Everything under tests/claude_code/ that the daily cron run shims into
the stable-tag worktree but that existed only on the cron VM's disk:
check_regressions.py (required by run_daily.sh's auto-merge gate, was
untracked), the count_tokens and long_context_1m test refinements,
http_probe/matrix_builder updates, and the cron_vm README + env
example matching the deployed direct-publish flow.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Two things, one file:
1. Capture the deployed-but-uncommitted run_daily.sh that has been
running in production on the cron VM: direct publish to
BerriAI/litellm-docs as mateo-berri (replacing the agent-shin fork
flow), PEP 440 final-release tag resolution (replacing v*-stable),
and the green->red auto-merge regression gate backed by
check_regressions.py.
2. NEW: sweep stale compat-matrix PRs after each publish. Keep at most
one compat-matrix PR open on litellm-docs: after today's PR is
opened or refreshed, close every other open compat-matrix/* PR and
delete its bot-owned branch. Gate-withheld PRs that nobody triaged
previously accumulated (25 open PRs between 2026-07-02 and
2026-08-10); now the newest PR supersedes them automatically.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Matrix grows from 11 to 15 feature rows. All new tests collected + 180
unit tests still pass; smoke runs hit real LiteLLM bug surfaces on
bedrock_invoke, bedrock_converse, and vertex_ai (cells correctly red
in PR #142).
Rename
------
`extended_thinking` -> `thinking` (directory, manifest id+name, 5
test fn names, 5 docstrings, builder unit-test fixtures, sample JSON,
run_compat.sh). Existing test logic already covers both manual
(`thinking.type=enabled`, Haiku 4.5) and adaptive
(`thinking.type=adaptive`, Opus 4.7) shapes because Claude Code picks
the shape per model from `--effort max`; the name change just stops
the column from looking like a Claude 3.7 reference.
New rows
--------
- structured_outputs (5 files, CLI `--json-schema`). Claude Code
synthesizes a single `StructuredOutput` tool from the schema and
surfaces the tool_use input as `structured_output` on the trailing
`result` event. Test ships its own `_validate_against_schema` so
we don't take a jsonschema dep just for matrix surface.
- count_tokens (5 files, HTTP probe). POSTs the proxy's
`/v1/messages/count_tokens` directly and asserts the response is
`{input_tokens: positive int}`. No CLI hook exists for this
endpoint; the test goes through the new http_probe helper instead.
- tool_search (5 files, HTTP probe). Sends
`tools: [{type: tool_search_tool_regex_20251119, name:
tool_search_tool_regex}]` and asserts the proxy doesn't 400. MCP
fan-out via `--mcp-config` would also exercise the tool-search
beta header path, but it's flaky w.r.t. Claude Code's internal
tool-deferral threshold; the HTTP probe hits the actual bug surface
(per-provider beta-header translation `advanced-tool-use-2025-11-20`
vs `tool-search-tool-2025-10-19`).
- long_context_1m (5 files, CLI `--betas context-1m-2025-08-07
--max-budget-usd 6`). A ~210k-token padded prompt over stdin
exercises the 1M-context beta. Sonnet 4.6 + Opus 4.7 only --
Haiku 4.5's window is 200k, so it's excluded from MODELS (not
marked not_applicable) to keep the per-cell aggregator semantics
intact. Prompt uses a document-style preamble + 8 cycling pangrams
rather than repeating identical chunks; without that, Opus 4.7
trips the safety filter mid-response with a Usage Policy refusal.
`--max-budget-usd 6` is a runaway-loop guard, ~2x worst-case Opus
per-cell spend.
New helper
----------
`tests/claude_code/http_probe.py`: shared `ProbeResult` dataclass
plus per-endpoint `probe_*` + `assert_*_shape` pairs for the
HTTP-probe rows. Uses httpx with `anthropic-version: 2023-06-01` and
a 30s timeout.
The cron host has no write access to BerriAI/litellm-docs by design. PRs
now open from a long-lived fork at agent-shin/litellm-docs:
- run_daily.sh validates AGENT_SHIN_GITHUB_TOKEN up front (failing 30 min
into a run because the env file is missing one line is wasted spend).
- The pre-commit shim adds a transient `fork` remote with the token
embedded in the URL, force-pushes the branch, then removes the remote
so the token never lives on disk.
- `gh pr create --head agent-shin:<branch>` opens the cross-repo PR
with GH_TOKEN scoped to AGENT_SHIN_GITHUB_TOKEN. A second
`gh pr edit --add-reviewer` runs under GITHUB_TOKEN (mateo-berri's
PAT) because agent-shin's PAT lacks RequestReviewsByLogin permission
on the upstream repo.
- PR_REVIEWERS env var (default `mateo-berri`) controls who gets
auto-tagged; empty disables.
Also bring litellm-compat-matrix.service to working state:
- Hardcode `/home/mateo` paths everywhere %h was used. systemd expands
%h against the *manager's* home (/root for PID 1) in *system* units,
not against the User= directive. The mismatch made ReadWritePaths
point at /root/.cache and the namespace setup failed with
status=226/NAMESPACE before run_daily.sh ever started.
- Explicit Environment=PATH so `uv` and `claude` under
~/.local/bin are visible to the up-front command-presence check;
systemd's default PATH excludes them.
- Expand ReadWritePaths to include ~/.claude (CLI per-session state)
and ~/.config/gh (gh host config fallback); both are written under
ProtectHome=read-only.
env.example refreshed: drop AWS_ACCESS_KEY_ID/SECRET +
GOOGLE_APPLICATION_CREDENTIALS in favor of AWS_BEARER_TOKEN_BEDROCK and
ADC via the VM's metadata server; document AGENT_SHIN_GITHUB_TOKEN,
FORK_OWNER/FORK_REPO overrides, and VERTEXAI_LOCATION=global.
- pytest_runtest_makereport: skip the defensive fail-row append when
the test has already recorded a fail via .add(), so the common pattern
of '.add(fail) per failing model, then pytest.fail() to surface them'
no longer produces duplicate rows in compat-results.json.
- _infer_feature_and_provider: validate the parent directory against
manifest.yaml instead of relying on a negative '_-prefix' filter, so
non-feature sibling dirs (e.g. cron_vm) can't leak rows into the
artifact or pollute the rate-limit summary counters.
Co-authored-by: Yassin Kortam <yassin@berri.ai>
Two related gaps in pytest_runtest_makereport let real failures show up as
green (or absent) cells in the published compatibility matrix:
1. Setup-phase failures (broken fixtures / imports) only produce a report
with when="setup"; the call phase never runs. The hook filtered on
when=="call" and returned, leaving no row for the cell. The matrix
builder then aggregated the empty cell to "not_tested" instead of
"fail".
2. A test that called compat_result.add({"status": "pass"}) for some
models and then raised before completing the rest produced a partial
list of pass entries. The "if not collected" guard was bypassed
because the list was non-empty, so no fail row was added. The cell
aggregator's all-pass check then returned pass for a cell that was
never fully exercised.
Now the hook also handles when=="setup" on failure, and always appends a
fail row when report.failed — preserving any partial pass entries from
add() for diagnostics while ensuring the cell aggregator surfaces the
crash.
Co-authored-by: Yassin Kortam <yassin@berri.ai>
The shim was previously gated on `tests/claude_code/test_config.yaml`
not existing in the worktree, so the moment a v*-stable tag landed
with its own copy of `tests/claude_code/` the cron would happily run
whatever frozen tests that release happened to ship — even though the
populator's whole purpose is to exercise *today's* tests against
*today's* stable proxy.
Drop the if-guard and make the shim unconditional: `rm -rf` the
worktree's `tests/claude_code/` after the tag checkout, then
`cp -r` the dev checkout's copy back in. This way fixes that land
on the dev checkout (like the stream-json vision rewrite, the
`--effort` thinking knob, the WebSearch tool_use assertion change)
take effect on the next cron run rather than waiting for a stable
release. The tag's own version of the tree, if any, is discarded each
run, so the worktree is byte-identical to
`${LITELLM_REPO}/tests/claude_code` every time.
Also drops `-e tests/claude_code` from the post-checkout `git
clean` invocation. We used to keep the prior run's shim across
`git clean -fdx` so subsequent runs didn't have to re-shim;
that's no longer necessary now that we re-shim unconditionally,
and keeping it would only delay garbage-collecting deleted files
across runs.
The previous early-return guard in pytest_sessionfinish exited before
the merge step for the xdist controller process: the controller never
runs tests itself (so _COLLECTOR.items is empty) and is not detected
as a worker (it has no workerinput), so the guard always tripped.
Worker shards were written but no process ever produced the canonical
compat-results.json. Also check for shards on disk so the controller
still proceeds to merge them under pytest -n auto.
Co-authored-by: Yassin Kortam <yassin@berri.ai>
- conftest: combine the two pytest_sessionstart definitions so stale
shard cleanup actually runs (the second def previously shadowed the
first, leaving compat-results.json.shards/ from prior sessions in
place and polluting the merged artifact).
- circleci: forward VERTEXAI_PROJECT and VERTEXAI_LOCATION into the
compat-proxy container so test_config.yaml's os.environ refs for the
Vertex AI routes resolve in the PR gate.
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* test: modernize models used in CircleCI e2e test suites
Replaces obsolete models (gpt-4o, gpt-4o-mini, gpt-3.5-turbo,
claude-3-5-sonnet-20240620, claude-sonnet-4-20250514) with current
equivalents across the e2e_openai_endpoints and
proxy_e2e_anthropic_messages_tests CircleCI jobs.
