This reverts merge commit 2b1bd20834 (#31125)
Two CircleCI jobs on the staging-to-main promotion went red the moment
that PR landed. proxy_multi_instance_tests boots two proxies against one
database, and both now race the same migration:
Error: P3018 A migration failed to apply
Database error code: 40P01, deadlock detected
Process 73 waits for ShareLock on virtual transaction 4/11;
blocked by process 75. Process 75 waits for ExclusiveLock on
advisory lock [16384,0,72707369,1]; blocked by process 73
Neither proxy comes up, so the job times out after 300s waiting on
localhost:4000. The same wait took 36.5s on the last green run
Timeline: #31125 merged at 18:46:14Z and the failing run started at
18:49:59Z. The merge commit is not an ancestor of the last green
revision (194a3cc) and is an ancestor of the first failing one
(01de2837)
The v2 resolver was meant to avoid exactly this class of contention, so
the deadlock looks like a bug in it rather than a reason to abandon it.
Putting the default back to v1 buys time to fix it without holding up
the release
The omitted-format path deliberately no longer dispatches through
embeddings.create, so four legacy tests now intercept at the transport or
client.post instead. Also adds a bypass error-path unit test, rewords a stale
comment and a README scope note, and ratchets the lint budgets down.
Consolidate the new regression tests into
test_openai_embedding_encoding_format_default.py, replacing mocks that
pinned the old float default with respx captures of the request body,
and update the stale local_testing default-float test to assert
omission
The v2 resolver skips the diff-and-force recovery that caused schema
thrashing when two LiteLLM versions contend for one database during a
rolling deploy. The standalone migration Job already defaulted to v2; this
aligns the proxy-server path.
v1 stays reachable two ways: --use_legacy_migration_resolver on the CLI, and
USE_V2_MIGRATION_RESOLVER=false for containerised deploys, where
prisma_migration.py calls run_server with a fixed argv and the env var is the
only route in. --use_v2_migration_resolver still parses, so existing commands
do not die on an unknown option.
Because v2 fails fast where v1 retried every failed deploy, a database that is
not accepting connections yet, or another instance holding the migration
advisory lock, would now kill a boot that used to ride it out. Those two
failures are retried, with Prisma's stderr logged each round, and still raise
once the attempts are spent.
Moves the resolver tests from litellm-proxy-extras/tests, which no CI job
runs, into tests/litellm-proxy-extras, and repoints the dedicated Postgres
CircleCI job at the legacy path so v1 keeps real-DB and proxy-boot coverage.
batch_completion collects per-request failures into its result list rather than
raising them; its own source says "return exceptions if any". So the test's
`except Timeout` and `except litellm.InternalServerError` arms could never fire for
the case they were written for. An upstream 500 instead reached
`response.choices`, raised AttributeError on the exception object, and fell through
to the bare `except Exception` that calls pytest.fail. That is what CircleCI hit.
The tolerance now reads the returned values, which is where the failures actually
are. The same two exception types are tolerated as before, nothing broader.
Checked against four injected outcomes: three InternalServerErrors pass, three
Timeouts pass, an AuthenticationError fails, and a response whose content is None
fails. So it is not tolerating its way to a vacuous green.
test_opik_logging_http_request asserted "nothing has been POSTed yet" roughly one
second into a window governed by OpikLogger's 5-second periodic flush. On a loaded
CI worker the five preceding acompletion calls eat that budget, the periodic flush
fires, and the assertion flips. Reproduced with no product changes at all: letting
5.5 seconds pass before the assertion drains the queue and sets mock_post.called,
which is exactly the failure CircleCI reports.
The test now pins flush_interval past anything the test can reach, so the two
batching assertions measure batching instead of wall clock, and drives the flush
path explicitly at the end rather than sleeping the interval. That last phase used
to be near-vacuous, since the size-triggered flush had already emptied the queue.
Assertions now match only calls to Opik's own /traces/batch and /spans/batch.
get_async_httpx_client caches one client per special provider, so the mock is
process-wide and any other logging callback's POST would otherwise count.
Dropped the teardown that closed that shared client, which broke every later test
in the same worker that logs through it, and the try/except that turned assertion
failures into a pytest.fail with no traceback.
Mutation checked: flushing on every event and never flushing on size both fail the
test.
- test_custom_callback_input: audio redaction assertion expects None content
(redaction leaves None untouched, gpt-audio-1.5 returns content=None)
- local_testing conftest: drain GLOBAL_LOGGING_WORKER in isolate_litellm_state
teardown so mocked-router tests stop leaking pending logging tasks into
test_gcs_pub_sub
- test_together_ai: tools is always a supported param now; only response_format
is gated by function-calling support
- test_keys: /team/new omits models instead of sending null (422), so the key's
team really exists and auth no longer raises TeamNotFoundError
- test_team_delete_member_add_race: per-test unique team and user ids so xdist
workers sharing one Postgres stop deleting each other's team mid-race
* test: drop the cwd-relative sys.path.insert calls from the test suite
TQ003 stands at 1,077 across 1,058 files, and 1,015 of them are the same shape:
sys.path.insert(0, os.path.abspath("../..")) and its deeper siblings. The
argument resolves against the working directory rather than the file, so from
the repo root, where every job runs pytest, it inserts the directory two levels
above the checkout. It has never pointed at litellm. The package is installed
into the environment anyway, which is what actually makes the import work, and
what the rule's message has said all along.
Removing them leaves 1,634 imports of sys and os with no remaining reference,
and those go too, except where another test module imports the name back out of
the file. The rest of TQ003 is 62 call sites that resolve against __file__ or a
variable, which are a different question and are left alone.
Collection is identical either way: 45,871 tests and the same 51 pre-existing
collection errors before and after, and ruff reports no new undefined name.
* test: drop the duplicate imports the sys.path sweep exposed to F811
* test(pre-call-utils): restore the os import the new bedrock tests need
* test: unshadow the module handles the F811 sweep left behind, and pin the two live tests that went red with it
The F811 sweep in #37878 removed the fixture-local `import litellm` from four
conftests, but the bare `import litellm.proxy.proxy_server` a few lines below
still binds `litellm` as a function local, so `importlib.reload(litellm)` runs
before the name is assigned and every test in those directories errors at
setup. The `hasattr` guard on the line above already proves the module is
loaded, so the import only ever bound the name. Drop it, and enable F823 in
ruff-tests.toml, which flags all four sites at the failing line and would have
blocked the sweep
The same sweep renamed the `check_non_streaming_response` parameter but left
one read of `completion`, which now resolves to `litellm.completion`, and
removed an import whose side effect was the only thing making
`litellm.proxy.proxy_server` reachable in the moderation hook test. That test
already takes `monkeypatch`, so patch the router through it and stop leaking
the router into later tests
`test_content_policy_exception_openai` passed vacuously until #37887 turned it
into a real `pytest.raises`, and OpenAI no longer rejects a lyrics prompt with
a content policy error. Inject an AsyncOpenAI client whose transport answers
with OpenAI's own `content_policy_violation` rejection so the mapping to
ContentPolicyViolationError is exercised every run
`test_async_create_batch` hit a 409 cancelling a batch OpenAI had already
marked failed. The cancel step tolerated a completed batch but not a failed
one. Fold both guards into one helper that tolerates a failed batch only when
OpenAI's recorded error is the org's enqueued token limit, and prints the
batch's errors so the reason is in the log either way
* test: close the injected AsyncOpenAI client after the content policy test
* chore(lint): ratchet TQ005 down by the global mutation this branch cleared
* chore(lint): ratchet TQ005 to 2660 on the merged tree
* chore(lint): ratchet TQ005 to 2561 on the merged tree
* chore(lint): ratchet TQ005 to 2548 on the merged tree
Four more ruff rules for code the test suite runs but never checks. F601 is the
one that paid: the duplicate key it flagged in a get_form_data fixture was the
mock reproducing the production bug fixed in the previous commit.
B025 removed two unreachable handlers, one of them a pytest.skip shadowed by an
earlier `pass`, so an upstream Vertex flake reported green having asserted
nothing. F632 turned an `is ""` identity check, which passes only on CPython
interning, into the `== ""` it meant. B023 fixed three closures over loop
variables, all latent today but one iteration-order change away from checking the
last case N times.
A test that asserts on the error inside its own except block passes when the
call stops raising, because nothing runs the handler. That is the exact case
the test exists to catch, so the regression lands green.
Rewrites all 111 such blocks into pytest.raises, which fails when the call
succeeds, and selects PT017 in ruff-tests.toml so no new one lands.
A name bound twice keeps only the second binding. In `tests/` that is nearly
always a repeated import, harmless but misleading, and the same rule is what
catches the cases that are not harmless: a local that shadows an import the
module still calls, and a second `def test_x` that quietly replaces the first.
311 of the 344 sites were repeated imports and came out with ruff's own fix.
The remaining 33 needed a decision. Four modules imported a name they never
used because a local definition below already shadowed it. Two comprehensions
bound `call` over `unittest.mock.call`, which those modules import and use.
One test rebound the two module handles its nested reload closure had captured.
One class attribute shadowed an unused `status` import.
