedrock' explicitly so the
declarative 'supports_output_config' flag in
model_prices_and_context_window.json is the actual source of truth.
Also adds a regression test that exercises the full
'invoke/us.anthropic.claude-opus-4-6-v1' path and asserts output_config
survives.
The partner/gemma/model-garden handlers now call self._ensure_access_token
(inherited from VertexBase) instead of instantiating VertexLLM, so tests
must patch VertexBase._ensure_access_token for the mock to take effect.
- preserve existing shared backend `mode` when router deployment registration
reuses a provider/model key already in `litellm.model_cost` (prevents alias
with `mode: chat` from downgrading shared `chatgpt/gpt-5.4` from `responses`
to `chat` and triggering 403s on /v1/chat/completions)
- teach the ChatGPT Responses parser to recover `response.output_item.done`
entries when `response.completed.output` is empty
- add defensive /responses -> /chat/completions bridge fallback that
reconstructs output items from raw SSE when `raw_response.output` is empty
- regression coverage for shared alias routing, empty completed.output
parsing, and SSE bridge recovery
Closes#25403
Co-authored-by: afoninsky <andrey.afoninsky@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: reuse cached credentials in VertexAIPartnerModels instead of creating new VertexLLM per request
VertexAIPartnerModels.completion() was creating a throwaway VertexLLM()
instance on every call to get an access token, bypassing the credential
cache inherited from VertexBase. This caused a fresh token fetch for
every single request, adding significant latency overhead.
Fix: call super().__init__() to initialize VertexBase's credential cache,
and use self._ensure_access_token() instead of a new VertexLLM instance.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: apply same credential caching fix to VertexAIGemmaModels and VertexAIModelGardenModels
Same bug as VertexAIPartnerModels: both classes had `pass` in __init__
instead of `super().__init__()`, and created throwaway VertexLLM()
instances per request instead of using self._ensure_access_token().
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(vertex_ai): single-flight credential refresh to prevent thundering herd
When GCP credentials expire under high concurrency, all requests
simultaneously call credentials.refresh() via asyncify, saturating the
40-thread anyio pool and blocking the proxy for 20+ seconds.
This adds:
- Per-credential asyncio.Lock in get_access_token_async for single-flight
refresh (1 coroutine refreshes, others wait on the lock)
- Background refresh when token_state is STALE (usable but near expiry),
returning the current token immediately with zero added latency
- threading.Lock on the sync get_access_token path
- Uses google-auth's TokenState enum (FRESH/STALE/INVALID) instead of
reimplementing expiry logic
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: address PR review comments
- Use asyncio.create_task() instead of deprecated get_event_loop().create_task()
- Track in-flight background refresh tasks to prevent duplicate refreshes
when multiple STALE-path callers pass through the lock before the first
background task completes
- Add token validation in the STALE branch (consistent with FRESH/INVALID)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: lazy-import TokenState to avoid breaking when google-auth is not installed
Also extract helper methods to bring get_access_token_async under the
PLR0915 statement limit (50).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* chore: apply Black formatting to test file and update uv.lock
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: remove user-provided project_id from log messages (CodeQL log injection)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: avoid leaking token value in error message, log type instead
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* chore: restore uv.lock to match litellm_oss_branch
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: remove project_id from remaining log message (CodeQL log injection)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: remove remaining project_id from log and error messages
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace hardcoded _is_claude_4_6_model() string matching with
supports_output_config flag in model_prices_and_context_window.json,
accessed via _supports_factory(). This follows the project's established
pattern for model capability checks (per AGENTS.md rule #8).
Bedrock Invoke now conditionally preserves output_config for models
that declare supports_output_config=true (currently Claude 4.6 models),
while stripping it for older models to avoid request rejection.
Ref: https://github.com/BerriAI/litellm/issues/22797
Vertex multi-region endpoints (e.g. us, eu) use the rep host pattern, not
{geo}-aiplatform.googleapis.com. Regional IDs still contain a hyphen.
common_utils.get_vertex_base_url centralizes the rule for SDK/API URL building.
Proxy pass-through duplicates the same branching in a local get_vertex_base_url
(with trailing slashes) to avoid importing from common_utils there; live
WebSocket passthrough uses the same multi-region host logic for wss://.
Tests cover us/eu for the common_utils helper.