- gpt-4o -> gpt-5.5 (responses API e2e tests)
- gpt-4o-mini -> gpt-5-mini (websocket responses, oai_misc_config)
- gpt-4o-mini-2024-07-18 -> gpt-4.1-mini-2025-04-14 (fine-tuning,
still actively fine-tunable)
- gpt-4 / gpt-3.5-turbo target_model_names example -> gpt-5.5 /
gpt-5-mini
- bedrock claude-3-5-sonnet-20240620 batch entry -> haiku-4-5-20251001
(also aligning oai_misc_config model_name with what
test_bedrock_batches_api.py actually requests)
- bedrock claude-sonnet-4-20250514 (deprecated, retires 2026-06-15)
-> claude-sonnet-4-5-20250929
* test: point bedrock-claude-sonnet-4 alias at Sonnet 4.6, not 4.5
Greptile/Cursor flagged that after the previous commit, the
bedrock-claude-sonnet-4 alias collided with bedrock-claude-sonnet-4.5
(both pointed to claude-sonnet-4-5-20250929). Rename to
bedrock-claude-sonnet-4.6 and point it at the Sonnet 4.6 Bedrock ID
(us.anthropic.claude-sonnet-4-6, already in the litellm model
registry) so the alias name matches the underlying model version.
* test: modernize models across remaining CI-mounted configs & tests
Expands the modernization sweep to all CircleCI-mounted proxy configs
and to test directories where the model literal is a fixture/route key
(not the test's subject).
Config changes:
- proxy_server_config.yaml: bump gpt-3.5-turbo / gpt-3.5-turbo-1106 /
gpt-4o / gemini-1.5-flash / dall-e-3 underlying models; rename
gpt-3.5-turbo-end-user-test alias to gpt-5-mini-end-user-test; bump
text-embedding-ada-002 underlying to text-embedding-3-small. User-
facing aliases (gpt-3.5-turbo, gpt-4, text-embedding-ada-002, etc.)
preserved for backward compatibility with tests.
- simple_config.yaml, otel_test_config.yaml, spend_tracking_config.yaml:
bump gpt-3.5-turbo underlying to gpt-5-mini.
- pass_through_config.yaml: claude-3-5-sonnet / claude-3-7-sonnet /
claude-3-haiku entries replaced with claude-sonnet-4-5 / claude-
haiku-4-5 / claude-opus-4-7.
- oai_misc_config.yaml: align alias name with the gpt-5-mini rename.
Test changes (proactive: claude-sonnet-4-20250514 / claude-opus-4-
20250514 retire 2026-06-15):
- tests/llm_translation/test_anthropic_completion.py: bump 3 references
+ paired Vertex AI ID to claude-sonnet-4-5.
- tests/llm_translation/test_optional_params.py: bump 2 references.
- tests/pass_through_unit_tests/test_anthropic_messages_passthrough.py
and test_bedrock_anthropic_messages_test.py: bump router fixtures
using the deprecated model IDs.
- tests/pass_through_unit_tests/base_anthropic_messages_tool_search_test.py:
modernize docstring examples.
- tests/test_end_users.py: update references to renamed alias.
* test: modernize placeholder model literals in router_unit_tests
Mass replace_all on fixture/placeholder model literals across the
router_unit_tests/ suite (model name is a routing key / label, not the
test subject). Sub-agent sweep so far — additional commits will follow
for logging_callback_tests/, enterprise/, top-level tests/test_*.py,
and other CI-mounted dirs.
Mappings applied:
- gpt-3.5-turbo -> gpt-5-mini
- gpt-4 (bare) -> gpt-5.5
- gpt-4o (bare) -> gpt-5
- text-embedding-ada-002 -> text-embedding-3-small
- claude-3-sonnet-20240229 / claude-3-opus-20240229 /
claude-3-haiku-20240307 / claude-3-5-sonnet-20240620 ->
claude-sonnet-4-5-20250929 / claude-opus-4-7 /
claude-haiku-4-5-20251001 as appropriate
Explicitly preserved:
- gpt-4o-mini-* variants (transcribe, tts, etc.) where they're current
- gpt-4-turbo / gpt-4-vision-preview / gpt-4-0613 (subject literals)
- JSONL batch body literals
- Mock LLM response model fields (must match upstream)
- Fake/mock identifiers
* test: modernize placeholder model literals across remaining CI suites
Sub-agent sweep across logging_callback_tests/, guardrails_tests/,
enterprise/, pass_through_unit_tests/, otel_tests/,
llm_responses_api_testing/, batches_tests/, spend_tracking_tests/,
litellm_utils_tests/, unified_google_tests/, and a few top-level
tests/test_*.py files where the model literal is a fixture or
placeholder (router model_list, mock standard logging payload, mock
callback data) rather than the test's subject.
Mappings applied (see scope notes below):
- gpt-3.5-turbo -> gpt-5-mini
- gpt-4 (bare) -> gpt-5.5
- gpt-4o (bare) -> gpt-5.5 (corrected from initial gpt-5 — bare gpt-5
is not a valid OpenAI alias; only gpt-5.5 / gpt-5.4 / gpt-5.2-codex
/ gpt-5-mini exist)
- gpt-4o-mini (bare) -> gpt-5-mini
- text-embedding-ada-002 -> text-embedding-3-small
- claude-3-sonnet-20240229 -> claude-sonnet-4-5-20250929
- claude-3-opus-20240229 -> claude-opus-4-7
- claude-3-haiku-20240307 -> claude-haiku-4-5-20251001
- claude-3-5-sonnet-20240620/20241022 -> claude-sonnet-4-5-20250929
- claude-3-7-sonnet-20250219 -> claude-sonnet-4-6
- gemini-1.5-flash -> gemini-2.5-flash
- gemini-1.5-pro -> gemini-2.5-pro
Explicitly preserved (not modernized):
- llm_translation/ tests where model is the SUBJECT (provider-specific
translation/transformation logic). Only the deprecated 20250514
references were already bumped in a prior commit.
- Cost-calc / tokenizer subject tests in test_utils.py (skip-ranges
documented by the sub-agent).
- Bedrock model IDs in test_health_check.py path-stripping tests.
- JSONL batch request bodies and mock LLM response bodies (must match
upstream literal).
- Langfuse expected-request-body JSON fixtures (cost values are exact-
match-asserted; changing the model would shift response_cost).
- gpt-3.5-turbo-instruct (text-completion endpoint; no modern OpenAI
equivalent).
- Top-level tests calling the proxy through user-facing aliases
(gpt-3.5-turbo, gpt-4, text-embedding-ada-002, dall-e-3) — aliases
in proxy_server_config.yaml stay; only the underlying model was
bumped.
- tests/test_gpt5_azure_temperature_support.py (the test's whole point
is model-name handling).
- Fake / mock / openai/fake identifiers.
Notable side fixes:
- test_spend_accuracy_tests.py: UPSTREAM_MODEL now matches what
spend_tracking_config.yaml's proxy actually routes to (gpt-5-mini),
resolving a latent inconsistency.
- proxy_server_config.yaml: bare `gpt-5` alias renamed to `gpt-5.5`
(bare gpt-5 is not a valid OpenAI alias).
- test_batches_logging_unit_tests.py: explicit_models list entries
kept distinct (gpt-5-mini + gpt-5.5) after bulk rename.
* test: fix CI failures from model modernization sweep
CI surfaced 4 categories of regression from the bulk modernization:
1. Azure deployment names are customer-specific. Reverted:
- tests/litellm_utils_tests/test_health_check.py: azure/text-
embedding-3-small -> azure/text-embedding-ada-002 (the CI Azure
account does not have a text-embedding-3-small deployment).
- tests/logging_callback_tests/test_custom_callback_router.py:
same revert for two router fixtures driving aembedding.
2. gpt-5 family does not accept temperature != 1. Tests that pass a
custom temperature swapped from gpt-5-mini to gpt-4.1-mini (modern
non-reasoning OpenAI mini that still accepts temperature/logprobs):
- tests/logging_callback_tests/test_datadog.py
- tests/logging_callback_tests/test_langsmith_unit_test.py
- tests/logging_callback_tests/test_otel_logging.py
3. proxy_server_config.yaml's gpt-3.5-turbo-large alias was routing to
gpt-5.5 (a reasoning model that rejects logprobs). The proxy test
tests/test_openai_endpoints.py::test_chat_completion_streaming
exercises logprobs/top_logprobs through that alias. Bumped the
underlying model to gpt-4.1 (non-reasoning, still modern).
4. tests/logging_callback_tests/test_gcs_pub_sub.py asserts against a
pinned JSON fixture (gcs_pub_sub_body/spend_logs_payload.json) with
hardcoded model="gpt-4o" and a model-specific spend value. Reverted
the litellm.acompletion calls in the test to model="gpt-4o" so the
fixture's exact-match assertions still hold.
5. tests/pass_through_unit_tests/test_anthropic_messages_passthrough.py:
anthropic.messages.create routing to openai/gpt-5-mini returned an
empty content[0] with max_tokens=100 (reasoning-token consumption).
Swapped to openai/gpt-4.1-mini.
* test: fix Assistants API model + 2 cursor[bot] review nits
1. pass_through_unit_tests/test_custom_logger_passthrough.py: gpt-5.5
isn't accepted by the /v1/assistants endpoint
("unsupported_model"). Switch to gpt-4.1-mini (modern, Assistants-
API-supported, non-reasoning).
2. example_config_yaml/pass_through_config.yaml: the previous sweep
bumped the claude-3-7-sonnet alias to claude-opus-4-7, which is a
tier change (Sonnet -> Opus). Map to claude-sonnet-4-6 to keep the
Sonnet tier intact. (Cursor bugbot review.)
3. example_config_yaml/simple_config.yaml: model_name was left as
gpt-3.5-turbo while the underlying was bumped to gpt-5-mini, which
muddles the "simple" example. Make both sides gpt-5-mini so the
most basic example is a straight 1:1 mapping again. (Cursor bugbot
review.)