The load-test fixtures move to a conftest, which is how pytest is meant to share
them, so the test module no longer imports three fixture names it never calls.
The nine `prisma_client` parameters keep a narrow `noqa`: pytest resolves that
fixture by name before the body runs, so the parameter never shadows anything.
`pytest.raises(Exception)` with no `match=` passes on any error that broad. A
TypeError from a refactor, a botched fixture, an import that moved: all of them
read as the rejection the test claims to police, so the test goes green for the
wrong reason and stays green after the behaviour it guards is gone.
PT011 closes that gap for the 317 sites B017 could not reach, because B017 only
fires on a single-statement body with no `as e` binding. Each pattern here is the
message the code actually raised, recorded by running the sites under a plugin
that logged the concrete type and text per call site, so the assertions describe
observed behaviour rather than a guess. Where a site raises more than one message
across its parametrize cases, the pattern is an alternation of what was seen;
where the exception carries an empty `str()` and puts the text on `.message`, the
site keeps a narrow `noqa` with the reason.
PT014 removes four parametrize cases that were listed twice. The duplicate re-runs
an assertion that already passed, and it usually marks a case someone meant to
vary and forgot to edit.
* test: enforce PT012 so a pytest.raises block cannot hide dead assertions
`with pytest.raises(...)` stops at the first statement that raises. Anything
sequenced after it inside the block never runs, so an assertion written there is
never checked and the test still reports green.
Two sites were doing exactly that, and both assertions turned out to be wrong
once they started running. tests/llm_translation/test_prompt_factory.py asserted
the bedrock rejection names "requires at least one non-system message", which
holds. tests/proxy_unit_tests/test_proxy_server.py asserted the prisma startup
failure mentions "httpx.ConnectError", which never appears: the failure is an
httpx.ConnectError whose message is "All connection attempts failed", so that
test now asserts the type. Its DATABASE_URL override moves to monkeypatch, since
the old restore sat below the assertion and leaked the invalid URL into every
later DB test the moment the assertion started being able to fail.
The remaining 72 sites are rewritten without changing what they exercise: setup
that cannot raise moves above the block, a nested `patch` moves outside it, and
bodies with real control flow (a stream drain, an if/else on sync_mode, a
retry loop) move into a local closure the block calls.
Fixing PT012 unmasked two B017s, since ruff only reports a blind
pytest.raises(Exception) once the block holds a single statement.
tests/proxy_unit_tests/test_auth_checks.py narrows to the ProxyException
can_key_call_model actually raises. tests/local_testing/test_completion_cost.py
was asserting vertex_ai/medlm-medium has no cost entry, which stopped being true
at some point; that dead first half is gone and the rest of the test, which
checks medlm pricing resolves above zero, now runs instead of being skipped.
* chore(ci): ratchet TQ004 to 768 after the prisma test moved to monkeypatch
Every live together_ai call in CI has answered 503 Service unavailable since
2026-08-20, across two runs 2.5 hours apart, while Together's status page
reported no incident in either window. These are real calls, not replayed
cassettes: the VCR layer runs filter_non_2xx_response, so a 503 is never
written to a cassette and cannot be replayed back.
Qwen/Qwen2.5-7B-Instruct-Turbo does not appear anywhere on Together's monitored
component list, whose Qwen entries are all Qwen3.x, so a model-level outage
there would never surface as an incident. The same 503 already forced
test_basic_rerank_together_ai to be skipped on a different together_ai model,
so per-model 503s are an established failure mode here rather than a platform
outage.
openai/gpt-oss-20b is the cheapest together_ai entry that carries real pricing
and the capabilities these suites exercise, at $0.05/$0.20 per 1M tokens with
function calling, response schema and tool choice. Together monitors it as a
served component. The retired model also carries null pricing in the cost map,
which is its own liability now that unpriced models are blocked.
test_multiple_deployments.py keeps the old id: it is a router fallback list
that is green today, and busting its cassette to prove a point would trade a
passing test for a live call this change cannot vouch for.
* test(lint): ban blind pytest.raises(Exception) with ruff B017
A bare pytest.raises(Exception) accepts whatever the body throws. The TypeError
a refactor introduces satisfies it exactly as well as the rejection the test was
written for, so the crash reads as a pass and the test never goes red.
All 111 existing sites are narrowed here. A runtime probe recorded the concrete
exception each one actually catches, and each site now names that type. Where
the code under test genuinely raises a bare Exception, the site pins a stable
slice of the message with match= instead.
Two sites tell on themselves. The shared responses-API cancel test raises
"custom_llm_provider is required but passed as None" rather than talking to a
provider at all, because cancel_responses takes a provider, not a model. And
test_bedrock_guardrails_with_streaming was the only test in its file still
passing without AWS credentials, because the NoCredentialsError boto3 raised
long before the guardrail ran satisfied the blind raises.
* fix(test): widen the openai batch-dispatch assertion to OpenAIError
The narrowed NotFoundError only holds where OPENAI_API_KEY is set. Without one
the SDK raises OpenAIError while building the client, long before any 404, so CI
went red. OpenAIError covers both and still rejects a TypeError from a refactor.
* test(ci): serve /moderations from the canned OpenAI mock
The otel proxy E2E job points its `openai/*` wildcard deployment at the
canned mock, and #37492 made `get_model_list` agree with
`get_available_deployment` on bare model names. /moderations now resolves
`omni-moderation-latest` to that wildcard deployment the way
/chat/completions already did, so the request lands on the mock, which
never implemented the route and answers a bare 404.
Add /moderations and /v1/moderations to the mock, returning an
OpenAI-shaped response with one result per input item.
* style(ci): annotate the new moderations locals as Final
`assert False` inside a `try:` raises AssertionError, which the `except
Exception` right below it catches, so several tests reported green no matter
what the code did. `pytest.fail` raises Failed, a BaseException, and escapes.
A bare `a == b` statement is evaluated and discarded. Nine of those sat in
tests, and one was comparing against a model name the router never produces.
Selects B011, B015, B018, PT015, PLR0133 and PLW0127 in ruff-tests.toml
alongside F821, with all 50 existing violations fixed, so no budget file or
ratchet is needed. CI already runs this config over tests/.
ruff.toml excludes tests/* from `ruff check`, so nothing has ever checked the
test tree for names that do not exist. That matters more in tests than in
product code: a NameError inside a test whose body is wrapped in
`except Exception: pass` is swallowed, and the test reports green forever.
Adds ruff-tests.toml selecting F821 alone, wired into the lint workflow and
`make lint-ruff`, and clears every existing violation:
- 4 tests interpolated an unbound `e` into a `pytest.fail` message reached only
on the failure path, so the NameError, not the assertion, is what ran.
test_llm_guard_error_raising is the worst: it passes today with content
safety disabled entirely. It now asserts the 400 and its detail body.
- 5 sites construct BaseExceptionGroup, a 3.11 builtin, in a tree that still
supports 3.10. Guarded behind the exceptiongroup backport that anyio already
pulls in below 3.11.
- 9 missing imports (json, openai, Any, Final, HTTPException), including one in
a helper that catches HTTPException by a name it never imported, so the
challenge path it exists to detect raises NameError instead.
- 5 annotations naming types imported inside the function body, hoisted to
module scope or TYPE_CHECKING.
- 2 blocks of dead code: everything after a pytest.fail in
test_claude_agent_sdk, and an unused helper in test_end_users calling a
function defined in a different module.
- 1 error-path f-string in the router-settings doc test that masked the real
FileNotFoundError behind a NameError.
Only F821 for now. Widening the select list means ratcheting thousands of
pre-existing findings, so rules go in one at a time with their violations
already fixed.
* test: replace blind sleeps with deadline waits in callback and caching tests
tests/local_testing/test_custom_callback_input.py slept a fixed 1-3s after
every call and then asserted the callback handler recorded no errors. Because
the handler only appends to `states` when a callback actually fires, an assert
of `len(errors) == 0` passes just as happily when nothing fired at all, so the
sleep was buying flakiness in exchange for a vacuous check. The async tests
were worse: `time.sleep` blocks the event loop, so the success/failure tasks
scheduled on it could not run before the assertion.
Adds tests/_wait_helpers.py with `wait_until` / `await_until`, which poll a
predicate against a deadline, and converts all 17 sites to wait on the thing
the test actually cares about (the terminal state landing in `states`, or the
patched log hook being called). The waits assert the callback fired, so these
tests now fail on a dropped callback instead of passing silently.
The three sleeps in test_caching_handler.py sat between `sync_set_cache` and
`_sync_get_cache`, both fully synchronous against a local in-memory cache, so
they are just deleted.
* fix(test): wait on the priming call's own logging in the cache-hit test
The 3s sleep in test_logging_async_cache_hit_sync_call was not waiting for the
cache write, which lands before the stream iterator is exhausted. It was
waiting for the priming call's success callback to drain, so the handler
installed right after it only ever sees the second, cache-hit call. Waiting on
a populated cache_dict let the priming call's still-pending log_success_event
reach the new mock, and the test then read cache_hit off the wrong payload.
Waits on the priming handler's own sync_success state instead.