Made-with: Cursor
* feat: add gpt-5.5 to model cost map
Add gpt-5.5 entry with pricing from OpenAI flagship page:
input $5/1M, cached input $0.50/1M, output $30/1M, 272K context.
* test: add gpt-5.5 coverage for model cost map and gpt-5 routing
- Add gpt-5.5 to GPT5_MODELS parametrized list so both OpenAIGPT5Config
and AzureOpenAIGPT5Config routing tests cover the new model.
- Add test_generic_cost_per_token_gpt55 verifying the new entry's
cost-map values ($5/$0.50/$30 per 1M) and that generic_cost_per_token
returns the expected prompt/completion costs.
The original check `"gpt-5-chat" not in model` already correctly
classifies all current gpt-5 variants (including gpt-5.3-chat and
gpt-5.1-chat, which do NOT contain the substring "gpt-5-chat"). This
change replaces it with an explicit `startswith("gpt-5-chat")` prefix
test on the provider-prefix-stripped model name.
The new check is functionally equivalent for all existing model names
but makes the classification boundary unambiguous and forward-safe:
future model names that might contain "gpt-5-chat" as an interior
substring won't accidentally be excluded from the GPT-5 reasoning path.
Also moves the new regression test from tests/ root to
tests/test_litellm/llms/openai/ so it is included in `make test-unit`.
* fix(anthropic): handle tool_choice type 'none' in messages API
* test(anthropic): add regression test for tool_choice type 'none'
---------
Co-authored-by: BillionClaw <267901332+BillionClaw@users.noreply.github.com>
Co-authored-by: Krrish Dholakia <krrish+github@berri.ai>
When reasoning_auto_summary is enabled (via litellm_settings or env var),
automatically set thinking.display="summarized" on native /v1/messages
requests. This ensures thinking content is returned in the response
instead of being omitted (the default on Claude 4.7+).
Only applies when thinking is enabled (type != "disabled").
The existing reasoning_auto_summary flag already handles the
/v1/responses path (summary="detailed") and the chat/completions
adapter path — this extends coverage to the native messages handler.
* fix(model-info): include reasoning effort support fields in get_model_info
_get_model_info_helper constructs ModelInfoBase explicitly but never
reads supports_xhigh/minimal/none_reasoning_effort from the cost map
JSON. Add the three fields so get_model_info() returns them correctly.
Also add supports_minimal_reasoning_effort to the ModelInfo TypedDict
(xhigh and none were already declared, minimal was missing).
* fix(model-registry): add missing reasoning effort fields for claude 4.6/4.7
Claude Opus 4.7 supports max reasoning effort (above xhigh).
The field was present for Opus 4.6 but missing for all Opus 4.7
entries (base, dated, Bedrock, Vertex AI, Azure AI).
All Claude 4.6/4.7 models (Opus 4.6, Sonnet 4.6, Opus 4.7) support
minimal reasoning effort via adaptive thinking. Add the field to all
provider variants.
* fix(adapter): map output_config.effort to reasoning_effort (#25079)
Anthropic's adaptive thinking (thinking.type="adaptive") and
output_config.effort were silently dropped when translating to
OpenAI format, resulting in no reasoning_effort on the outgoing
request.