* fix: revert gpt-4/gpt-3.5-turbo alias underlying to non-reasoning models
tests/test_openai_endpoints.py::test_completion calls the proxy alias
"gpt-4" with temperature=0, and other tests call gpt-3.5-turbo with
custom temperature / logprobs / the legacy /v1/completions endpoint.
The earlier modernization mapped both aliases to gpt-5.5 / gpt-5-mini,
which are reasoning models that reject temperature != 1 and don't
expose /v1/completions. Map the aliases to gpt-4.1 / gpt-4.1-mini
(modern non-reasoning OpenAI models) instead — keeps user-facing
aliases preserved while picking a current underlying that still
supports the parameters/endpoints the tests exercise.
Adds test_update_config_env_var_round_trip_not_double_encrypted, which
drives the real /config/update handler: first write plaintext, then
re-POST the stored ciphertext (the Admin UI round-trip) and assert the
value is not stacked with a second encryption layer and untouched keys
stay byte-identical. Verified to fail against the pre-fix handler and
pass after. Also tightens the unit test to exactly three ciphertext
re-feeds.
A single decrypt-then-encrypt chokepoint (_encrypt_env_variables_for_db)
now backs both update_config and save_config. Re-submitting a value the
Admin UI read back from /get/config/callbacks as ciphertext no longer
stacks a second encryption layer, which previously decrypted to garbage
and silently broke the callback. The chokepoint decrypts with the pure
_decrypt_db_variables (no os.environ mutation on the write path) and
encrypts exactly once; update_config merges only the sent keys so
untouched env vars keep their stored ciphertext byte-for-byte.
* fix(bedrock-mantle): use /anthropic/v1/messages path for Mantle endpoint (#27943)
* docs: add one-line docstring to _disable_debugging (#27894)
Squash-merged by litellm-agent from oss-agent-shin's PR.
* Add jp. Bedrock cross-region inference profile for claude-sonnet-4-6 (#27831)
Squash-merged by litellm-agent from Cyberfilo's PR.
* Sanitize empty text content blocks on /v1/messages (#27832)
Squash-merged by litellm-agent from Cyberfilo's PR.
* fix(bedrock-mantle): use /anthropic/v1/messages path for Mantle endpoint
The bedrock-mantle gateway (Claude Mythos Preview) serves the Anthropic
Messages API at /anthropic/v1/messages; /v1/messages returns 404 Not
Found. Both AmazonMantleConfig (chat/completions caller route) and
AmazonMantleMessagesConfig (anthropic-messages caller route) hardcoded
the wrong path, so every Mantle request 404'd before reaching the model.
Per the Anthropic docs: "[Claude in Amazon Bedrock] uses the Messages
API at /anthropic/v1/messages with SSE streaming."
https://platform.claude.com/docs/en/api/claude-on-amazon-bedrock
Confirmed independently against the live endpoint:
/v1/chat/completions -> 200 OK
/v1/messages -> 404 Not Found (what litellm used)
/anthropic/v1/messages -> 200 OK (Claude only)
Adds a regression test asserting both Mantle configs build the
/anthropic/v1/messages path, and updates the existing assertions that
encoded the wrong path.
---------
Co-authored-by: oss-agent-shin <ext-agent-shin@berri.ai>
Co-authored-by: Filippo Menghi <113345637+Cyberfilo@users.noreply.github.com>
* fix: sanitize empty text blocks in sync anthropic_messages_handler path
Co-authored-by: Yassin Kortam <yassin@berri.ai>
---------
Co-authored-by: João Costa <13508071+jpv-costa@users.noreply.github.com>
Co-authored-by: oss-agent-shin <ext-agent-shin@berri.ai>
Co-authored-by: Filippo Menghi <113345637+Cyberfilo@users.noreply.github.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* Feat: Add Weighted-Routing Failover
* test(router): cover weighted failover helper functions
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(router): align weighted failover deployment list type with mypy
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(router): address greptile review on weighted failover
- Narrow exception swallowing in `_maybe_run_weighted_failover` to
`openai.APIError` so model failures defer to the regular fallback
while programming bugs (AttributeError/KeyError/TypeError) surface.
- Note async-only limitation of `enable_weighted_failover` in the
Router constructor docstring.
- Make the weighted distribution test less flaky (1000 iterations,
looser bound) and make the non-simple-shuffle test deterministic by
failing both deployments instead of relying on the latency strategy's
first pick.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(router): ensure weighted failover metadata persists in kwargs
The previous `kwargs.setdefault(metadata_variable_name, {}) or {}` returned
a brand-new dict whenever the existing metadata was falsy (empty dict or
None), so writes to `_failover_excluded_ids` never made it back into
`kwargs`. Multi-hop weighted failover then re-selected previously failed
deployments and exhausted `max_fallbacks` prematurely.
Explicitly assign a fresh dict into kwargs when metadata is missing so
mutations are visible to subsequent failover hops.
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* test(router): regression for weighted failover metadata persistence
Asserts kwargs["metadata"]["_failover_excluded_ids"] is populated after
_maybe_run_weighted_failover, proving the metadata dict written by the
helper is the same object that lives in kwargs (no disconnected copy).
Pairs with the prior fix that replaced `setdefault(..., {}) or {}` with
an explicit get/assign so writes survive across hops.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(router): harden weighted failover error/state handling
- Catch RouterRateLimitError (ValueError) alongside openai.APIError in
_maybe_run_weighted_failover so an exhausted intra-group retry falls
through to the regular cross-group fallback path instead of bubbling
out and bypassing configured fallbacks.
- Stop mutating the shared input_kwargs dict; build a local copy with
the weighted-failover keys so the entry (with _excluded_deployment_ids)
cannot leak into later fallback paths reading the same dict.
- _get_excluded_filtered_deployments now returns an empty list when the
exclusion filter removes every healthy deployment, instead of falling
back to the original list. The original-list behavior risked re-picking
the just-failed deployment; callers already handle the empty case by
raising their no-deployments error, which weighted failover now catches
and converts into a normal cross-group fallback.
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* fix(router): fall through to rpm/tpm when total weight is zero
When the weight metric's total is zero (e.g. after weighted-failover
exclusion leaves only zero-weight backups), continue to the next metric
(rpm/tpm) instead of returning a uniform random pick immediately. This
lets rpm/tpm still drive routing when present, and only falls back to
the uniform random pick at the end if no metric provides a positive
total weight.
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* fix(router): skip weighted failover when remaining deployments are all in cooldown
_maybe_run_weighted_failover was computing 'remaining' from all_deployments
(every deployment in the model group, including those in cooldown). This meant
that when all non-excluded deployments were in cooldown the method still invoked
run_async_fallback unnecessarily, which propagated into async_get_healthy_deployments,
found no eligible deployments, and raised RouterRateLimitError — only safely
caught thanks to the earlier exception-broadening fix.
The fix: before computing 'remaining', fetch the current cooldown set via
_async_get_cooldown_deployments and subtract it from all_ids. This allows
_maybe_run_weighted_failover to return None immediately (skipping the
run_async_fallback call entirely) when every non-failed deployment is in cooldown,
letting the caller fall through to the correct cross-group fallback path without
the wasteful extra round-trip.
Tests added:
- unit: _maybe_run_weighted_failover returns None without calling run_async_fallback
when all remaining deployments are in cooldown
- unit: _maybe_run_weighted_failover still calls run_async_fallback when at least
one healthy (non-cooldown) deployment is available
- integration: end-to-end fallthrough to cross-group fallback when remaining
deployments are in cooldown
Co-authored-by: Sameer Kankute <Sameerlite@users.noreply.github.com>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Yassin Kortam <yassin@berri.ai>
Co-authored-by: Sameer Kankute <Sameerlite@users.noreply.github.com>
* fix(vertex-ai): fix zero cost/usage on completed Vertex AI batch jobs
Vertex batch jobs recorded 0 spend and 0 tokens after PR #25627 added
automatic transformation of GCS predictions.jsonl to OpenAI format.
Two bugs fixed:
1. batch_utils.py: the Vertex-specific cost/usage reader
(calculate_vertex_ai_batch_cost_and_usage) was always invoked and
reads raw usageMetadata fields that no longer exist in the
OpenAI-shaped output. Now the reader is only used when
disable_vertex_batch_output_transformation=True; otherwise the
generic path handles the already-transformed OpenAI-shaped content.
2. cost_calculator.py: batch_cost_calculator skipped the global
litellm.get_model_info() lookup when a model_info dict was passed
in, even when that dict had no pricing fields (e.g. deployment
metadata with only id/db_model). It now falls back to the global
pricing table when the provided model_info has no pricing data.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Update litellm/cost_calculator.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix(cost-calculator): use not-any guard for pricing fallback in batch_cost_calculator
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(cost-calculator): treat explicit zero batch pricing as set in model_info
The fallback to litellm.get_model_info() used truthy checks on pricing
fields, so 0.0 was treated as missing and replaced by global rates.
Use `is not None` like elsewhere in cost calculation. Add regression test.
Co-authored-by: Sameer Kankute <Sameerlite@users.noreply.github.com>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: Sameer Kankute <Sameerlite@users.noreply.github.com>
* fix(managed_batches): convert raw output_file_id to managed ID in CheckBatchCost poller
CheckBatchCost bypasses async_post_call_success_hook, causing raw provider
output_file_ids to be persisted in LiteLLM_ManagedObjectTable. This fix converts
output_file_id and error_file_id to managed base64 IDs before the DB write.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(check_batch_cost): persist managed file before mutating response and propagate team_id
- Move setattr after store_unified_file_id so the response only receives the
managed ID once the DB record is successfully written. Avoids serializing
an orphaned managed ID into file_object when the store call fails.