Python binds a name once per scope, so when a module or class defines the same
test twice only the last one exists. The earlier definitions are unreachable:
pytest never collects them, and nothing that references them can fail.
A sweep in August cleared nine of these. Five have appeared since, which is the
argument for a rule rather than another sweep.
Each survivor is the better version, so nothing is lost. The two SQS logger
twins additionally stub `asyncio.create_task`, which the shadowed copies did
not. The cost-calculator duplicate is a two-line stub that also takes a
`model_item` parameter no fixture supplies, so it could not have run even
unshadowed. The two `test_prompt_caching` bodies are both `pass`.
Collecting the four files reports 416 tests before and after.
`tests/proxy_unit_tests/conftest copy.py` goes with them. pytest only loads a
file named exactly `conftest.py`, nothing imports this one, and the space in the
name says what it was.
The earlier sweep only caught the conformance suite in tests/llm_translation.
Groq retired llama-3.1-8b-instant alongside llama-3.3-70b-versatile, and four
tests under tests/local_testing still call them for real, so litellm_router_testing
and both local_testing shards 404 with model_not_found.
Only the sites that leave the process move. The chunk fixtures in
test_stream_chunk_builder, and the cost and routing tests that never open a
socket, keep the old ids because the string is data there, not a request.
* feat(complexity_router): custom classifier plugins via classifier_type 'plugin'
Adds a third classification mode where an operator-supplied hook decides the
tier instead of the heuristic scorer or the LLM classifier. The hook implements
an async classify(context) returning a tier name (built-in value, tier_labels
label, or tier_definitions name) or None to decline; failures, timeouts, and
unknown tiers fall back exactly like a failed LLM classifier. The context
carries the request messages and metadata, including caller identity, so a
plugin can route by team, spend, or any business rule.
The plugin resolves from a dotted path at proxy startup with a load-time check
that classify is a coroutine function, and is closed off over HTTP like the
routing plugins list. Routing decisions record the new classifier_plugin cause.
tier_definitions now accepts classifier_type 'plugin' alongside 'llm'.
* fix(proxy): resolve plugin dotted paths in _delete_deployment before hashing ids
The db-sync reconcile re-reads the raw config and hashes litellm_params to
compute which ids the config wants served, but the router's ids were hashed
from the resolved params where plugin dotted paths are live instances. The
mismatched ids made the reconcile evict every plugin-bearing auto-router one
sync after startup, on any proxy with a database connected. This also affected
the existing routing plugins list, not just the new classifier plugin.
Resolving the plugins in _delete_deployment the same way load_config does makes
both sides hash the same canonical form. A plugin module broken on disk at
reconcile time skips cleanup instead of evicting valid deployments, matching
how a get_config failure is handled
* fix(complexity_router): treat non-string plugin verdicts as declines, centralize the empty-mapping sentinel
A hook returning a non-string raised inside resolve_classified_tier outside the
plugin exception boundary, failing the request instead of falling back. Also
moves the read-only empty mapping to constants.py per repo convention and moves
the classifier plugin product docs out of the package README for the docs repo
* refactor(complexity_router): rename the plugin classifier mode to classifier_type 'custom'
The mode value now names the operator's intent while classifier_plugin keeps
naming the mechanism; routing decisions keep the classifier_plugin cause
* refactor(proxy): pin plugin-bearing deployment ids from the raw params instead of resolving in the reconcile
Replaces the previous approach of re-running plugin resolution inside
_delete_deployment, which imported operator modules on every reconcile cycle
and skipped the whole cleanup pass when any one module was broken on disk.
load_config now stamps model_info.id from the raw litellm_params before
resolution swaps dotted paths for live instances, so the reconcile's raw-config
hash matches by construction and needs no resolution at all: a broken module
cannot stall cleanup for unrelated models, and any future param-transforming
resolution is covered by the same pin. _generate_model_id becomes a staticmethod
so the pin can run before the Router exists; its statically dead non-string key
branches are removed. Also documents candidate_models as an informational
snapshot for classifier plugins, unlike the narrowing surface RoutingPlugin
filters
* fix(router): restore _generate_model_id key handling, align classifier context with the routing-plugin pattern
The staticmethod conversion accidentally dropped the non-string-key branches
from _generate_model_id, a silent hash change for any params with non-string
keys; they are restored verbatim. The classifier plugin context now follows
the Router-level routing-plugin recipe exactly: structured messages come from
resolve_structured_messages over the raw messages, and the metadata key comes
from the shared get_metadata_variable_name_from_kwargs helper, which also
replaces the duplicated inline sniff in _pick_model_for_tier. This removes the
raw-or-resolved fallback where a plugin could silently receive resolved
messages when a call site forgot to pass the raw ones
* refactor(router): make generate_model_id public, guard classifier context construction
Two modules legitimately hash deployment ids with the same helper now (Router
and the proxy's config-load pin), so the private name was lying about its
audience and the cross-module call needed a pyright suppression; renaming it
public restores the static safety net. The classifier plugin's RoutingContext
construction moves inside the failure boundary, matching the LLM path where
litellm-side prompt building also falls back rather than failing the request,
and a prompt-only call with no message list is now covered by a test
Three groups, all verified by running the suite rather than by inspection.
18 files whose every test function carries an unconditional @pytest.mark.skip,
39 test functions in total. They are collected on every CI run and always skip,
so they advertise coverage the suite does not have. Reasons on the marks include
"AWS Suspended Account", "lakera deprecated their v1 endpoint" and "moved to
using 'otel' for logging"; 26 of the marks predate 2025.
30 test functions with a byte-identical body and identical decorators to a
sibling in the same file and class, differing only in name. Deleting one of each
pair removes no coverage. Four further candidates were excluded because they
override an inherited test, where deleting the override un-shadows the base
class implementation instead of removing a duplicate.
9 test functions that a later definition of the same name shadows, so Python
never binds them and pytest cannot collect them.
One file that is a demo script rather than a test; its own docstring says to run
it with python.
Verification: collecting the 26 edited files gives 2,492 node IDs before and
2,462 after. The 30 duplicate deletions account for exactly 30 removals, the 9
shadowed deletions account for 0 (confirming at runtime that they were never
collectable), nothing unexplained disappeared, and nothing new appeared. No
other test or module imports any deleted symbol.
AWS no longer serves `anthropic.claude-3-sonnet-20240229-v1:0`. The streaming
path returns a plain 404, "Model with the provided id
anthropic.claude-3-sonnet-20240229-v1:0 is not found", and the non-streaming
path answers 500 for the same reason. Our own cost map has carried a
2026-07-30 deprecation date for it since #36538
That accounts for 20 failures across local_testing_part1, local_testing_part2
and llm_translation_testing. litellm maps both statuses correctly, so the
tests are what went stale, not the client
Replacement is `us.anthropic.claude-sonnet-4-5-20250929-v1:0`: a like-for-like
Sonnet, and the newest Bedrock Sonnet this repo exercises against the real API
in tests/e2e. Newer ids exist in the cost map, but nothing in the repo calls
them live, so picking one would be an unverified guess about model access on
the CI account
Scope is limited to the tests that actually issue a request. The occurrences
that assert on the model string itself, or that feed mocked transformations,
keep the old id so their assertions stay meaningful
`supports_native_structured_output` was set only on the bare `deepseek.v3.2`
and `zai.glm-5` entries, so the cross-region inference profiles and the
region-pinned ids resolved to None. The flag gates the native
`outputConfig.textFormat` branch in BedrockConverseConfig, so callers
addressing the same model as `us.deepseek.v3.2` or
`bedrock/us-west-2/deepseek.v3.2` silently fell back to synthetic tool
injection. `us.` is the form Bedrock steers callers toward, so the most
common way to reach these models was the one missing the capability.
Adds the flag to the 12 affected ids and keeps the packaged backup in sync.
test_get_model_info_bedrock_models already caught the region-pinned ids, but
it filters on `litellm_provider == "bedrock"` and the cross-region profiles
carry `bedrock_converse`, so reverting just `us.deepseek.v3.2` and
`eu.deepseek.v3.2` left it green. The new parity test covers the prefixed
profiles and fails on exactly that mutation.
The management route-coverage guard fires because /team/metadata_schema landed
in #33353 without a behavior-suite scenario, so this adds one covering the nine
seeded actors plus the unauthenticated 401
The prometheus budget-metric assertions read the log call's first positional
arg, which #35703 turned into an unrendered "%s" format string when it moved
logging to lazy args. They now render the message from the call args, which
also pins the arg order and the exception text that the old substring check
never reached
GitHub Models was fully retired on 2026-07-30, so test_completion_github_api
can no longer pass: the endpoint the github provider targets returns 404 and
models.github.ai answers 410 "github_models_retirement_brownout". The dead live
test is removed rather than skipped
_delete_deployment stopped returning a count of evictions in #35400 and now returns
the frozenset of ids the db and config still want, so a caller judging its own reload
can tell a deliberate eviction from a deployment that went missing. These two tests in
tests/local_testing were left comparing that frozenset against an int and have been
failing since; the directory is only referenced by .circleci/config.yml, which no
longer reports checks on PRs, so nothing caught them.