Adapter changes (format translation):
- adapters/transformation.py: add "adaptive" branch to
translate_anthropic_thinking_to_reasoning_effort(); pass through
output_config.effort as-is in _translate_thinking_to_openai();
add "output_config" to translatable_anthropic_params
- adapters/handler.py: extract output_config from extra_kwargs into
request_data so it reaches the translation layer
- responses_adapters/transformation.py: add "adaptive" branch and
output_config param to translate_thinking_to_reasoning()
Handler changes (model-aware normalization):
- utils.py: add normalize_reasoning_effort_value() that uses
get_model_info() to map "max" → "xhigh"/"high" and
"minimal" → "minimal"/"low" based on model capabilities
- adapters/handler.py: call normalization before responses routing
- responses_adapters/handler.py: call normalization after translation
Relates to BerriAI/litellm#25079
* test(reasoning-effort): add tests for effort capability fields and normalize logic
Test coverage for:
- get_model_info returning supports_minimal/max_reasoning_effort fields
- JSON registry entries for claude 4.6/4.7 across all providers
- normalize_reasoning_effort_value degradation chains and exception fallback
- Adapter translation of adaptive thinking + output_config.effort
* fix: forward custom_llm_provider to normalize_reasoning_effort_value in responses adapter
* add moonshot/kimi-k2.6 to model registry
* add moonshot/kimi-k2.6 to backup model registry
* add tests for moonshot/kimi-k2.6 model registry
* fix moonshot/kimi-k2.6 pricing and add reasoning support
* fix moonshot/kimi-k2.6 pricing and add reasoning support in backup
* update kimi-k2.6 tests: fix pricing, add tool_choice and reasoning checks
* fix: load kimi-k2.6 registry tests from local backup instead of remote cost map
Two fail-safes for the /v1/messages → Bedrock Invoke pass-through so new
Anthropic-only extensions Claude Code starts sending can't reach Bedrock
and trigger a 400 "Extra inputs are not permitted":
1. Top-level body fields are filtered to a typed allowlist. New
`BedrockInvokeAnthropicMessagesRequest` TypedDict (in
`litellm/types/llms/bedrock.py`) captures the Bedrock Invoke Anthropic
Messages body schema; the runtime allowlist is derived from its
`__annotations__` so the type and the filter can't drift. Anchored to
the AWS reference page in docstrings + transform comment. An
exact-set test pins the resolved allowlist so any future edit forces
conscious review.
Drops context_management, output_config, speed, mcp_servers,
container, inference_geo, internal litellm_metadata, and any future
Anthropic addition. output_format stays as an active inline-schema
conversion (not just a strip).
2. The anthropic-beta header list is filtered + transformed against the
bedrock mapping for ALL betas, not just auto-injected ones. The
previous code union'd user-provided betas back in unfiltered, so a
client on a new Anthropic-direct beta (e.g. advisor-tool-…,
context-management-…) could still pin the request to fail. In a proxy
context the client can't know the backend is Bedrock; the provider
mapping is authoritative. User-provided drops are logged at WARNING
so intentional overrides leave a breadcrumb.
Updates one existing test that happened to assert on the old buggy
pass-through (it used output-128k-2025-02-19, which is null in the
bedrock mapping and would 400 at runtime); rewrote it against a
bedrock-supported beta.
Scope: messages/invoke only. The same user-beta bypass exists in
chat/invoke but that's a different code path with different
user-expectation trade-offs — follow-up.
* feat(router): add auto_router/quality_router for quality-tier routing (#25987)
* feat(router): add auto_router/quality_router for quality-tier routing
Adds a new auto-router type that routes a request to a model at a target
quality tier. The quality tier is inferred by re-using the existing
ComplexityRouter's classification, then mapped through an admin-configured
complexity_to_quality table. Each candidate model declares its own
quality_tier in model_info.litellm_routing_preferences.
Resolution strategy: exact tier match, else round up to the next higher
tier, else fall back to default_model.
Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
* feat(quality_router): add capability-based filtering
Each deployment can declare a `capabilities: List[str]` field in
`model_info.litellm_routing_preferences` (e.g. ["vision",
"function_calling"]). Requests can pass `litellm_capabilities` in
`request_kwargs` to require specific capabilities — the router will only
route to deployments whose declared capabilities are a superset.
Resolution still walks tier (exact → round up), but at each tier filters
by capability before picking. Falls back to default_model only when it
also satisfies the required capabilities; otherwise raises rather than
silently routing to a model that lacks a required capability.
Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
* feat(quality_router): expose routing decision in response headers
For transparency, expose the QualityRouter's routing decision in the
proxy response headers:
x-litellm-quality-router-model → picked model_name (e.g. "haiku-vision")
x-litellm-quality-router-tier → resolved quality tier (e.g. "1")
x-litellm-quality-router-complexity → ComplexityTier name (e.g. "SIMPLE")
Mechanism: the pre-routing hook stashes the decision in
request_kwargs["metadata"]["quality_router_decision"]. After the call
returns, Router.set_response_headers lifts the decision into
response._hidden_params["additional_headers"] alongside the existing
x-litellm-model-group / x-litellm-model-id headers. Existing metadata
keys (trace_id, user_id, etc.) are preserved.
Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
* feat(quality_router): replace capabilities with keyword override
Drops the capability-based filtering in favor of a keyword-based override
for v0:
- RoutingPreferences.keywords: List[str] (replaces capabilities) — each
deployment can declare substring keywords.