- Populate team_id on the minimal UserAPIKeyAuth from job.team_id so the
managed file record is created with the correct team ownership, allowing
other team members to access the batch output file via /files/{id}/content.
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* test(managed_batches): extend test to cover error_file_id conversion
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix managed file test
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* feat(proxy): fix vector store retrieve/list/update/delete routing without model
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(proxy): remove unchecked query-param injection in vector store management endpoints
Co-authored-by: Cursor <cursoragent@cursor.com>
* test(proxy): use subset assertion for vector store route test to allow extra kwargs like shared_session
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
_build_mcp_server_table omitted delegate_auth_to_upstream, so GET /v1/mcp/server always returned the default false while the registry kept the DB value.
Co-authored-by: Cursor <cursoragent@cursor.com>
Log verbose_logger.warning when loading oauth2 interactive servers with
available_on_public_internet=false and delegate_auth_to_upstream=true
(config + DB). Dashboard Alert for the same combo. CLAUDE note for
operators. Tests for log and M2M skip.
Remove available_on_public_internet gating from delegate-auth-to-upstream
paths so oauth2 + delegate_auth_to_upstream interactive servers behave
the same when marked internal. Keeps M2M exclusion. Updates tests.
* feat(custom_logger): add async_post_agentic_loop_response_hook
Lets a CustomLogger shape the response returned by the agentic-loop
follow-up call without bypassing the loop's safety / observability
machinery (depth tracking, fingerprinting, etc.). Default returns the
response unchanged.
Used by websearch_interception to inject Anthropic-native
web_search_tool_result blocks when the originating client requested a
native web_search_* tool.
* feat(llm_http_handler): call post-agentic-loop hook on the originating callback
In _execute_anthropic_agentic_plan, after anthropic_messages.acreate
returns, call the originating callback's
async_post_agentic_loop_response_hook so it can mutate the final
response (e.g. inject native tool_result blocks). Pass the callback
through from _call_agentic_completion_hooks.
Exceptions in the post-hook are caught and logged so a buggy callback
can't kill the request.
* feat(websearch_interception): add is_anthropic_native_web_search_tool
Identifies tools the Anthropic-native clients (Claude Desktop, the
Anthropic SDK, the Anthropic Console) use to request native search:
type starts with "web_search_" (e.g. web_search_20250305). Rejects the
LiteLLM standard tool, the OpenAI-function variant, the bare
"WebSearch" legacy name, and the bare "web_search" Claude Code shape.
This lets us decide per-request whether the client expects
web_search_tool_result content blocks in the response, without
renaming any existing constants or touching native-provider skip
logic.
* feat(websearch_interception): add build_web_search_tool_result_block
Produces the Anthropic-native web_search_tool_result content block
from a structured SearchResponse. Anthropic-native clients use this
block to populate citations / source links — the existing text-blob
flatten path only feeds readable evidence to the model and discards
the structure, so this builder gives us the missing piece.
Shape matches https://docs.anthropic.com/en/api/web-search-tool —
web_search_result items carry url, title, page_age, encrypted_content
(empty string when the search provider doesn't supply one).
* feat(websearch_interception): emit native web_search_tool_result blocks
When the originating client request carried a native Anthropic
web_search_* tool, the final response now also carries
web_search_tool_result content blocks alongside the model's text
answer — so Claude Desktop / Anthropic SDK clients can populate the
citations panel and replay conversation history with structured search
evidence.
Wiring:
- Pre-request hooks (both deployment + Anthropic path) set a flag on
kwargs when they see a native web_search_* tool, so the signal
survives the conversion-to-litellm_web_search step regardless of
which hook fires first.
- _execute_search now returns (text, SearchResponse) so the structured
results aren't lost when the text is flattened for the follow-up
model call.
- _build_anthropic_request_patch returns the parallel list of
SearchResponse objects.
- async_build_agentic_loop_plan pre-builds the web_search_tool_result
blocks (one per tool_use_id) and stashes them on plan.metadata when
the flag is set.
- async_post_agentic_loop_response_hook reads the metadata and
prepends the blocks to response.content.
- _execute_agentic_loop mirrors the injection for the legacy path so
both paths behave identically.
Clients that send the LiteLLM standard tool keep the existing
text-only behavior — no regression.
* test(websearch_interception): cover native web_search_tool_result emission
18 tests across:
- detector branches (native vs litellm-standard, OpenAI-function shape,
Claude Desktop builtin WebSearch, bare web_search, missing type)
- block-builder shape (results, none, empty)
- pre-request hook flag-setting (native sets, standard does not)
- async_build_agentic_loop_plan attaches blocks to plan.metadata when
the flag is present, leaves metadata untouched when absent
- post-hook injection into dict and object responses
- legacy _execute_agentic_loop mirrors the injection so both paths
return the same shape
* test(websearch_short_circuit): keep _execute_search mocks in sync with new tuple return
* test(websearch_thinking_constraint): keep _execute_search mocks in sync with new tuple return
* feat(websearch_interception): emit native blocks from try_short_circuit_search
The agentic-loop post-hook only fires when the model returns a tool_use
block. Cowork / Claude Desktop on Bedrock actually make TWO requests
per user turn: the main /v1/messages with their builtin tool, and a
separate standalone /v1/messages whose only tool is
web_search_20250305. That second request hits try_short_circuit_search
— no agentic loop, no post-hook — and was returning text-only, leaving
the citations panel empty.
When the short-circuit input carries a native web_search_* tool, build
a synthetic server_tool_use + web_search_tool_result pair (using the
structured SearchResponse already returned by _execute_search) so the
client gets the native shape it expects. The legacy text block is
preserved so non-native short-circuit callers (Claude Code,
github_copilot, etc.) see the same payload as before.
Failure path still emits the native block pair (with empty results)
plus the text-error block, so the client gets a well-formed response
rather than a malformed half-shape.
* test(websearch_native_blocks): cover short-circuit native-block emission
Three new cases on top of the existing 18:
- native web_search_20250305 short-circuit → [server_tool_use,
web_search_tool_result, text], ids paired, urls/titles carried.
- litellm_web_search short-circuit → text-only (no regression).
- native short-circuit on search failure → still emits the native
block pair (empty results) plus the text-error block, so the client
never sees a malformed half-shape.
* test(websearch_short_circuit): index assertions by block type, not by position
Native short-circuit responses now have [server_tool_use,
web_search_tool_result, text] when the input carries
web_search_20250305 — find the text block by type rather than relying
on content[0].
* fix(websearch_interception): gate legacy WebSearch name on schema absence
Clients like Cowork / Claude Desktop ship a client-side tool named
"WebSearch" with a full input_schema — they handle it themselves and
expect to make a separate native web_search_20250305 sub-request for
the actual search.
Today is_web_search_tool matches the bare name regardless of other
fields, which hijacks the client's tool server-side. The agentic loop
fires on the main request, the model never gets to emit the
client-side tool_use, and the separate native sub-request (where
citation data flows) is never made. Net: citations panel empty.
Real Anthropic client tools always carry input_schema (the API rejects
them otherwise), so a bare {name: "WebSearch"} with no schema is the
only thing that could be a legacy interception marker. Gate the match
on schema absence: legacy callers (if any) keep working, real
client-side WebSearch tools pass through untouched.
* fix(websearch_interception): drop "WebSearch" from response-detection lists
Post-conversion the model always sees ``litellm_web_search``, so the
"WebSearch" entry in the response-side tool_use detection lists was
dead at best. If a model ever did return ``tool_use(name="WebSearch")``
it would now (incorrectly) hijack the client's own ``WebSearch`` tool
again — same Cowork problem we just fixed on the input side. Drop it.
* test(websearch_native_blocks): cover the WebSearch legacy-name schema gate
Three new cases:
- {name: "WebSearch"} (bare interception marker) → still matched
- {name: "WebSearch", input_schema: {...}} (Cowork client tool) →
passes through untouched
- {name: "WebSearch", description: "..."} (no schema) → still matched
on the assumption it's a legacy marker rather than a malformed real
client tool.
---------
Co-authored-by: Ishaan Jaffer <ishaanjaffer0324@gmail.com>
* fix(rate-limit): stop v3 limiter from leaking internal stash to provider body
PR #27001 (atomic TPM rate limit) introduced a reservation flow that
writes four LiteLLM-internal keys onto the request data dict:
_litellm_rate_limit_descriptors
_litellm_tpm_reserved_tokens
_litellm_tpm_reserved_model
_litellm_tpm_reserved_scopes
_litellm_tpm_reservation_released
These keys are forwarded as request body params to the upstream provider,
which rejects them as unknown fields:
OpenAI -> 400 'Unknown parameter: _litellm_rate_limit_descriptors'
(mapped by litellm to RateLimitError / 429, hiding the bug
behind a misleading 'throttling_error' code)
Anthropic -> 400 '_litellm_rate_limit_descriptors: Extra inputs are
not permitted'
Net effect: every chat completion against any real provider fails the
moment a virtual key has any tpm_limit / rpm_limit set — i.e. v3-enforced
key-level TPM/RPM limits are broken end-to-end. The v3 RPM/TPM check
itself still runs (raises 429 on over-limit), but the success path
poisons the upstream body.
Reproduced on litellm_internal_staging HEAD (410ce761dc) against
gpt-4o-mini and claude-haiku-4-5 with a 1-RPM/1-TPM key — first request
fails with the provider's unknown-field error.
Fix: the stash is metadata only.
- Add RATE_LIMIT_DESCRIPTORS_KEY constant and a _LITELLM_STASH_KEYS
registry so we have a single source of truth for stash keys.
- New helper _stash_value_in_metadata_channels writes to
data['metadata'] / data['litellm_metadata'] without touching the
top level.