The eviction behavior itself is unchanged, so the fix is on the assertions: compare
against the expected id set, and pin the router's surviving ids so a mutation that
evicts the wrong deployment is caught rather than passing a bare length check.
aiohttp 3.14.0 and 3.14.1 re-arm the sock_read timer on a keep-alive
connection after it has already been returned to the idle pool. The stray
timer stamps a SocketTimeoutError on the pooled connection without closing
it, so the pool keeps handing it out and the next request to pick it up
fails instantly on an error left behind by an earlier, unrelated request.
Because a single pool is shared across providers, the failures appear
simultaneously across Vertex AI, Bedrock, Anthropic and OpenAI-compatible
deployments as sub-millisecond "Connection timed out" errors.
uv.lock resolved aiohttp 3.14.1 and the published images install via
`uv sync --frozen`, so every image built from that lock shipped the
regression. The wheel's own metadata declared `aiohttp>=3.10,<4.0`, which
also left pip consumers free to resolve into the same broken window, so
both the runtime floor and the uv constraint move to >=3.14.2.
Upstream fixed this in aio-libs/aiohttp#12954, released in aiohttp 3.14.2;
the lock now resolves 3.14.3. Raising the floor rather than capping below
3.14 keeps the advisories that the existing 3.14.1 floor cleared, so no
osv-scanner ignores are needed. litellm requires Python >=3.10 and aiohttp
3.14.2 requires >=3.10, so no supported interpreter loses support.
Both new tests fail on the previous pins and pass on these.
* fix(passthrough): stream non-sse passthrough responses instead of buffering in memory
Non-SSE passthrough responses were fully read into proxy memory (content = await response.aread()) before the first byte reached the client. For large non-JSON bodies such as Anthropic batch results jsonl files this ballooned proxy RSS to a multiple of the file size and produced near-total TTFB dead air, letting intermediaries kill the silent connection and truncate the download.
The upstream request is now sent with httpx stream semantics and the buffering decision is made from the response headers: application/json (and +json) bodies plus upstream errors keep the buffered behavior since spend logging, guardrails and managed-id rewriting inspect them, while every other 2xx body is relayed as a StreamingResponse that iterates upstream bytes without accumulating them, preserving status code and headers (including x-litellm-*) and firing the success-handler logging with response_body=None once the stream completes.
* fix(passthrough): log client disconnects mid-stream and derive test client cache key from production code
* test(passthrough): intercept AsyncClient.send in legacy passthrough tests and assert final wire params
* test(passthrough): fail with a clear assert when the passthrough client cache scan misses
* fix(main): stop per-request custom pricing from clobbering shared model_cost pricing
A request routed through a wildcard deployment with explicit zero pricing
(e.g. openai/* with input_cost_per_token: 0) registered that pricing on the
shared {provider}/{model} key in litellm.model_cost, so sibling deployments
relying on built-in pricing logged $0 until process restart (LIT-3991).
Request-time registration in completion()/embedding() now mirrors the
router-startup isolation: router-originated requests register full pricing
under the deployment's unique model id only, while the shared backend key
receives the entry with custom pricing fields stripped. Direct SDK calls
without a router deployment id keep the legacy shared-key registration.
The stripping logic is shared via
CustomPricingLiteLLMParams.strip_custom_pricing_fields and reused by
Router._create_deployment and Router.add_deployment.
* test: update legacy tests that asserted per-request pricing leaking into shared model_cost
test_router_fallbacks_with_custom_model_costs asserted the shared
claude-sonnet-4-5-20250929 entry ends up with the deployment's 30/60
pricing, which is exactly the cross-deployment leak this PR removes; it
now asserts the shared key keeps the built-in pricing, matching the
test's stated goal.
test_cost_calc.py::test_run computed streaming cost via
completion_cost(response), which only matched the non-stream cost while
the shared gpt-3.5-turbo entry was poisoned with the per-request
2/token pricing; it now passes the request's custom pricing explicitly
via custom_cost_per_token.
* fix(bedrock): drop strict/additionalProperties from toolSpec for Claude Sonnet 4
Claude Sonnet 4 on Bedrock Converse rejects toolSpec.strict and
additionalProperties the same way Opus 4.7/4.8 do. Add
bedrock_converse_supports_strict_tools: false to all Sonnet 4 regional
variants so those fields are suppressed before the request is sent.
Co-authored-by: Cursor <cursoragent@cursor.com>
* test(bedrock): assert additionalProperties dropped for strict-unsupported models
Rename the regression test to reflect Opus 4.7/4.8 and Sonnet 4 coverage,
and assert both strict and additionalProperties are stripped from toolSpec.
Co-authored-by: Cursor <cursoragent@cursor.com>
* test(fireworks): skip embeddings live test when provider account is suspended
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Claude <noreply@anthropic.com>
* feat: declarative fallback generalizations for unknown models
Unknown or newly-released models previously degraded (missed cost lookups,
wrong supports_* flags, broken provider routing) and were patched with one-off
hardcoded regexes scattered across Python. This adds a single data-driven source
of truth: a fallback_generalizations block in model_prices_and_context_window.json
holding ordered, case-insensitive regex rules that map a model name to the
metadata to apply when it has no exact entry.
A new fallback_generalizations module owns the rules and a compiled-regex cache
that is built once and invalidated on reload, so the O(n) scan runs only on a
cache miss. get_llm_provider now routes an otherwise-unknown model via the first
matching rule's litellm_provider, replacing the hardcoded _CLAUDE_PATTERN and
_matches_claude_model_pattern. _get_model_info_helper falls back to a matching
rule's model_info after the exact lookups miss, so get_model_info and the
supports_* helpers resolve unknown models from the same rule. get_model_cost_map
extracts the block out of the returned map, and the integrity check now counts
real model entries (excluding reserved meta keys) so the new key cannot mask a
genuinely shrunk upstream file.
The top level of the file stays a flat map of models so existing litellm releases
that fetch the live file keep working and keep receiving updates; the block ships
in both the root file and the bundled backup. An anthropic-claude rule reproduces
the old future-claude routing and additionally supplies capability flags and a
context window
https://claude.ai/code/session_01G8Jro8dPLktwnaaSJwVDpo
* refactor(anthropic): derive adaptive-thinking from a version threshold; harden generalizations
Replace the per-minor-version _is_claude_4_6_model / _is_claude_4_7_model substring
matchers with a single _claude_version_at_least predicate that parses the Claude
family version from the model name and compares against 4.6. This covers 4.8/4.9/5.x
without a code change (the old matchers missed 4.8 entirely) while keeping an explicit
supports_adaptive_thinking flag authoritative when present, so there is one source of
truth. The two direct call sites in the chat transformation now route through
_is_adaptive_thinking_model instead of the deleted matchers.
Also address review feedback on the generalizations module: return a copy of the
matched model_info so a future caller cannot mutate the compiled-rule cache, document
that patterns are matched with re.search and must anchor with ^ and $, and reindent
the fallback_generalizations block to the file's 2-space style in both JSON files.
https://claude.ai/code/session_01G8Jro8dPLktwnaaSJwVDpo
* fix(anthropic): surface adaptive-thinking from the cost map; fix date misparse
supports_adaptive_thinking shipped in the model cost map but was never declared
on ModelInfo nor copied during construction, so get_model_info (and the supports_*
factory) silently dropped it for every provider-prefixed or generalized name; only
a bare base entry resolved. Wire it through ModelInfo like the other capability
flags and backfill the flag onto the genuine Claude 4.6/4.7/4.8 entries across
providers so the data, not code, declares the capability. The anthropic-claude
fallback rule also carries the flag (and now accepts a dotted minor, e.g. 4.6) so
an unmapped future Claude degrades to adaptive thinking without a code change.
Tighten the Claude version parser so an eight-digit date suffix
(claude-opus-4-20250514, the non-adaptive Opus 4.0) is no longer read as minor
4.20250514. The cost map stays authoritative; the version check is only a fallback
for provider-prefixed names (bedrock/invoke routes, -v1-less ids) that resolve to
no mapped entry and so cannot be reached by an exact lookup or the bare-name rule.
https://claude.ai/code/session_01G8Jro8dPLktwnaaSJwVDpo
* fix(anthropic): date-safe adaptive-thinking version fallback, conservative fallback pricing, ruff strict gate
Reconcile adaptive-thinking detection after merging litellm_internal_staging.