- If any declared keyword (case-insensitive) appears in the user message,
the router short-circuits the complexity-classification flow and routes
to the matching deployment.
- Tiebreaker for overlapping keyword matches: quality_tier DESC, then
cheapest model_info.input_cost_per_token ASC. Unpriced models lose ties
to priced ones.
Decision metadata + headers now expose the override:
x-litellm-quality-router-via → "keyword" | "quality_tier"
x-litellm-quality-router-keyword → matched keyword (only on keyword route)
x-litellm-quality-router-complexity → complexity tier (only on tier route)
Removes:
- request_kwargs["litellm_capabilities"] reading
- _model_capabilities, _model_supports_capabilities,
_first_capable_model_at_tier, capability filter in
_resolve_model_for_quality_tier
Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
* feat(quality_router): add explicit `order` to RoutingPreferences
Adds an explicit priority field to RoutingPreferences for resolving
collisions deterministically:
RoutingPreferences.order: Optional[int] # lower wins; unset = +inf
Used as the PRIMARY tiebreaker in two places:
1. Keyword overlap: when multiple deployments declare the same matching
keyword, sort by (order ASC, quality_tier DESC, input_cost_per_token
ASC, model_name ASC). Explicit always beats implicit.
2. Tier resolution: when multiple deployments share a quality tier,
`_resolve_model_for_quality_tier` picks the one with the lowest
order. The tier list is now sorted at index-build time.
This lets admins make routing decisions explicit when the natural
quality-and-price ordering would pick the wrong model.
Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
* feat(quality_router): reorder tiebreak to (quality, order, price)
Changes the tiebreak ordering so quality_tier always wins first, then
explicit `order` is used to break ties within the same tier, then price
breaks the rest:
1. quality_tier DESC ← best model wins first
2. order ASC ← explicit priority within a tier
3. input_cost_per_token ASC
4. model_name ASC
Previously `order` was the primary key — that meant a tier-2 model with
`order=1` would beat a tier-3 model with no `order`, which is the wrong
default. Now `order` only resolves collisions among same-tier candidates.
Tier resolution (within a single tier) keeps the same key minus quality:
(order ASC, cost ASC, name).
Test renames + flips:
- test_explicit_order_overrides_quality_tier → test_quality_wins_over_explicit_order
- new: test_order_breaks_tie_within_same_quality_tier
Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
* fix(quality_router): resolve Greptile review feedback
Addresses four P1 findings from PR review plus test coverage:
1. set_model_list missing quality_routers reset
- Hot-reloading the Router would leave stale QualityRouter instances
pointing at the old model_list. `set_model_list` now clears
`self.quality_routers` alongside the other indices.
2. Round-down fallback before default_model
- `_resolve_model_for_quality_tier` now rounds DOWN to the closest
lower tier after round-up fails, before falling back to
`default_model`. Degrades gracefully rather than jumping straight
off-tier.
3. RoutingPreferences validation bypass
- `_build_tier_index` now instantiates `RoutingPreferences(**prefs)`
so invalid shapes (e.g. non-int quality_tier) raise a clear
ValueError instead of silently succeeding.
4. Config-ordering dependency
- `_tier_to_models` is now built lazily on first access. Previously,
eager construction in `__init__` meant a QualityRouter deployment
had to appear AFTER all its referenced models in config.yaml,
because `Router._create_deployment` populates `model_list`
incrementally. Any `available_models` defined after the router
entry would silently be reported as missing.
Also adds 6 new tests covering each fix:
- test_invalid_quality_tier_type_raises_clear_error
- test_router_can_be_instantiated_before_its_targets_exist
- test_set_model_list_clears_quality_routers_registry
- test_rounds_down_when_no_higher_tier_exists
- test_rounds_down_prefers_closest_lower_tier
- test_prefers_round_up_over_round_down
Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
* style: apply black 24.10.0 formatting to pre-existing offenders
Unblocks the LiteLLM Linting check for this PR — these 12 files are already
failing `black --check` on main (the lint workflow only runs on PRs, so main
drifts). No behavior changes; formatting-only.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* Update litellm/router.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
---------
Co-authored-by: Claude Opus 4 (1M context) <noreply@anthropic.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* Support /v1/responses in complexity router (#26137)
* feat(proxy): add --reload flag for uvicorn hot reload (dev only)
Opt-in CLI flag, off by default, no env var. Only affects the uvicorn
run path; gunicorn/hypercorn paths and prod (which doesn't pass the
flag) are unaffected.