- _stash_reservation_in_data and the descriptor stash now route
through that helper. _mark_reservation_released stops writing
top-level.
- _lookup_stashed_value also checks kwargs['metadata'] /
kwargs['litellm_metadata'] (raw request_data shape) in addition to
kwargs['litellm_params']['metadata'] (completion kwargs shape).
- async_post_call_failure_hook now reads descriptors via the unified
metadata lookup instead of request_data.get(top-level).
- Defense in depth: async_pre_call_hook strips any stash key that
somehow surfaced at the top level (stale cache, future refactor,
test fixture) before returning.
Tests:
- New regression test asserts no _litellm_* stash key is present at
the top level of data after async_pre_call_hook, and that the
metadata channel still carries the reservation + descriptors so
success / failure reconciliation works.
- Existing test_tpm_concurrent.py tests that asserted top-level
presence are updated to read from data['metadata'] — the location
is an implementation detail; the spec is that post-call callbacks
can resolve the stash.
Verified end-to-end against OpenAI gpt-4o-mini and Anthropic
claude-haiku-4-5 via /v1/chat/completions on a low-rpm key:
- With limits not exceeded: HTTP 200, valid completion response,
no leaked fields in body.
- With RPM exceeded: HTTP 429 from v3 enforcement
('Rate limit exceeded ... Limit type: requests').
- With TPM exceeded: HTTP 429 from v3 enforcement
('Rate limit exceeded ... Limit type: tokens').
Full v3 hook test suite passes (171 tests).
Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
* chore(rate-limit): use RATE_LIMIT_DESCRIPTORS_KEY constant in test, trim noisy comments
Address greptile P2: test fixture now uses the imported constant.
Drop comments that re-explain what well-named identifiers already convey.
* fix(rate-limit): reject caller-supplied stash values to prevent TPM-refund abuse
Strip _LITELLM_STASH_KEYS from data top-level and both metadata channels at
the start of async_pre_call_hook. Without this, an authenticated caller can
inject _litellm_rate_limit_descriptors plus _litellm_tpm_reserved_tokens in
body metadata, trigger a proxy-side rejection, and cause
async_post_call_failure_hook to refund TPM counters against attacker-named
scopes (e.g. another tenant's api_key).
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
- Introduce `_CallbackCapabilities` dataclass and `ProxyLogging._callback_capabilities()` static method that inspects `litellm.callbacks` once and caches capability flags keyed on (list length, member ids); invalidates automatically when the callback list mutates without per-request iteration overhead
- Replace O(n) `litellm.callbacks` walks in `async_pre_call_hook`, `during_call_hook`, `async_post_call_streaming_iterator_hook`, `async_post_call_streaming_hook`, and `post_call_response_headers_hook` with fast-path exits when no relevant callbacks are registered
- Add `needs_iterator_wrap()` and `needs_per_chunk_streaming_hook()` instance methods to decouple iterator-level wrapping from per-chunk hook execution; avoids `get_response_string` materialization per chunk when no guardrail or chunk-hook callback is active
- Introduce `_fast_serialize_simple_model_response_stream()` using `orjson` for common single-choice text streaming chunks, bypassing the full Pydantic serializer; falls back to `model_dump_json` for tool calls, logprobs, usage, and provider-specific fields
- Add early-return in `_restamp_streaming_chunk_model` when downstream model already matches the requested model, avoiding unnecessary string comparisons on every chunk
- Fix stale zero-cost cache bug in `_is_model_cost_zero`: move the per-router `_zero_cost_cache` dict onto the `Router` instance and clear it in `_invalidate_model_group_info_cache` so in-place pricing updates via `upsert_deployment` immediately resume budget enforcement
- Add `scripts/benchmark_chat_completions_perf.py`: standalone async benchmarking tool with a mock OpenAI provider, LiteLLM proxy process management, non-streaming RPS, streaming TTFT, and full-stream latency measurements with repeat/median run support
- Add comprehensive unit tests covering capability detection, cache invalidation, fast-path correctness, zero-cost cache regression, and the no-callback streaming fast path
Co-authored-by: Yassin Kortam <yassinkortam@g.ucla.edu>
* feat(lasso): extend LassoGuardrail to support tool calling (RND-5748)
* fix(lasso): PR review followups for tool-calling guardrail (RND-5748)
* fix(lasso): handle object-style tool_calls in _update_tool_calls_from_masked (RND-5748)
* fix(lasso): use model role for tool_use blocks (RND-5748)
* test(lasso): add round-trip tests for message transformation (RND-5748)
* fix(lasso): remove unused imports, handle Responses-API input masking, flatten multimodal content (RND-5748)
* fix(lasso): inspect Responses-API input field (RND-5748)
* fix(lasso): guard text-cursor remap against Lasso count mismatch (RND-5748)
* fix(lasso): flatten list content in tool_result.content (RND-5748)
* fix(lasso): remap multimodal list content during masking (RND-5748)
Bug: _map_masked_messages_back counted list-content messages in
original_text_count but the remap loop only handled isinstance(str).
The positional text_cursor never advanced for list messages, causing
all subsequent masked texts to be written onto the wrong messages.
Fix: added elif isinstance(content, list) branch that replaces the
list with the masked text string and advances the cursor — mirrors
the existing string-content branch. Also handles the assistant +
tool_calls combo for list-content messages.
Test: test_map_masked_messages_back_list_content verifies a user
message with [text + image_url] followed by an assistant message
gets correct masked content on both (cursor stays aligned).
* refactor(lasso): extract _get_field and _extract_tool_call_fields helpers (RND-5748)
The dict-vs-object access pattern (x.get('y') if isinstance(x, dict)
else getattr(x, 'y', None)) was duplicated 14 times across 5 methods.
_get_field(obj, field) — single-point dict/Pydantic field access.
_extract_tool_call_fields(call) — returns (call_id, name, parsed_input)
with JSON argument parsing, replacing ~30 duplicate lines in both
async_post_call_success_hook and _expand_messages_for_classification.
Also simplified _update_tool_calls_from_masked, _prepare_payload tool
mapping, and _apply_masking_to_model_response call_id extraction.
Net ~60 lines removed. No behavior change — all 32 tests pass.
* fix(lasso): add count guard to _apply_masking_to_model_response (RND-5748)
_apply_masking_to_model_response used a bare text_cursor without
verifying 1:1 correspondence between text-bearing choices and masked
text entries. If Lasso returned a different number of text messages
than choices with content, masked text would be applied to the wrong
choice or silently skip choices.
Added the same count-mismatch guard pattern already used in
_map_masked_messages_back: count original text-bearing choices,
compare to masked_text length, skip text remap on mismatch with a
warning log. Tool_call masking via id-based lookup is unaffected.
Tests:
- test_apply_masking_to_model_response_multiple_choices: verifies
correct per-choice masked text with 2 choices
- test_apply_masking_to_model_response_count_mismatch: verifies
content is left unchanged when counts disagree
* fix(lasso): close two guardrail-bypass paths flagged in review (RND-5748)
* tool-call args: when function.arguments is malformed JSON or parses
to a non-object, preserve the raw string as {"arguments": <raw>} so
Lasso still inspects it instead of receiving input=None. Covers both
pre-call and post-call extraction (shared helper). Also resolves the
CodeQL empty-except warning since the except body now assigns parsed=None.
* Responses-API input: when a request carries both "messages" and
"input", inspect both. Previously a benign messages array let the
guardrail skip data["input"] entirely. The masking write-back is
split via a count boundary so masked messages flow back to
data["messages"] and masked input flows back to data["input"]
without cross-contamination.
Tests: malformed/non-object args round-trip, dual-field classification,
dual-field masking write-back split.
* chore(lasso): black formatting + comment on expand skip branch (RND-5748)
* black: wrap two long expressions in lasso.py and reformat dict
literals in test_lasso.py to satisfy CI lint.
* add a short comment in _expand_messages_for_classification
explaining why empty string and None content are intentionally
skipped (None is the OpenAI shape for a pure tool-call turn).
* fix(lasso): satisfy mypy in _handle_masking, _update_tool_calls_from_masked, _apply_masking_to_model_response (RND-5748)
* Narrow `response.get("messages")` into a local before slicing so
mypy doesn't see `Optional[List[Dict[str, str]]]` as non-indexable.
* Rename the two write-side `func` bindings in
`_update_tool_calls_from_masked` to `func_dict` / `func_obj` so
mypy doesn't unify the dict and Any|None branches.
* Rename the inner loop variable in `_apply_masking_to_model_response`
from `msg` to `masked_msg` to avoid clashing with the
`msg = choice.message` rebinding below.
No behavior change; resolves the 7 mypy errors from the CI lint job.
* fix: block NaN/Inf budget bypass and add missing non-admin guards
Addresses three security issues:
GHSA-wvg4-6222-3q4r: /user/update exposes max_budget, soft_budget, spend
to self-editing non-admin users with no server-side guard. Non-admin callers
now receive HTTP 403 if any of those fields appear in the update payload.
GHSA-q775-qw9r-2r4g: _enforce_upperbound_key_params returned early (no-op)
when upperbound_key_generate_params was absent from config, letting any
authenticated user generate a key with unlimited max_budget. Fix adds a
delegated-authority ceiling in _common_key_generation_helper: non-admins
cannot grant a key more budget than their own key carries.
GHSA-2rv4-xv66-fpjg: float('nan') passes every `value < 0` guard because
nan < 0 is False in Python, and spend >= nan is always False, permanently
disabling budget enforcement for any entity carrying a NaN max_budget.
All write-time budget guards now use `not math.isfinite(v) or v < 0`.
_enforce_upperbound_key_params validates finiteness unconditionally (before
the early-return). All spend-enforcement comparisons in auth_checks.py are
now guarded with math.isfinite(max_budget) as defense-in-depth.