Keep the cost-map resolver (_supports_model_capability) as the source of truth and
add a date-safe opus/sonnet/haiku >= 4.6 name version as a fallback for
provider-prefixed ids the cost map cannot resolve (e.g.
bedrock/invoke/us.anthropic.claude-opus-4-6). A two-digit cap on the minor keeps an
eight-digit date suffix from being misread as a minor version, so the dated Claude
4.0 release stays non-adaptive
Price the shipped anthropic-claude fallback rule at the Opus tier so an unknown or
newly released Claude is over-costed rather than billed as free
Drop the module-level global state in fallback_generalizations (PLW0603) in favor of
a small registry object, and switch its annotations plus the new utils helper to
builtin generics (UP006), bringing the ruff strict-rule totals back under ceiling
* refactor(anthropic): drive adaptive-thinking version gate from a declarative rule
Replace the bespoke _claude_version_at_least heuristic with a version-gated fallback_generalizations rule. Unmapped Claude ids now resolve adaptive thinking purely from the cost map: an explicit entry, or the new self-contained anthropic-claude-adaptive-thinking rule that matches opus/sonnet/haiku >= 4.6 (covering 5.x, 6.x and beyond with no code change). New families ship via Price Data Reload instead of a code edit
The rule carries the same Opus-tier pricing as the broad anthropic-claude rule plus supports_adaptive_thinking, and is matched first; the broad rule stays version-neutral, so an unmapped >= 4.6 Claude resolves to full pricing and the adaptive flag from one rule, while a sub-4.6 alias such as claude-opus-4-0 is still priced yet stays non-adaptive. The regex caps the minor at two digits so a dated 4.0 id (...-4-20250514) is never read as a >= 4.6 minor
* refactor(anthropic): dedupe adaptive-thinking rule via declarative extends
The version-gated anthropic-claude-adaptive-thinking rule duplicated the
broad anthropic-claude rule's entire Opus-tier price block because rules do
not merge: first match wins and returns one rule's whole model_info, so the
adaptive rule had to be self-contained.
Add a declarative extends field to fallback_generalizations: a rule names a
parent and inherits its model_info, with its own keys overriding. Inheritance
is resolved once at install time against each rule's raw model_info, so the
adaptive rule now carries only its delta (supports_adaptive_thinking) and
inherits pricing from the broad rule. Runtime matching, provider routing and
gating are unchanged; the broad rule stays anchored and first-match-wins still
holds.
* docs(anthropic): add ignored description key documenting each generalization regex
* fix(anthropic): drop fabricated pricing from the anthropic-claude fallback rule
Per review feedback, the base rule no longer carries input/output/cache costs, and the
adaptive-thinking rule that extends it inherits that no-pricing model_info. Pricing an
unmapped model at a guessed tier reports a confidently-wrong cost without the caller
knowing; dropping it keeps the standard unpriced behavior (zero, not a fabricated
number) so a missing price stays visible. The rules still supply provider routing,
context window, and capability flags, so a brand-new Claude can still be called and its
capabilities (including adaptive thinking for >= 4.6) resolved. Description and tests
updated to match
* fix(ui): widen Y-axis gutter on Usage charts so large token/request labels aren't clipped
The Total Tokens Over Time and Total Requests Over Time AreaCharts on the
Usage page used Tremor's default yAxisWidth (~56 px), which is too narrow
once totals pass the hundred-million mark — leading digits of labels like
"100.00M" / "4500.00M" got clipped against the chart edge. The requests
chart was worse: it formatted with toLocaleString(), so billion-scale
request counts produced "1,000,000,000" (13 chars) and overflowed
immediately.
Fix in two places so neither alone has to carry the whole margin:
- activity_metrics.tsx: add yAxisWidth={80} to both AreaCharts, and
switch the requests chart to the shared valueFormatter so it uses the
same compact k/M/B suffixes as the tokens chart.
- value_formatters.tsx: add a >= 1e9 branch to valueFormatter /
valueFormatterSpend that emits a "B" suffix (4.50B, $4.50B), keeping
every formatted label at most 7 chars.
Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
* Update ui/litellm-dashboard/src/components/UsagePage/utils/value_formatters.tsx
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* docs(readme): add Deploy on AWS/GCP with Terraform section
Adds a quickstart for the two published Terraform modules on the public
registry (BerriAI/litellm/aws and BerriAI/litellm/google). Copy-paste
main.tf for each cloud, the one-time GCP Artifact Registry remote-repo
command, and pointers to the registry pages for the full input surface.
Sits inside the Get Started section, between the gateway/SDK table and
Run in Developer Mode -- where someone scanning the README for "how do I
deploy this" will land.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* docs(readme): add 1-click deploy buttons for AWS + GCP
GCP gets the real 1-click: Open in Cloud Shell badge that clones the repo
and walks through `terraform apply` via the existing DeployStack
tutorial (already shipped at terraform/litellm/gcp/examples/default/
TUTORIAL.md). User just picks a project.
AWS gets a soft 1-click: a Launch in AWS CloudShell badge that opens an
in-browser, already-authenticated shell. User runs four commands
(clone + cd + cp tfvars + terraform apply) once inside. There's no
native AWS deeplink that pre-clones a repo + runs a tutorial -- CFN
"Launch Stack" + CodeBuild would be needed for that, and that's a
separate piece of work.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* docs(readme): move AWS + GCP deploy buttons next to Render button
* docs(readme): unify deploy button sizes and badge styles
* docs(readme): bump deploy button height to 48 to match Render/Railway
* docs(readme): bump AWS/GCP badge height to compensate for SVG padding
* docs(readme): bump AWS/GCP badge height to 72
* docs(readme): bump AWS/GCP badge height to 84
* fix(readme): make deploy buttons same height (48px)
https://claude.ai/code/session_01MxQRMHSDXbqJh74rF86UBc
* docs(readme): flag GCP project ID substitution in image_registry
* docs(readme): equalize deploy button heights and fix Cloud Shell button font
GitHub rewrites an image's height attribute to "height: auto; max-height: Npx", which only caps and never stretches, so each image renders at its intrinsic height. The AWS/GCP shields badges are intrinsically 28px while the Render/Railway buttons are 40px, leaving the row uneven regardless of the height="48" we set. Replace the two shields badges with committed 40px PNGs so all four header buttons render at the same 40px.
Also swap the Cloud Shell button from open-btn.svg to open-btn.png. The SVG renders its label as live text with font-family "Roboto, Sans" and no generic fallback; since neither font exists in GitHub's render environment, the text fell back to a serif (Times New Roman). The PNG bakes in the correct typeface.
* docs(readme): collapse Railway deploy anchor to a single line
The Railway button wrapped its img across indented lines, so the anchor contained leading and trailing whitespace. GitHub underlines link content, rendering that whitespace as a small blue underline beside the button. Put the anchor on one line like the other three buttons so there is no inner whitespace to underline.
* Add Claude Fable 5 cost map entries as a data-only hotfix
Backports only the model map changes from #30064 so deployments on
released litellm versions pick up Fable 5 pricing, context window, and
the adaptive thinking flag through the hosted cost map fetch without
upgrading. Includes the supports_sampling_params flag on the 28
Fable 5 / Opus 4.7 / Opus 4.8 entries (ignored by released code, read
by the gating that ships with the next release) and the matching
one-line schema declaration so the map validation test passes.
https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm
* fix: correct context window tokens for GPT-5 Pro and GPT-5.4 Mini/Nano
Three bugs in model_prices_and_context_window.json:
1. gpt-5-pro and gpt-5-pro-2025-10-06: max_input_tokens and max_tokens
were SWAPPED. GPT-5 Pro has a 400K context window (input) with 128K
max output, but the values were set as max_input=128000,
max_tokens=272000. This caused token limit errors when sending
prompts over 128K tokens to GPT-5 Pro.
2. gpt-5.4-mini and gpt-5.4-mini-2026-03-17: max_input_tokens was
272000, but GPT-5.4 Mini shares the same 1,050,000 token context
window as GPT-5.4. This was inconsistent with the azure/ variants
which already correctly had 1,050,000.
3. gpt-5.4-nano and gpt-5.4-nano-2026-03-17: same issue as Mini,
max_input_tokens was 272000 instead of 1,050,000.
Source: OpenAI model documentation and contextwindows.dev which
aggregates official context window sizes.
Fixes#30928 (partially — the issue incorrectly claims gpt-5/gpt-5-mini
should be 400K; their 272K values are correct per OpenAI docs)
* fix: also correct max_output_tokens for gpt-5-pro (272000→128000)
Per reviewer feedback, max_output_tokens was left at 272000 while
max_tokens was corrected to 128000, causing an internal inconsistency.
Both should be 128000 per OpenAI docs.
* fix(cost): price gpt-image generated output tokens as image tokens (#31147)
The OpenAI Images endpoints (/v1/images/generations, /v1/images/edits) return
usage with no output token breakdown — litellm's `ImageUsage` has no
`output_tokens_details` field — so generated-image OUTPUT tokens were priced at
the text rate (`output_cost_per_token`) instead of the image rate
(`output_cost_per_image_token`). For gpt-image-2 that is $10/1M vs $30/1M, a ~3x
undercount on the dominant cost component (image output is ~74% of spend). This
also affects azure gpt-image, which shares this calculator.
The OpenAI gpt-image cost calculator re-implemented usage handling instead of
reusing `calculate_image_response_cost_from_usage`, the shared helper that
azure_ai/gemini/vertex_ai already use. That helper classifies generated output
tokens as image tokens when the provider does not itemize output, and splits
text/image when it does.
Fix: route the ImageUsage path through `calculate_image_response_cost_from_usage`
(pre-transformed chat Usage objects are still costed directly). Adds a regression
test for the no-breakdown ImageUsage case (gpt-image-2).
* fix(bedrock): route application-inference-profile ARNs to converse (#18258) (#31098)
A bare application-inference-profile ARN passed as bedrock/arn:... fell
through to the invoke route, which cannot derive a provider from the
opaque profile id and raised 'Unknown provider=None'. The converse route
needs no provider, so detect these ARNs in get_bedrock_route and route
them to converse, matching the behavior of the already-documented
bedrock/converse/arn:... workaround.