* Feature/add audio support for scaleway (#26110)
* feat(scaleway): add SCALEWAY to LlmProviders enum
* feat(scaleway): add audio transcription config and dispatch wiring
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test(scaleway): add behavior tests for audio transcription config
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(scaleway): advertise audio_transcriptions in endpoint-support JSON
* docs(scaleway): document audio transcription support
* fix(scaleway): address PR review — plain-text response_format + missing-key fail-fast
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test(scaleway): cover new response paths, drop gettysburg.wav coupling
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* Prompt Compression - add it to the proxy (#25729)
* refactor: new agentic loop event hook
simplifies how to create logic for tool based multi llm calls
* fix: compress - make it work on anthropic input as well
* fix(compress.py): working prompt compression for claude code
ensures claude code messages can run through proxy easily
* docs: add agentic loop hook guide
* docs: add agentic_loop_hook to sidebar
* fix: fix multiple arguments error
* fix: fix tool call loop for compression on streaming /v1/messages
* fix: fix linting errors
* fix: fix ci/cd errors
* feat(litellm_pre_call_utils.py): use claude code session for litellm session id
allows claude code logs to be stitched together, making it easy to know they were all part of the same conversation
* fix: suppress incorrect mypy warning rE: module
* revert: drop PR's changes to litellm/proxy/_experimental/out/
Restores the 34 HTML files under _experimental/out/ to their pre-PR
paths (X/index.html -> X.html). All renames are R100 (content
unchanged); no other files are touched.
* fix: address greptile review comments on PR #25729
- Skip ``kwargs["tools"] = []`` injection when compression is a no-op —
Anthropic Messages rejects empty tool arrays on requests that did not
originally declare tools.
- Move agentic-loop safety guards (fingerprint cycle / max depth) out of
the per-callback try/except so they propagate instead of being swallowed
by the generic exception handler. Extracted _check_agentic_loop_safety.
- Gate generic ``x-<vendor>-session-id`` capture behind the
LITELLM_CAPTURE_VENDOR_SESSION_HEADERS env var (off by default) to
preserve backwards compatibility; explicit x-litellm-* headers are
unaffected.
- Fix monkeypatch target in pre-call-hook test to patch the actual
module-level binding
(litellm.integrations.compression_interception.handler.compress).
- Add regression tests for empty-tools skip and opt-in session capture.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* revert: drop LITELLM_CAPTURE_VENDOR_SESSION_HEADERS flag
Generic x-<vendor>-session-id header capture is a new feature and only
runs *after* the explicit x-litellm-trace-id / x-litellm-session-id
checks, so it does not change behavior for any existing caller that was
already using the LiteLLM headers — no backwards-incompatibility to gate.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor(compress): replace input_type with CallTypes call_type
Drop the bespoke ``CompressionInputType`` literal and use the existing
``litellm.types.utils.CallTypes`` enum instead. ``litellm.compress()``
now takes ``call_type: Union[CallTypes, str]`` (default
``CallTypes.completion``) — no new concept to learn, and the enum is
already the way the rest of the codebase talks about request shapes.
Supported values: ``completion`` / ``acompletion`` (OpenAI chat-completions
shape) and ``anthropic_messages`` (Anthropic structured content blocks).
Updated: compress(), the compression_interception handler, tests, docs,
and the two eval scripts.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* Support /v1/responses in complexity router
Adds cross-format support to the complexity router via the guardrail
translation handler dispatch. Adds get_structured_messages to base
translation plus OpenAI chat, Responses, and Anthropic handlers.
Auto-router helper _extract_text_from_messages handles tool-call and
multimodal messages. Widens async_pre_routing_hook messages type to
Dict[str, Any].