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* fix: close budget ceiling bypass for callers with no max_budget (GHSA-q775)
Non-admin callers whose API key has no explicit max_budget (None) could
bypass the delegated-authority ceiling and create keys with arbitrary
budgets. Now blocks budget assignment when caller has no budget configured.
Also removes redundant inline import of LitellmUserRoles.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: only apply budget ceiling to explicitly requested max_budget
Capture the caller-supplied max_budget before _enforce_upperbound_key_params
can fill it with a default, so auto-filled defaults don't trigger the
ceiling guard for non-admin users with no budget on their own key.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: capture requested max_budget before any defaults are applied
Move _requested_max_budget capture before both default_key_generate_params
and upperbound_key_generate_params mutations, so auto-filled values don't
trigger the ceiling check for non-admin users.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: allow unlimited-budget callers to delegate any budget
Callers with max_budget=None (unlimited) can legitimately create
budget-capped keys. Only block when caller has an explicit budget
and the requested budget exceeds it.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: yuneng-jiang <yuneng@berri.ai>
Co-authored-by: ryan-crabbe-berri <ryan@berri.ai>
Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
Provider validation errors (e.g. OpenAI RateLimitError carrying 178
pydantic errors each with their own 'input': [...]) were stored verbatim
in LiteLLM_SpendLogs.metadata.error_information.error_message via
str(original_exception), producing rows >12 MB.
Sanitize before metadata is serialized:
- redact 'input'/'messages' values in both error_message and traceback
when store_prompts_in_spend_logs is False (back-door leak paths)
- always apply the MAX_STRING_LENGTH_PROMPT_IN_DB size cap to
error_message and traceback (DB-storage safeguard)
Value scanning uses a parser-based balanced-bracket walk that respects
string quoting, so multi-modal payloads ('messages': [{'content': [...]}])
and user text containing literal brackets ("secret[123") are handled
correctly instead of leaking past a depth-1 regex.
Scoped to the spend-log path so OTEL/Datadog/etc. callbacks still
receive the untruncated error per LITELLM_TRUNCATION_DB_SAFEGUARD_NOTE.
Co-authored-by: Yassin Kortam <yassinkortam@g.ucla.edu>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: patch Host-header auth bypass in get_request_route
Starlette reconstructs request.url from the Host header. A malformed
Host like `localhost/?x=1` causes Starlette to build the full URL as
`http://localhost/?x=1/health`, which url-parses to path="/". Since "/"
is in LiteLLMRoutes.public_routes, all protected routes became reachable
without authentication.
Fix: read scope["path"] (set by uvicorn from the HTTP request line,
not derivable from headers) instead of request.url.path. Sub-path
deployments are handled via scope["app_root_path"] / scope["root_path"],
mirroring Starlette's own base_url construction logic.
Affected variants confirmed fixed:
Host: localhost/?x=1
Host: localhost:4000/?x=1
Host: localhost/#test
Host: localhost:4000/#test
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* style: reduce comments in route fix
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* fix: block credential fields in RAG ingest vector_store options
Credential fields (vertex_credentials, aws_access_key_id, api_key, etc.)
in ingest_options.vector_store are now rejected at the API boundary with
a 400 error. Credentials must be configured server-side.
Previously any authenticated user could supply a vertex_credentials dict
with type=external_account pointing credential_source.file at an
arbitrary path (e.g. /proc/1/environ) and token_url at an
attacker-controlled server. google-auth's identity_pool.Credentials
refresh() would read the file and POST its contents to the attacker.
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* fix: block /key/update self-escalation by assigned users
Non-admin users who were assigned a key (created_by != caller) could
update any non-budget field — models, rpm_limit, guardrails, etc. —
without admin authorization, allowing privilege self-escalation.
Gate: only the key creator (created_by == caller) may edit their own
key without admin check; budget changes always require admin regardless
of creator status. All other callers must pass _check_key_admin_access.
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* fix: block user-controlled api_base in RAG ingest vector_store options
A user-supplied api_base in ingest_options.vector_store caused the server
to forward its configured provider credentials (Gemini, OpenAI) to an
attacker-controlled endpoint via SSRF.
Add api_base to the blocked credential params set alongside api_key and
the existing credential fields.
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* fix: restrict /utils/transform_request to PROXY_ADMIN and apply body safety check
Any authenticated internal_user could POST arbitrary provider config
(aws_sts_endpoint, api_base, etc.) to /utils/transform_request and have
the server forward its credentials to an attacker-controlled endpoint.
- Gate the endpoint on PROXY_ADMIN role (403 for all other roles)
- Call is_request_body_safe() to reject banned params even for admins
- Convert ValueError from safety check to HTTP 400
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* fix: apply banned-param check to /utils/transform_request
Without is_request_body_safe(), any authenticated user could pass
aws_sts_endpoint, api_base, or aws_web_identity_token to
/utils/transform_request and have the server forward its configured
provider credentials to an attacker-controlled endpoint during SDK
credential resolution.
Applies the same banned-param blocklist already used by LLM endpoints.
Endpoint remains accessible to all authenticated users.
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* fix: block SSRF via api_base in /prompts/test dotprompt YAML frontmatter
Any frontmatter key not in ["model","input","output"] flowed into
optional_params and was merged into the LLM call data dict, bypassing
is_request_body_safe. An attacker with any bearer key could set
api_base in YAML to redirect the outbound LLM request — including the
provider API key — to an attacker-controlled host.
Fix: call is_request_body_safe on the constructed data dict after
optional_params are merged, before invoking ProxyBaseLLMRequestProcessing.
ValueError from the banned-param check is surfaced as HTTP 400.
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* Update litellm/proxy/rag_endpoints/endpoints.py
Co-authored-by: veria-ai[bot] <224490171+veria-ai[bot]@users.noreply.github.com>
* fix: coerce nested config strings before banned-param check
_NESTED_CONFIG_KEYS descent used isinstance(nested, dict) which silently
skipped litellm_embedding_config when delivered as a JSON string via
multipart/form-data. Banned params (api_base, aws_sts_endpoint, etc.)
nested inside the stringified value were invisible to is_request_body_safe.
_NESTED_METADATA_KEYS already used _coerce_metadata_to_dict which parses
JSON strings before checking. Apply the same coercion to _NESTED_CONFIG_KEYS.
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* fix: replace substring match with prefix match in is_llm_api_route
mapped_pass_through_routes used `_llm_passthrough_route in route` (substring)
so any admin-only path whose URL contained a provider name (openai, anthropic,
azure, bedrock, etc.) was misclassified as an LLM API route and bypassed the
admin gate in non_proxy_admin_allowed_routes_check.
Confirmed live: non-admin key could GET /credentials/by_name/openai (read
masked provider API key) and DELETE /credentials/openai (delete credential).
Fix: use exact match or startswith(prefix + "/") — the same pattern used
everywhere else in RouteChecks — so only routes that actually start with a
passthrough prefix are allowed through.
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* fix: stabilize PR #27878 test failures
- key_management_endpoints: extend can_skip_admin_check to team keys so
team members with /key/update permission can update non-budget fields.
can_team_member_execute_key_management_endpoint already validates team
membership + permission and raises if unauthorized; reaching the admin
check on a team key means the caller was authorized.
- test: set created_by on mock key in
test_update_key_non_budget_fields_allowed_for_internal_user so
caller_is_creator resolves correctly (MagicMock default ≠ user_id).
- auth_utils.get_request_route: guard against non-dict request.scope
(e.g. MagicMock in unit tests) to prevent a MagicMock leaking into
UserAPIKeyAuth.request_route and failing Pydantic validation.
- ci: assign test_multipart_bypass_repro.py to the proxy-runtime shard
in test-unit-proxy-db.yml to satisfy the shard-coverage check.
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* fix(lint): add explicit str() cast in get_request_route for MyPy
scope.get() returns Any|None which MyPy cannot coerce to str implicitly.
Wrap both scope.get() calls in str() to satisfy the type checker.
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* fix: guard bare-/ root_path strip + make total_spend migration idempotent
auth_utils.get_request_route: when Starlette sets scope["app_root_path"]
to "/" (e.g. behind some middleware), the old stripping logic would
remove the leading slash from every path ("/team/new" → "team/new"),
breaking route matching and causing auth to misclassify protected routes.
Skip stripping when root_path is bare "/".
migration: add IF NOT EXISTS to total_spend ALTER TABLE so the migration
is safe to replay when a prior partial run already created the column.
Without this guard, prisma migrate deploy fails on CI DBs that were
partially migrated, causing all subsequent DB operations (including
/team/new) to 500.
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* fix: require creator still owns key for personal-key bypass in /key/update
caller_is_creator now requires both created_by == caller AND user_id ==
caller. Previously checking only created_by let a demoted admin who
originally created a key for another user continue editing non-budget
fields on it after reassignment, bypassing _check_key_admin_access.
Adds regression test: creator whose key was reassigned is blocked (403).
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* fix: extract auth checks to fix PLR0915 + broaden max_budget assertion
internal_user_endpoints._update_single_user_helper exceeded 50 statements
(PLR0915). Extract authorization checks into _check_user_update_authz helper
to bring statement count under the limit.
test_validate_max_budget: assert "negative" (substring of both the local
"cannot be negative" and the CI "non-negative finite number" messages) so
the test is stable regardless of which exact wording the function uses.
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: veria-ai[bot] <224490171+veria-ai[bot]@users.noreply.github.com>
``test_azure_ad_token_is_in_banned_list`` only asserted tuple
membership of a name the parametrized test already exercises end-to-end
through ``is_request_body_safe``. Removed.
Tightened the admin-opt-in test comment.