Explicit invoke/ prefixes still win, and they remain a dead end for these
ARNs by design (no provider derivable). System-defined inference-profile
ARNs that embed a known model, and other opaque ARN types
(provisioned-model, imported-model, custom-model-deployment) that are
frequently invoke-only, are deliberately left on their current routes;
tests guard both boundaries.
* fix(moonshot): stop mutating caller messages on tool_choice='required' (#31060)
_add_tool_choice_required_message appended the "select a tool" prompt to
the caller's messages list in place, so transform_request corrupted the
caller's conversation history and appended a duplicate prompt on every
retry. Build and return a new list instead so the call stays idempotent.
Adds a regression test asserting the input messages list is unchanged
across repeated transform_request calls.
Co-authored-by: Wassbdr <wassim.badraoui07@gmail.com>
* fix(transcription): accept fractional usage.seconds in diarized_json responses (#30996)
gpt-4o-transcribe and compatible ASR backends return a diarized_json
response with usage={"type": "duration", "seconds": <float>}, e.g. 295.8.
TranscriptionUsageDurationObject typed seconds as int, so parsing the
response raised a pydantic ValidationError (int_from_float). That error
surfaces as an APIConnectionError which the router treats as retryable, so
it keeps re-calling the upstream (200 every time) until the upstream
rate-limits and returns 429 to the caller.
OpenAI specs this field as a float (see openai SDK UsageDuration.seconds),
so widen seconds to float. With the parse succeeding there is no exception
left to retry, which removes the loop.
Co-authored-by: Neimar Avila <19142978+neimaravila@users.noreply.github.com>
* fix(deepseek): drop non-function tools before chat completions call (#30910)
* fix(deepseek): drop non-function tools before chat completions call
DeepSeek's /chat/completions only accepts tools of type "function".
Requests bridged from /v1/responses can carry responses-API-native tool
types, for example a Codex CLI tool typed "namespace", which DeepSeek
rejects with "unknown variant 'namespace', expected 'function'" so the
whole request fails (issue #30722).
Filter unsupported tool types in the DeepSeek request transform so the
function tools still go through; when nothing callable remains, also drop
the now-dangling tool_choice and parallel_tool_calls
Fixes#30722
* test(deepseek): cover async tool filtering and document tool_choice assumption
Add an async_transform_request regression test so the sync and async tool
filtering paths cannot silently diverge, and document in _drop_unsupported_tools
that only non-function tools are dropped, so a function-named tool_choice always
references a surviving tool
* feat(catalog): add zai/glm-5.1, zai/glm-4.7-flash, openrouter/z-ai/glm-5.1 (#29840)
* feat(ui): surface team budget on key overview when key has no own budget (#30801)
* feat(ui): surface team budget on key overview when key has no own budget
* fix(ui): replace IIFE with derived variable and use find() for team budget display
* fix(anthropic): emit replayable streaming thinking blocks (#31022)
* feat(proxy): read cold-storage prompts back in the logs detail view (#30364)
* feat(proxy): read cold-storage prompts back in the logs detail view
When a deployment offloads prompts and responses to cold storage instead of
Postgres, the spend-log row holds only "{}" placeholders plus a
metadata.cold_storage_object_key pointer, so the UI logs detail drawer showed
nothing. The detail endpoint only read the placeholder columns and never
fetched the object back.
Resolve the payload per row based on actual content, not a config flag: if
Postgres has content, return it; otherwise read the exact stored object key and
fetch from the configured cold storage backend through ColdStorageHandler.
Reading the persisted key is a single GET. The key embeds a microsecond
timestamp that cannot be reconstructed from the millisecond-precision startTime
column, and listing the day's prefix to match on request_id would be too
expensive for this per-open path.
Also teach the detail drawer's pretty-view parser to accept a bare messages
array. The cold storage payload carries the prompt as a top-level messages list
with no proxy_server_request, so without this the output rendered while the
input stayed blank.
ColdStorageHandler gains an optional injected logger so the resolver can be unit
tested without monkeypatching. Postgres-stored prompts are unaffected: the fast
path returns the existing columns and the request-body object still renders the
same way.
* Update litellm/proxy/spend_tracking/spend_management_endpoints.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* test(proxy): cover ColdStorageHandler resolution paths and cold-storage fetch failure
Add unit tests for ColdStorageHandler (injected logger, graceful None when no
logger is configured, and resolution of a configured logger from the callback
registry) and a regression test asserting a cold storage backend exception
degrades to the Postgres values instead of surfacing a 500.
---------
Co-authored-by: Bytechoreographer <Bytechoreographer@users.noreply.github.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix(mavvrik): advance metricsMarker after upload; fix scheduler startup (#31068)
* fix(mavvrik): advance metricsMarker after upload + fix scheduler startup
Two bugs fixed:
1. deliver() never called PATCH /metrics/agent/ai/{connectionId} after a
successful GCS upload, so metricsMarker stayed at 0 and every daily run
re-exported the same dates in an infinite catch-up loop.
Fix: add _update_metrics_marker(date_epoch) called at the end of deliver()
after _upload_to_gcs() succeeds. A 4xx warns but does not raise (the GCS
file is already committed). A 410 raises consistent with the rest of the
destination.
2. init_mavvrik_focus_background_job runs at proxy startup before any LLM call
has triggered lazy instantiation of MavvrikFocusLogger, so it found no
logger instance and silently skipped registering the daily export job.
Fix: if no instance is found but "mavvrik" is in litellm.callbacks, call
_init_custom_logger_compatible_class to force instantiation before
the APScheduler job is registered.
* fix(mavvrik): catch up from earliest window when metricsMarker=0
When the connector is freshly registered, metricsMarker=0 parses to None.
The catch-up block was guarded by `if last_ingested and ...` which skipped
it entirely for None, so only yesterday was exported instead of the full
_MAX_CATCHUP_DAYS window.
Fix: treat None as being _MAX_CATCHUP_DAYS behind (start from earliest_catchup).
The existing > 7 day warning only fires for non-None markers that are old.
* fix(mavvrik): use now as end_time for yesterday's export window
LiteLLM_DailyUserSpend rows for a given date get their updated_at
bumped by the spend flush job throughout the next morning. The core
database query filters on updated_at, so capping end_time at midnight
(yesterday + 1 day) missed any spend rows flushed after midnight.
Fix: pass now (cron fire time) as end_time for the daily "yesterday"
window so all fully-settled rows are captured regardless of when the
flush job ran.
Verified: claude-3-5-sonnet BilledCost went from 0.0 to ~$2.40 per
row in the exported FOCUS CSV.
* fix(mavvrik): also use now as end_time for catch-up windows
* fix(mavvrik_focus): pass required args to _init_custom_logger_compatible_class
Calling it with only logging_integration raised TypeError at proxy startup
because internal_usage_cache and llm_router have no defaults. Also fix test
name to reflect the actual status code (5xx not 4xx) used in the mock.
* ci: retrigger CI run
* feat: pass through optional `instruction` field in the rerank API (vLLM/Qwen3-Reranker) (#30757)
* Add optional `instruction` passthrough to the rerank API
vLLM's /v1/rerank and /v1/score accept an optional top-level `instruction`
field (folded into the model's chat_template_kwargs and consumed by the
chat template — e.g. Qwen3-Reranker). LiteLLM's managed rerank route silently
dropped it: RerankRequest / OptionalRerankParams had no such field, so the
outgoing body was rebuilt without it.
Thread an opt-in `instruction: Optional[str]` through rerank()/arerank(),
get_optional_rerank_params, and the hosted_vllm transformation into the
request body, only when non-None. When callers omit it, model_dump(exclude_none)
drops the field and the outgoing request is byte-for-byte unchanged — fully
backward-compatible. (DeepInfra already forwards `instruction` via
non_default_params; this formalizes the field in the shared types.)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Address review: thread `instruction` as a typed param + cover rerank_utils
Per PR review (greptile P2 + codecov):
- Make `instruction` a typed, named argument on the rerank provider interface
instead of recovering it from the opaque `non_default_params` blob. Adds
`instruction: Optional[str] = None` to `BaseRerankConfig.map_cohere_rerank_params`
and every provider override, and forwards it explicitly from
`get_optional_rerank_params`. hosted_vllm now reads the named param directly.
It is still also surfaced in `non_default_params` so providers that read it
there (e.g. DeepInfra) keep working now that `rerank()` consumes `instruction`
as a named param rather than leaving it in **kwargs.
- Add get_optional_rerank_params unit tests (present + absent) to cover the
previously-uncovered threading line flagged by codecov.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix: scan rerank `instruction` through request guardrails
The rerank guardrail translation (CohereRerankHandler.process_input_messages)
only scanned `query`, so the newly added `instruction` field reached the
backend model unscanned. Since instruction-aware rerankers (hosted vLLM /
Qwen3-Reranker) fold `instruction` into the prompt, an authenticated caller
could place content there to bypass configured rerank request guardrails.