Fixes https://github.com/BerriAI/litellm/issues/25134
* chore: apply black formatting
* fix: fallback to trying each handler when route inference fails
---------
Co-authored-by: Ryan Crabbe <ryan@berri.ai>
Co-authored-by: nhyy244 <106547304+nhyy244@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* test: cover _is_quality_router_deployment and init_quality_router_deployment
* fix: reset auto_routers on set_model_list to prevent hot-reload ValueError
* style: apply black formatting to websearch_interception and agentic_streaming_iterator
---------
Co-authored-by: yuneng-jiang <yuneng@berri.ai>
Co-authored-by: Claude Opus 4 (1M context) <noreply@anthropic.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: Ryan Crabbe <ryan@berri.ai>
Co-authored-by: nhyy244 <106547304+nhyy244@users.noreply.github.com>
* refactor: new agentic loop event hook
simplifies how to create logic for tool based multi llm calls
* fix: compress - make it work on anthropic input as well
* fix(compress.py): working prompt compression for claude code
ensures claude code messages can run through proxy easily
* docs: add agentic loop hook guide
* docs: add agentic_loop_hook to sidebar
* fix: fix multiple arguments error
* fix: fix tool call loop for compression on streaming /v1/messages
* fix: fix linting errors
* fix: fix ci/cd errors
* feat(litellm_pre_call_utils.py): use claude code session for litellm session id
allows claude code logs to be stitched together, making it easy to know they were all part of the same conversation
* fix: suppress incorrect mypy warning rE: module
* revert: drop PR's changes to litellm/proxy/_experimental/out/
Restores the 34 HTML files under _experimental/out/ to their pre-PR
paths (X/index.html -> X.html). All renames are R100 (content
unchanged); no other files are touched.
* fix: address greptile review comments on PR #25729
- Skip ``kwargs["tools"] = []`` injection when compression is a no-op —
Anthropic Messages rejects empty tool arrays on requests that did not
originally declare tools.
- Move agentic-loop safety guards (fingerprint cycle / max depth) out of
the per-callback try/except so they propagate instead of being swallowed
by the generic exception handler. Extracted _check_agentic_loop_safety.
- Gate generic ``x-<vendor>-session-id`` capture behind the
LITELLM_CAPTURE_VENDOR_SESSION_HEADERS env var (off by default) to
preserve backwards compatibility; explicit x-litellm-* headers are
unaffected.
- Fix monkeypatch target in pre-call-hook test to patch the actual
module-level binding
(litellm.integrations.compression_interception.handler.compress).
- Add regression tests for empty-tools skip and opt-in session capture.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* revert: drop LITELLM_CAPTURE_VENDOR_SESSION_HEADERS flag
Generic x-<vendor>-session-id header capture is a new feature and only
runs *after* the explicit x-litellm-trace-id / x-litellm-session-id
checks, so it does not change behavior for any existing caller that was
already using the LiteLLM headers — no backwards-incompatibility to gate.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor(compress): replace input_type with CallTypes call_type
Drop the bespoke ``CompressionInputType`` literal and use the existing
``litellm.types.utils.CallTypes`` enum instead. ``litellm.compress()``
now takes ``call_type: Union[CallTypes, str]`` (default
``CallTypes.completion``) — no new concept to learn, and the enum is
already the way the rest of the codebase talks about request shapes.
Supported values: ``completion`` / ``acompletion`` (OpenAI chat-completions
shape) and ``anthropic_messages`` (Anthropic structured content blocks).
Updated: compress(), the compression_interception handler, tests, docs,
and the two eval scripts.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Fixes SyntaxError at pytest collection time caused by leftover
<<<<<<<, =======, >>>>>>> markers in test_bedrock_common_utils.py.
Keeps the assertion matching the model under test
(claude-haiku-4-5-20251001-v1:0).
Unit Tests: Proxy DB Operations / proxy-db (auth-checks, tests/proxy_unit_tests/test_auth_checks.py tests/proxy_unit_tests/test_user_api_key_auth.py, 20, 8) (push) Waiting to run
Unit Tests: Proxy DB Operations / proxy-db (remaining, tests/proxy_unit_tests --ignore=tests/proxy_unit_tests/test_key_generate_prisma.py --ignore=tests/proxy_unit_tests/test_auth_checks.py --ignore=tests/proxy_unit_tests/test_user_api_key_auth.py, 30, 8) (push) Waiting to run
* Add capability to override default GitHub Copilot authentication endpoints
This feature adds support for GitHub Enterprise subsriptions with custom domain/data ownership (which use a different URL compared to standard accounts)
* Update documentation with new parameters
* Move access token URL and Client ID retrieval outside for loop
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* Fix spurious comment from Greptile review
* Align api_base retrieval behavior across chat and embedding transformations
* Add missing GitHub Copilot client ID parameter in docs
* Update website documentation with newer options for GitHub Enterprise Copilot
* Fix default value for Copilot client ID in docs
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
---------
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Drop test_bedrock_invoke_messages_injects_thinking_for_clear_thinking_context_management.