``_NESTED_CONFIG_KEYS`` descent used ``isinstance(nested, dict)``, so a
caller sending ``extra_body`` as a JSON-encoded string instead of an
object (the same shape multipart/form-data clients use for
``litellm_metadata``) skipped the banned-key check entirely. Switched to
``_coerce_metadata_to_dict`` so the JSON-string path is parsed before
descent — mirrors the existing handling on ``_NESTED_METADATA_KEYS``.
``extra_body`` is the OpenAI-SDK passthrough container. Provider
modules read provider-auth fields out of it directly (Azure's
``extra_body.azure_ad_token``, Bedrock's
``extra_body.aws_web_identity_token``, etc.) without re-validating, so
the boundary check has to walk it the same way it walks
``litellm_embedding_config``. Adding it to ``_NESTED_CONFIG_KEYS``
extends single-level banned-key descent into the container — top-level
admin opt-ins (``allow_client_side_credentials`` /
``configurable_clientside_auth_params``) still apply.
``azure_ad_token`` was not in ``_BANNED_REQUEST_BODY_PARAMS`` despite
being the bearer-token field the Azure transformer resolves through
``get_secret`` (same shape as ``aws_web_identity_token`` on the
Bedrock STS path). Added so it can't be supplied per-request without
an admin opt-in.
* feat(mcp): support MCP access group names in URL-based namespacing
Extends dynamic_mcp_route to resolve /{name}/mcp requests where {name}
is an MCP access group tag or a comma-separated list of servers/groups,
matching what the documentation promised but the handler did not implement.
Resolution order: registered server alias → toolset → comma-separated
list → single access group tag (404 if none match).
Adds unit tests covering all four resolution paths plus 404 cases.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(mcp): address Greptile review comments on dynamic_mcp_route
- Move comma-separated check before toolset DB lookup so comma names
short-circuit without hitting the database
- Cache access-group DB lookups via user_api_key_cache to avoid a raw
find_many on every request (matches toolset caching pattern)
- Remove unused response_started variable from _forward_as_mcp_path
- Update tests to assert comma list skips toolset call and to mock cache
Co-authored-by: Cursor <cursoragent@cursor.com>
* refactor(mcp): extract helpers to fix PLR0915 too-many-statements in dynamic_mcp_route
Extract _mcp_forward_as_path and _is_mcp_access_group_cached as
module-level helpers so dynamic_mcp_route stays under the 50-statement
limit. Update tests to patch the new module-level symbols directly.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Avoid caching missing MCP access groups
* fix(mcp): stream MCP responses via _stream_mcp_asgi_response instead of buffering
_mcp_forward_as_path previously accumulated the full response body in
memory before sending it. Replace the buffering custom_send pattern with
_stream_mcp_asgi_response, which uses an asyncio.Queue bridge so chunks
are yielded to the client as they arrive, preventing unbounded memory
growth on large or long-lived MCP responses.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(mcp): short-TTL negative cache for access-group existence lookup
An unauthenticated caller could repeatedly request /<unknown>/mcp and
force a fresh DB lookup for the access-group existence check on every
request (only positive results were cached). Cache negative results
for a short DEFAULT_MCP_ACCESS_GROUP_NEGATIVE_CACHE_TTL window (10s by
default) so the DB is shielded from flooding while a transient DB error
(which surfaces as an empty list) cannot hide a real group for long.
https://claude.ai/code/session_01SjyPmwfmrq8fveFgw9iHW9
* fix(mcp): use plain int for access-group negative cache TTL
Drop the os.getenv wrapper around DEFAULT_MCP_ACCESS_GROUP_NEGATIVE_CACHE_TTL
to avoid the documentation_test_env_keys check failing on the new variable.
The negative-cache window is a small internal tuning constant, not a
user-facing knob, so a plain integer is clearer than an env override.
https://claude.ai/code/session_01SjyPmwfmrq8fveFgw9iHW9
* fix(mcp): validate, dedupe, and cap CSV tokens in dynamic MCP route
For /{name1,name2,...}/mcp, validate every token resolves to a known
server alias or access group, dedupe case-insensitively, and cap at
DEFAULT_MCP_NAMESPACE_CSV_MAX_TOKENS=16 before forwarding.
- Bounds the per-request DB / cache fan-out an authenticated caller can
trigger by stuffing the path with tokens (raised by veria-ai).
- Returns 404 instead of forwarding when no token resolves, so the
downstream server filter cannot silently fall back to the full
allowed_mcp_servers list (raised by Cursor agentic security review).
- Forwards only the resolved subset, so unknown tokens cannot ride along
into the downstream filter.
Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
* fix(mcp): exact-match CSV token dedupe to preserve case-sensitive distinct tokens
Bugbot flagged that case-insensitive dedup on `MyGroup,mygroup` could
collapse to whichever case appeared first and silently drop the matching
casing if the downstream resolver is case-sensitive. Switch to exact-match
dedup so distinct casings survive; whitespace-only differences still
collapse via the .strip() before comparison.
Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Claude <claude@anthropic.com>
Co-authored-by: mateo-berri <mateo@berri.ai>
Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
A guardrail entry's ``callbacks`` list (v1: ``{name: {callbacks:[...]}}``,
v2: ``{guardrail_name, litellm_params: {callbacks: [...], guardrail:
"module.path"}}``) is iterated during config load and threaded through
``get_instance_fn``. A PROXY_ADMIN persisting
``litellm_settings.guardrails[*].callbacks: ["s3://..."]`` or
``litellm_settings.guardrails[*].litellm_params.guardrail: "s3://..."``
via ``/config/update`` was not covered by the previous scrub matrix.
Walk both v1 and v2 entry shapes and null out remote-URL callbacks /
module-path values before the merge. Adds four regression tests.
aws_sts_endpoint, aws_web_identity_token, and aws_bedrock_runtime_endpoint
in ingest_options.vector_store were passed directly to the Bedrock ingestion
class, which reads them into boto3 STS client construction. Any authenticated
caller could redirect AssumeRole calls to an attacker-controlled server,
leaking the proxy's instance profile credentials.
Calls is_request_body_safe() on ingest_options["vector_store"] before
forwarding to litellm.aingest(). Same banned-params list and admin opt-in
escape hatch (allow_client_side_credentials) as the /chat/completions path.
ValueError from the safety check is caught and re-raised as HTTP 400.
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* fix(prometheus): emit remaining_tokens/requests gauges for bedrock + vertex (LIT-2719)
Bedrock and Vertex AI never return x-ratelimit-remaining-* response headers,
so litellm_remaining_tokens_metric / litellm_remaining_requests_metric only
fired for OpenAI / Azure / Anthropic deployments even when tpm/rpm was
configured on the router.
Add a provider-agnostic fallback in PrometheusLogger.async_log_success_event
that asks Router.get_remaining_model_group_usage() for the same model_group
and emits the gauges with configured_limit - current_usage when the upstream
provider didn't populate the headers itself. Existing OpenAI / Azure /
Anthropic flows are unchanged because the fallback short-circuits when both
header values are already present.
Tests: 8 new tests covering bedrock + vertex emission, header short-circuit,
partial-header fill, llm_router=None, missing model_group, empty router
result, and router exception swallowing.
Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
* fix(prometheus): narrow except to ImportError, log router lookup failures via verbose_logger.exception
Address greptile review:
- The optional 'from litellm.proxy.proxy_server import llm_router' should
guard against ImportError specifically, not all exceptions, so that
unexpected errors (e.g. AttributeError from partially-initialized state)
stay visible.
- get_remaining_model_group_usage failures are now logged via
verbose_logger.exception (with traceback) instead of debug, matching the
PR description's intent and avoiding silent loss of router-cache errors
in production.
Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
* fix(prometheus): subtract in-flight delta in router-remaining fallback
The router's TPM/RPM counter is incremented by
Router.deployment_callback_on_success, which fires alongside this
prometheus callback in the success-log fan-out. Prometheus wins the
race, so get_remaining_model_group_usage returns the pre-decrement
counter for the current request — while vendor headers
(OpenAI/Anthropic/Azure) are already post-decrement.
That broke parity between providers on the same gauge: dashboards
plotting litellm_remaining_requests_metric showed Bedrock/Vertex
perpetually one request behind Anthropic for the same throughput.
Replay the in-flight increment before emit: subtract total_tokens
from remaining_tokens and 1 from remaining_requests.
* Revert "fix(prometheus): subtract in-flight delta in router-remaining fallback"
This reverts commit 001ce95ecdd952b4b5a23dd2b1e62c4562c932bc.
* fix(router): post-decrement router-derived ratelimit headers
Router.set_response_headers injects x-ratelimit-remaining-{tokens,
requests} for providers that don't return them natively (Bedrock,
Vertex). The values come from get_remaining_model_group_usage, which
reads the router's TPM/RPM counter — incremented post-response by
deployment_callback_on_success. So the headers reflected the counter
state before the current request was counted: pre-decrement.
Vendor headers from OpenAI/Anthropic/Azure are post-decrement (the
vendor counted the request before responding). Same metric name, two
semantics — dashboards plotting litellm_remaining_requests_metric
showed Bedrock/Vertex perpetually one request behind for the same
throughput, and the HTTP response headers exposed the same skew to
clients.
Subtract the in-flight delta before writing: 1 from
remaining-requests, response.usage.total_tokens from remaining-tokens.
Fixes both the response headers and (transitively) the prometheus
gauges that read from standard_logging_payload.additional_headers.
---------
Co-authored-by: cursor <cursor@example.com>
Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
A pass-through endpoint's ``target`` field is passed through
``create_pass_through_route`` into ``get_instance_fn`` during config
load. A PROXY_ADMIN persisting ``target: "s3://attacker/m.i"`` via
the DB-overlay ``pass_through_endpoints`` write path was not covered
by the previous scrub matrix, so the remote module load would still
reach the loader because the YAML-load chain has ``config_file_path``
set.