Generalize the handler to scan every user-controlled text field (`query` and
`instruction`) in one apply_guardrail call and write each sanitized value back
by index. Query-only requests are unchanged (single-element list at index 0);
non-string fields are left untouched. Adds tests covering instruction
scanning, PII masking write-back, and the non-string case.
Addresses the Veria AI security review on PR #30757.
* test: narrow Optional results before len() to satisfy basedpyright budget
The lint gate (basedpyright delta-vs-base budget) flagged one new
reportArgumentType: len(result.results) where results is
List[RerankResponseResult] | None. Assert results is not None first to
narrow the type before len()/indexing.
* fix: read rerank `instruction` from kwargs to satisfy basedpyright budget
The basedpyright delta-vs-base gate flagged one new reportArgumentType: the
Router forwards rerank calls via an untyped `**kwargs` unpack
(`litellm.arerank(**{**data, **kwargs})`), and declaring `instruction` as a
typed named param on the public `rerank`/`arerank` entrypoints made pyright
check that key against `str | None`, adding an error at router.py with no real
safety gain. Read `instruction` from kwargs in `rerank` instead.
It remains fully typed where it matters - threaded as a typed argument through
`get_optional_rerank_params` and each provider's `map_cohere_rerank_params`
(the original Greptile P2 ask). Whole-repo reportArgumentType is back to the
base count (net 0); rerank hosted_vllm + cohere guardrail suites pass; ruff clean.
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(github_copilot): synthesize empty choices at the provider seam (#30929)
Newer Copilot Claude models (opus-4.7, opus-4.8) return responses with
choices=[], either carrying Anthropic-native content blocks or, for the
max_tokens=1 probe Claude Code sends, no content at all. github_copilot
is dispatched through the OpenAI SDK handler, which calls
convert_to_model_response_object directly and never invokes
GithubCopilotConfig.transform_response, so the empty-choices guard there
surfaced as a 500
Instead of synthesizing choices inside the shared
convert_to_model_response_object (which would silently turn empty choices
into a fabricated success for every provider), add a no-op
transform_parsed_response_dict hook on BaseConfig. GithubCopilotConfig
overrides it to synthesize choices from Anthropic-native content, reusing
its existing parsing, and the OpenAI SDK handler routes its parsed
response through the hook before generic conversion. The core utility
keeps treating empty choices as an error for all other providers
Fixes: https://github.com/BerriAI/litellm/issues/30927
Signed-off-by: David J. M. Karlsen <david@davidkarlsen.com>
* fix(router): stop fallback lookups from mutating the router fallbacks config (#30624)
* fix: correct amazon.titan-embed-text-v2 input price to $0.02/1M tokens (#29693)
* fix: correct amazon.titan-embed-text-v2 input price to $0.02/1M tokens
* test: scope local cost map env var with monkeypatch to avoid test pollution
* fix(sensitive_data_masker): fully mask secrets at or below the reveal threshold (#30764)
* fix(sensitive_data_masker): fully mask secrets at or below the reveal threshold
_mask_value did partial reveal by showing the first visible_prefix and last
visible_suffix characters, but for a value whose length was at or below
visible_prefix + visible_suffix (8 by default) it returned the value verbatim.
A value of exactly 8 chars fell through the length guard and computed
masked_length == 0, reconstructing the original string with no mask characters;
anything shorter hit the early return. Either way short credentials were emitted
in plaintext.
mask_dict routes real secrets through this path, so an 8-char-or-shorter redis
password, api key, or token could be written to logs and the UI unmasked. The
sibling helper mask_sensitive_keys already guards this case; _mask_value now does
the same by fully masking any value at or below the threshold.
* fix(sensitive_data_masker): add mask_short_values opt-out for truncation callers
Fully masking short values is the right default for secret masking, but
CooldownCache reuses the masker purely to truncate exception messages to the
first 50 characters, and it relies on short messages being returned readable.
Masking those blanked out short exception text and broke its tests.
Add a mask_short_values flag (default True, secure) and have CooldownCache pass
False so it keeps the truncation behavior, while every secret-masking caller
still gets short values fully masked.
* fix(mcp_debug): opt out of short-value masking to keep diagnostic token preview
MCPDebug uses the masker to preview auth tokens in debug headers and documents
that values of 10 chars or fewer are shown unchanged so token types stay
distinguishable. Pass mask_short_values=False so that diagnostic behavior is
preserved while secret maskers keep masking short values.
* fix(mcp_debug): mask short auth values in debug headers instead of echoing them
Earlier this masker opted out of short-value masking to keep a token preview, but
that echoes short authorization and token values verbatim in debug response
headers, which is the same leak this change is meant to close. Auth material
should never be emitted in full, so mask short values here too; the first/last
character preview still applies to longer tokens. Only CooldownCache keeps the
opt-out, since it truncates exception text rather than masking secrets.
* test(mcp_debug): assert masked short value preserves length
* refactor(fireworks_ai): remove deprecated audio transcriptions endpoint (#30917)
Fireworks AI deprecated audio inference on 2026-06-10
(https://docs.fireworks.ai/updates/changelog#audio-inference-and-image-generation-deprecation).
Live API testing confirms the endpoint is already non-functional: a valid
Fireworks API key receives HTTP 401 "Unauthorized" from
api.fireworks.ai/inference/v1/audio/transcriptions for every request,
regardless of payload. The audio-prod.api.fireworks.ai host referenced in
the test suite returns 401 for every path; the entire host is decommissioned.
Remove the dead FireworksAIAudioTranscriptionConfig class and every
reference to it across the codebase:
- Delete litellm/llms/fireworks_ai/audio_transcription/ directory (17-line
config class that inherited from OpenAIWhisperAudioTranscriptionConfig)
- Remove the Fireworks branch from
ProviderConfigManager.get_provider_audio_transcription_config() in
litellm/utils.py; update the stale comment in
get_optional_params_transcription that referenced fireworks ai
- Remove the FireworksAIAudioTranscriptionConfig entries from
LLM_CONFIG_NAMES and _LLM_CONFIGS_IMPORT_MAP in
litellm/_lazy_imports_registry.py
- Remove the TYPE_CHECKING re-export in litellm/__init__.py
- Remove the transcription branch in the fireworks_ai case of
get_supported_openai_params() in
litellm/litellm_core_utils/get_supported_openai_params.py
- Remove the whisper-v3 and whisper-v3-turbo entries from
model_prices_and_context_window.json and
litellm/model_prices_and_context_window_backup.json (both had
mode: audio_transcription and zero-cost pricing)
- Remove the TestFireworksAIAudioTranscription test class and its
imports from tests/llm_translation/test_fireworks_ai_translation.py
No other provider is affected. The openai_compatible_providers list,
FireworksAIMixin, and the OpenAI Whisper transcription handler all stay
because they are shared with other Fireworks endpoints and other
providers. The provider_endpoints_support.json registry already had
audio_transcriptions set to false for fireworks_ai.
* feat: add darkbloom provider (#30876)
* feat: add darkbloom provider
* fix: document darkbloom provider endpoints
* fix: address darkbloom review feedback
* fix: update darkbloom tool metadata
* fix: fail fast for non-Postgres database URLs (#30883)
* fix(proxy): fail fast on non-PostgreSQL DATABASE_URL instead of hanging on startup
LiteLLM's Prisma datasource is pinned to provider = 'postgresql', so a sqlite:// or mysql:// DATABASE_URL can never connect.
Today that surfaces as an opaque startup stall where the port never binds, and a separate 'DB not connected' 500 on /key/generate when no DATABASE_URL is set at all leaves operators guessing what to configure.
Validate the DATABASE_URL / DIRECT_URL scheme in run_server before any Prisma call and exit with an actionable message naming the unsupported scheme.
Also reword CommonProxyErrors.db_not_connected_error to tell the operator to set DATABASE_URL to a postgresql:// connection string.
Add regression tests covering postgres acceptance and sqlite/mysql/mssql rejection.
* fix: resolve CI failures and proxy DB URL typing issue
* fix(proxy): fail fast on non-PostgreSQL DATABASE_URLs with clear startup errors instead of hanging
* Validate DIRECT_URL alongside DATABASE_URL startup guards
* fix(bedrock): surface modeled HTTP status for mid-stream error events so 5xx is retryable (#24608) (#30946)
* fix(bedrock): surface modeled HTTP status for mid-stream error events (#24608)
* test(bedrock): mid-stream server errors trigger streaming fallback (#24608)
* style(bedrock): black-format stream-error helper (#24608)
* fix(mcp): re-land native tool preservation with typed annotations (#30645)
* fix(mcp): preserve native tools in semantic filter hook with typed annotations
* fix(mcp): tighten _is_mcp_tool Chat Completions shape check
* fix(sambanova): return embeddings supported params instead of dropping them (#30937)
* fix(router): send fallback metadata when streaming (#30914)
When a streaming request triggers a fallback, there was previously no way to
know it happened. This commit addresses this in a few ways:
1. The response now correctly populates the fallback headers
(`x-litellm-attempted-fallbacks`) so callers know a fallback happened.
2. The correct model ID is passed in the streaming chunks.
3. A streaming chunk with the fallback error can be optionally sent back
to the client (opt-in) by passing `include_fallback_errors: true` in
the request.