Its assertion 'interleaved-thinking-2025-05-14' in betas cannot hold because
anthropic_beta_headers_config.json maps that header to null for the bedrock
provider, so filter_and_transform_beta_headers drops it from the auto-added
beta set before anthropic_beta is written to the request.
The adjacent test_bedrock_invoke_messages_skips_thinking_injection_when_already_enabled
already covers the inverse behavior for the same model, so no coverage is lost.
Bedrock rejects clear_thinking_20251015 unless thinking is enabled or adaptive.
Inject minimal extended thinking and interleaved-thinking beta when Claude Code
sends context_management without thinking. Adds unit tests.
Made-with: Cursor
* feat(proxy): add NO_OPENAPI env var to disable /openapi.json endpoint (#25696)
* feat(proxy): add NO_OPENAPI env var to disable /openapi.json endpoint - Fixes#25538
* test(proxy): add tests for _get_openapi_url
---------
Co-authored-by: Progressive-engg <lov.kumari55@gmail.com>
* feat(prometheus): add api_provider label to spend metric (#25693)
* feat(prometheus): add api_provider label to spend metric
Add `api_provider` to `litellm_spend_metric` labels so users can
build Grafana dashboards that break down spend by cloud provider
(e.g. bedrock, anthropic, openai, azure, vertex_ai).
The `api_provider` label already exists in UserAPIKeyLabelValues and
is populated from `standard_logging_payload["custom_llm_provider"]`,
but was not included in the spend metric's label list.
* add api_provider to requests metric + add test
Address review feedback:
- Add api_provider to litellm_requests_metric too (same call-site as
spend metric, keeps label sets in sync)
- Add test_api_provider_in_spend_and_requests_metrics following the
existing pattern in test_prometheus_labels.py
* fix: ensure `litellm_metadata` is attached to `pre_call` guardrail to align with `post_call` guardrail (#25641)
* fix: ensure `litellm_metadata` is attached to pre_call to align with post_call
* refactor: remove unused BaseTranslation._ensure_litellm_metadata
* refactor: module level imports for ensure_litellm_metadata and CodeQL
* fix: update based off of Codex comment
* revert: undo usage of `_guardrail_litellm_metadata`
* feat: add pricing entry for openrouter/google/gemini-3.1-flash-lite-preview (#25610)
* fix(bedrock): skip synthetic tool injection for json_object with no schema (#25740)
When response_format={"type": "json_object"} is sent without a JSON
schema, _create_json_tool_call_for_response_format builds a tool with an
empty schema (properties: {}). The model follows the empty schema and
returns {} instead of the actual JSON the caller asked for.
This patch:
- Skips synthetic json_tool_call injection when no schema is provided.
The model already returns JSON when the prompt asks for it.
- Fixes finish_reason: after _filter_json_mode_tools strips all
synthetic tool calls, finish_reason stays "tool_calls" instead of
"stop". Callers (like the OpenAI SDK) misinterpret this as a pending
tool invocation.
json_schema requests with an explicit schema are unchanged.
Co-authored-by: Claude <noreply@anthropic.com>
* fix(utils): allowed_openai_params must not forward unset params as None
`_apply_openai_param_overrides` iterated `allowed_openai_params` and
unconditionally wrote `optional_params[param] = non_default_params.pop(param, None)`
for each entry. If the caller listed a param name but did not actually
send that param in the request, the pop returned `None` and `None` was
still written to `optional_params`. The openai SDK then rejected it as
a top-level kwarg:
AsyncCompletions.create() got an unexpected keyword argument 'enable_thinking'
Reproducer (from #25697):
allowed_openai_params = ["chat_template_kwargs", "enable_thinking"]
body = {"chat_template_kwargs": {"enable_thinking": False}}
Here `enable_thinking` is only present nested inside
`chat_template_kwargs`, so the helper should forward
`chat_template_kwargs` and leave `enable_thinking` alone. Instead it
wrote `optional_params["enable_thinking"] = None`.
Fix: only forward a param if it was actually present in
`non_default_params`. Behavior is unchanged for the happy path (param
sent → still forwarded), and the explicit `None` leakage is gone.