Walk each entry in ``general_settings.pass_through_endpoints`` and
null out any ``target`` that starts with ``s3://`` or ``gcs://``. The
entry itself is preserved so the path-registration helper can choose
how to handle a missing target (the existing code skips the route
when ``target is None``).
Adds two regression tests.
When ``ProxyConfig`` merges DB-persisted ``litellm_settings`` /
``general_settings`` on top of the YAML config, the merged dict is
later iterated by ``load_config`` which threads ``config_file_path``
(the YAML path) into ``get_instance_fn``. The runtime gate that
refuses ``s3://`` / ``gcs://`` modules when ``config_file_path`` is
``None`` therefore can't distinguish a YAML-sourced value from a
DB-sourced one: both look the same to ``get_instance_fn``.
Strip ``s3://`` / ``gcs://`` entries from the DB-overlay value for
every field whose contents reach ``get_instance_fn`` during config
load:
- litellm_settings: ``callbacks``, ``success_callback``,
``failure_callback``, ``audit_log_callbacks``, ``post_call_rules``,
``custom_provider_map[].custom_handler``
- general_settings: ``custom_auth``, ``custom_key_generate``,
``custom_key_update``, ``custom_sso``,
``custom_ui_sso_sign_in_handler``,
``litellm_jwtauth.custom_validate``
The YAML config-file load path is unchanged — the documented operator
flow (``callbacks: ["s3://bucket/module.instance"]`` in ``config.yaml``)
still works. Only DB-overlay writes (e.g. via ``/config/update``) are
stripped.
Adds 16 regression tests covering the scrub matrix.
Authenticated clients could supply CustomPricingLiteLLMParams fields
(input_cost_per_token, output_cost_per_token, etc.) in the request body.
These were forwarded to register_model() in main.py, permanently mutating
the shared global litellm.model_cost dict for all users on the instance.
Adds all CustomPricingLiteLLMParams fields to _BANNED_REQUEST_BODY_PARAMS
so is_request_body_safe() rejects them before they reach completion().
New pricing fields added to CustomPricingLiteLLMParams are auto-covered.
Admin opt-in via allow_client_side_credentials or
configurable_clientside_auth_params still works as before.
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* fix(fireworks_ai): strip thinking_blocks from chat messages before API call
Fireworks OpenAI-compatible ChatMessage schema uses additionalProperties:false
and rejects Anthropic-style messages[].thinking_blocks (e.g. Claude Code replays),
returning invalid_request_error. Remove the field in _transform_messages_helper
alongside provider_specific_fields.
Adds unit test test_transform_messages_helper_strips_thinking_blocks.
Co-authored-by: Cursor <cursoragent@cursor.com>
* chore(fireworks_ai): drop inline comments from message sanitization
Co-authored-by: Cursor <cursoragent@cursor.com>
* docs(fireworks_ai): explain why provider_specific_fields and thinking_blocks are stripped
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix: strip Gemini thought-signature from tool_use.id in non-streaming path; example websearch config (#27873)
- adapters/transformation.py: mirror the streaming path and strip the
`__thought__<b64>` suffix off `tool_call.id` before building the
AnthropicResponseContentBlockToolUse. Base64's `+ / =` characters
violate Anthropic's `^[a-zA-Z0-9_-]+$` tool_use.id pattern, so when a
conversation that flowed through Gemini is later replayed to an
Anthropic-native provider (Bedrock or Anthropic API) the request 400s.
- example_config_yaml/websearch_interception_config.yaml: register the
interceptor under `callbacks:` not `success_callback:`. `success_callback`
does not run pre-request hooks, so the tool-conversion step never fires
on `/v1/messages` and the raw `web_search_20250305` tool is forwarded
to Bedrock, which 400s.
- adds a unit test pinning the non-streaming strip behavior and the
surviving `^[a-zA-Z0-9_-]+$` shape of the resulting id.
Co-authored-by: oss-agent-shin <279349115+oss-agent-shin@users.noreply.github.com>
* Fix/azure image edit auth header (#27863)
* fix(azure/image_edit): use api-key header instead of Authorization Bearer
Delegate `AzureImageEditConfig.validate_environment` to
`BaseAzureLLM._base_validate_azure_environment` so the image-edit route
follows the same auth resolution as every other Azure provider:
- prefer the Azure-native `api-key` header when an API key is available
- fall back to `Authorization: Bearer <azure_ad_token>` only for AAD auth
The previous implementation unconditionally set
`Authorization: Bearer <api_key>`, which is the OpenAI-direct convention
and is rejected by Azure OpenAI / APIM-fronted deployments with
`401 Access denied due to missing subscription key`.
Adds regression tests covering api_key kwarg, litellm_params.api_key, and
the AAD-token fallback path.
Co-authored-by: Cursor <cursoragent@cursor.com>
* docs(azure/image_edit): pin api-key precedence semantics + add regression test
Address review feedback that the move to
``BaseAzureLLM._base_validate_azure_environment`` changed the relative
priority of the positional ``api_key`` kwarg vs. ``litellm_params["api_key"]``.
The new behavior — ``litellm_params["api_key"]`` wins, positional only fills
in when ``litellm_params["api_key"]`` is empty — is intentional and matches
every other Azure ``validate_environment``: ``AzureVideosConfig`` uses the
exact same merge logic, while ``AzureVectorStoresConfig`` and
``AzureResponsesAPIConfig`` don't accept a positional ``api_key`` at all.
The old ``or`` chain (positional wins) was the outlier and was part of the
same OpenAI-vs-Azure convention drift that produced the original
``Authorization: Bearer`` bug.
The only production caller (``llm_http_handler.image_edit``) sources both
values from the same ``litellm_params.api_key``, so this change is
behaviorally a no-op there. Document the precedence in the docstring and
lock it in with an explicit test so future refactors can't quietly
re-invert it.
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: yuneng-jiang <yuneng@berri.ai>
Co-authored-by: ryan-crabbe-berri <ryan@berri.ai>
Co-authored-by: Adam Kirstein <adam.kirstein@disney.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
* test(azure/image_edit): expect api-key header instead of Authorization Bearer
PR #27863 fixed Azure image edit to use the Azure-native api-key header
instead of OpenAI's Authorization: Bearer convention, but did not update
test_azure_image_edit_litellm_sdk to match. The test still asserted
'Authorization' in headers, which now fails since the new code routes
through BaseAzureLLM._base_validate_azure_environment and emits
api-key when an api_key is provided.
Update the assertion to pin the correct Azure behavior: api-key header
present with the resolved key, and no Authorization header.
---------
Co-authored-by: oss-agent-shin <ext-agent-shin@berri.ai>
Co-authored-by: oss-agent-shin <279349115+oss-agent-shin@users.noreply.github.com>
Co-authored-by: Adam Kirstein <107421694+justalittleadam@users.noreply.github.com>
Co-authored-by: yuneng-jiang <yuneng@berri.ai>
Co-authored-by: ryan-crabbe-berri <ryan@berri.ai>
Co-authored-by: Adam Kirstein <adam.kirstein@disney.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Ishaan Jaffer <ishaanjaffer0324@gmail.com>
* fix(ollama): Include provider in model list for ollama (#26135)
* Include provider in model names for ollama
* Fix unit tests
* fix(ollama): process both thinking and content in same streaming chunk (#26098)
* fix(health_check): skip max_tokens for image_generation mode (#26417)
* fix(health_check): skip max_tokens for image_generation mode
`_update_litellm_params_for_health_check` injected `max_tokens` for
every deployment. OpenAI `/v1/images/generations` strictly rejects
unknown fields, so health checks for dall-e-* and gpt-image-1 always
failed with `400 "Unknown parameter: 'max_tokens'"` even though the
actual image endpoint calls succeed. Skip the `max_tokens` injection
when `model_info.mode == "image_generation"`. `messages` still gets
injected (downstream `_filter_model_params` already strips it for
non-chat handlers).
* Switch to allow-list with per-deployment override
Per @krrishdholakia review: deny-listing image_generation only re-introduces
the same bug for every other non-chat mode (embedding, audio_*, rerank,
video_generation, ocr, search, moderation, ...).
Replace the single image_generation skip with `_MAX_TOKEN_SUPPORT_MODES =
{chat, completion, responses}`. Missing `mode` is treated as chat for
backward compatibility. New modes are safe by default.
Add `model_info.health_check_supports_max_tokens` as an operator escape
hatch — True forces injection on a non-listed deployment (operator wants
to bound probe tokens), False suppresses it on a chat-style deployment
behind a strict-schema provider.
Tests: parametrize over 3 chat-style + 10 non-chat modes, plus override
on/off and the no-mode legacy path.
* fix(http_handler): handle RequestNotRead in MaskedHTTPStatusError for multipart uploads (#26718)
Squash-merged by litellm-agent from dawidkulpa's PR.
* fix(ollama): guard against double 'ollama/' prefix in live model listing
Greptile flagged that Ollama servers can return names that already start
with 'ollama/'. Check the prefix before prepending so we don't produce
'ollama/ollama/...'. Adds a regression test.
* Fix Ollama empty reasoning stream chunks
Co-authored-by: Yassin Kortam <yassin@berri.ai>
---------
Co-authored-by: James Myatt <james@jamesmyatt.co.uk>
Co-authored-by: VHash <225398745+vhash0@users.noreply.github.com>
Co-authored-by: hayden <sewhan.kim+@a-bly.com>
Co-authored-by: dawidkulpa <84176950+dawidkulpa@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Claude <claude@anthropic.com>
Co-authored-by: Yassin Kortam <yassin@berri.ai>