Adds a regression test exercising the helper in isolation so the test
does not depend on any provider-specific `map_openai_params` plumbing.
Fixes#25697
---------
Co-authored-by: lovek629 <59618812+lovek629@users.noreply.github.com>
Co-authored-by: Progressive-engg <lov.kumari55@gmail.com>
Co-authored-by: Ori Kotek <ori.k@codium.ai>
Co-authored-by: Alexander Grattan <51346343+agrattan0820@users.noreply.github.com>
Co-authored-by: Mohana Siddhartha Chivukula <103447836+iamsiddhu3007@users.noreply.github.com>
Co-authored-by: Amiram Mizne <amiramm@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
* fix(ollama): propagate done_reason='length' as finish_reason for max_tokens truncation
Ollama returns done_reason='length' when a response is cut off by num_predict
(the max_tokens limit). Previously, non-streaming responses hardcoded
finish_reason='stop', and streaming used chunk.get('done_reason', 'stop')
which also defaulted to 'stop' when done_reason was absent.
This meant callers (e.g. the Anthropic pass-through adapter, which maps
OpenAI 'length' -> Anthropic 'max_tokens') could never detect truncation,
making stop_reason always appear as 'end_turn' even for cut-off responses.
Fix: read done_reason from the response JSON in the non-streaming path and
use `chunk.get('done_reason') or 'stop'` in the streaming path, so Ollama's
actual done_reason passes through to the caller unchanged.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* Update test_ollama_chat_transformation.py
* Update litellm/llms/ollama/chat/transformation.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
The Vertex AI count-tokens endpoint rejects model names that include
version suffixes (@default, @20251001, etc.) with:
"claude-sonnet-4-6@default is not supported for token counting"
The same model without the suffix ("claude-sonnet-4-6") works correctly.
Strip @suffix from both the model parameter and request_data["model"]
in handle_count_tokens_request before sending to the API.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Bedrock /v1/messages streams can report cache tokens only on message_start while message_delta carries only uncached input tokens. Merge cache fields onto the final delta usage and clamp negative text-token remainders in cost calc to keep usage/cost consistent.
Made-with: Cursor
MaskedHTTPStatusError constructs a new httpx.Response from the original
error. Two bugs surfaced under real HTTP error responses:
1. The new Response was created without request=, so response.request
raised RuntimeError("The .request property has not been set.") for
any downstream caller (e.g. exception_mapping_utils) that inspected it.
2. The decoded response bytes were passed together with the original
Content-Encoding header. On construction httpx tried to decompress
the already-decoded bytes and raised httpx.DecodingError
("Error -3 while decompressing data: incorrect header check").
Set response.request to the masked Request and strip Content-Encoding
(and the now-stale Content-Length) before rebuilding the Response.
URL/message masking is unchanged; the new request carries the already
masked URL.
Also update test_logging_key_masking_gemini: the security commit
25f93bed91 moved Gemini API keys from ?key=... URL params to the
x-goog-api-key header, so api_base no longer contains the key.
* [Test] Add Azure async chat completion timeout test. WIP
* Capture TTFT for /v1/messages streaming responses
The pass-through streaming path for /v1/messages (Anthropic, Bedrock,
Vertex AI, Azure AI, Minimax) logged completion_start_time only after
the entire stream finished. async_success_handler then fell back to
end_time, making TTFT equal to total duration or null in the UI and
Prometheus.
Record the timestamp of the first chunk in async_sse_wrapper and
propagate it to model_call_details before the logging handler runs,
so gen_ai.response.time_to_first_token reflects the real first-chunk
latency.
Fixes#25598
* [Refactor] Implement timeout resolution logic in completion function
add fetch ``request_timeout`` from litellm_settings
* remove stale test case
* remove extra print statement
* default request timeout value in constants to 600s to match timeout defaults handled in the proxy
* fix request timeout if using default value from constants.py
* update code structure, test cases
* only override if the global timeout sets timeout to 6000s
* update code structure, move hard coded values to const and make the reslve function readable by moving fallback logic to a seperate function
* modify default timeout values, replacing hard coded ones with default values defined
---------
Co-authored-by: harish876 <harishgokul01@gmail.com>
Co-authored-by: Joaquin Hui Gomez <joaquinhuigomez@users.noreply.github.com>