The format of the fallback errors while streaming is intentionally OpenAI
compatible to not break existing libraries that parse these events. It was
tested with Vercel's AI SDK (ai-sdk.dev). It is also opt-in, so it is not
delieved unexpectedly to callers by default.
* fix(mistral): drop output-only reasoning fields from input messages (#30884)
LiteLLM attaches reasoning_content and thinking_blocks to assistant
responses. Replaying those assistant turns verbatim forwarded the fields
back to Mistral, whose input schema forbids unknown keys, so the whole
request failed with a 422 extra_forbidden and reasoning models became
unusable across multiple turns.
Strip both fields from assistant messages before the request is built, in
a spot that runs ahead of the image/file branch so it applies on every
path. Fixes#30835
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(perplexity): bill search queries at the per-request price, not 1/1000 of it (#30652)
* fix(perplexity): bill search queries at the per-request price, not 1/1000
The fallback cost calculator divided search_context_cost_per_query by
1000, but that field stores the per-request price in USD: sonar is
{low: 0.005, medium: 0.008, high: 0.012}, matching Perplexity's published
$5/$8/$12 per 1,000 requests expressed per request. The gemini cost
calculator reads the same field per request with no division (its
docstring calls it "the per-request cost").
The division understated search cost by 1000x on every Perplexity call
that falls back to manual calculation (i.e. when the API does not return
a pre-computed usage.cost). Use the value directly.
Update the tests that had encoded the /1000 factor in their expectations,
and drop an unused import flagged by ruff in the touched test file.
* test(perplexity): update integration test search-cost expectations to per-request
The integration tests still encoded the old /1000 search-cost factor, so
they failed once the fallback calculator was corrected to bill
search_context_cost_per_query per request. Update the four expected-cost
computations (and the high-volume dollar-value comments) to match.
* test(perplexity): drop unused mock imports flagged by ruff
* fix: include model_access_groups when expanding all-team-models in get_team_models (#30622)
* fix(fireworks_ai): return None for transcription in get_supported_openai_params
Fireworks AI deprecated audio inference on 2026-06-10; the endpoint is
decommissioned. Without an explicit transcription branch, requests with
request_type='transcription' fell through to the else and returned
FireworksAIConfig chat-completion params. Return None instead to signal
the provider does not support transcription.
* fix(proxy): gate include_fallback_errors behind expose_fallback_errors_to_caller setting
Without an operator gate, any authenticated caller could set include_fallback_errors=True,
trigger a fallback, and read raw upstream exception messages from the
x-litellm-fallback-errors header and the litellm-fallback-metadata SSE event.
Strip include_fallback_errors from request data in common_processing_pre_call_logic
when expose_fallback_errors_to_caller is not set, so the router never builds the
error list. Also gate _should_include_fallback_errors on the same setting as a
secondary check for the streaming SSE injection path.
* test(proxy): opt in to expose_fallback_errors_to_caller in streaming SSE test
The operator gate added in e7ff3e1 means include_fallback_errors is only
honoured when general_settings.expose_fallback_errors_to_caller is True.
Set that flag via monkeypatch in the test that exercises the emit path.
* test(prompt_templates): make test_convert_url hermetic instead of hitting picsum.photos
test_convert_url called convert_url_to_base64 against a live picsum.photos
URL and asserted nothing, so it added no real signal and broke CI whenever
the host was unreachable (it was returning 522 and blocking this branch).
Replace the live call with a mocked HTTP client and assert the produced
base64 data URL, so the conversion path is exercised deterministically with
no network dependency. This suite runs under VCR, which is why a transport
level mock (respx) does not reliably intercept; mocking the client object
itself is robust regardless.
* fix(interactions): drop role from Interaction response to match Google spec
Google removed the output-only role field from the Interaction schema (it
now lives only on Turn), so the live OpenAPI compliance canary started
failing with 'role' not in spec. Reconcile our generated types by removing
role from Interaction, CreateModelInteractionParams, CreateAgentInteractionParams
and from the LiteLLM InteractionsAPIResponse/InteractionsAPIStreamingResponse,
stop stamping role=model in the responses-to-interactions transformation, and
update the compliance and integration tests accordingly. Turn.role is kept
since the spec still defines it.
* fix: align all-team-models sentinel access
* fix(router): forward include_fallback_errors through multi-hop fallbacks
run_async_fallback received include_fallback_errors as an explicit named
parameter, so it was bound out of **kwargs and never reached the nested
async_function_with_fallbacks call. Multi-hop fallback chains (a fallback
group that itself fails over) therefore stopped collecting fallback errors
beyond the first hop when a caller opted in. Re-inject the flag into kwargs
before the nested call so inner hops keep accumulating errors, which
add_fallback_headers_to_response already merges across levels.
* fix(router): stop fallback lookups from mutating the router fallbacks config
get_fallback_model_group resolved a bare-string fallback by popping it out
of the fallbacks list it was handed. That list is frequently the live
router.fallbacks config, so a single lookup permanently removed the entry and
the configured fallback stopped applying to later requests until restart. The
pop also ran inside enumerate(), shifting indices and skipping an adjacent
string fallback. Read the item instead of popping it, and add a regression
test that fails on the old mutating behavior
---------
Co-authored-by: Srivatsa Kamballa <skamb10@uic.edu>
Co-authored-by: Ahmad Shahzad <107808273+shzdehmd@users.noreply.github.com>
Co-authored-by: Jeremy Chapeau <113923302+jychp@users.noreply.github.com>
Co-authored-by: KRISH SONI <67964054+krishvsoni@users.noreply.github.com>
Co-authored-by: Kent <72616338+kingdoooo@users.noreply.github.com>
Co-authored-by: Ayush Shekhar <106994833+ayushh0110@users.noreply.github.com>
Co-authored-by: dav nguyxn <hoangson091104@gmail.com>
Co-authored-by: Tal Marian <tal.marian@island.io>
Co-authored-by: Hemant K <51333870+hemant1026@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Yash Raj Pandey <55940078+devYRPauli@users.noreply.github.com>
Co-authored-by: Zang Peiyu <166481866+factnn@users.noreply.github.com>
Co-authored-by: Sameer Kankute <sameer@berri.ai>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(sambanova): update pricing, deprecate retired models, and add missing models (#30016)
* feat(bedrock): add amazon.titan-embed-g1-text-02 embedding model support
- Add model to provider routing allowlist in embedding.py
- Add request transformation using AmazonTitanG1Config
- Add response transformation using AmazonTitanG1Config
- Add pricing metadata to model_prices_and_context_window.json
- Add unit tests for embedding and model info
Fixes missing cost tracking reported in #29786
Related to VANDRANKI/litellm PR #29790
* style: fix syntax error, trailing whitespace and missing newline
* style: apply black formatting to embedding.py
* style: apply black formatting to test_bedrock_embedding.py
* fix(sambanova): update pricing, fix context windows, add deprecation dates, and add missing models
* fix(sambanova): sync model_prices_and_context_window_backup.json with primary
* fix(sambanova): fix indentation on Meta-Llama-3.2-1B-Instruct deprecation_date
* fix(bedrock): add amazon.titan-embed-g1-text-02 to unmapped model error message
* style: apply black formatting to embedding.py
* fix(sambanova): correct indentation on DeepSeek-V3.2 entry
* fix(sambanova): replace gemma-3-12b-it with gemma-4-31B-it (verified pricing)
* fix(utils): preserve arbitrary above-threshold tiered pricing keys in get_model_info (#30880)
* fix(utils): preserve arbitrary above-threshold tiered pricing keys in get_model_info
get_model_info rebuilt ModelInfo by copying a fixed allow-list of
input/output_cost_per_token_above_<N>_tokens keys (128k/200k/272k/512k), so any other
threshold a user registered was dropped before reaching _get_token_base_cost, which already
reads an arbitrary threshold out of the key name. Custom tiers such as above_500k_tokens were
silently ignored and billing fell back to the base per-token rate. Carry over any
_above_<N>_tokens cost key present on the source cost-map entry that the fixed fields miss
Fixes#30344
* test(cost): keep suite hermetic by popping the temp tiered-pricing model
Wrap the regression body in try/finally so litellm.model_cost no longer
leaks the litellm-test-non-standard-tier entry into later tests that
iterate or reset the global cost map. Addresses Greptile review thread.
* fix: resolve UP045 lint violations (Optional[X] -> X | None)
Convert Optional[X] type annotations to X | None syntax across rerank
transformations, spend tracking, and other modules to satisfy ruff strict gate.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: run black formatting on UP045-fixed files
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: remove unused Optional imports after UP045 migration
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: black format cold_storage_handler.py
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(ci): correct OSS staging branch name in guard-main-branch errors
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix: strip trailing zeros from M/B spend formatter
* fix: address focus and streaming edge cases
* feat: add LAR-1 semantic routing strategy
Optional router strategy that picks a deployment tier from
request_kwargs.metadata.lar1 (confidence, evidence, time). Deployments
are tagged with model_info.type (cloud-smart, cloud-fast, local, deep).
Thresholds are configurable via routing_strategy_args. Includes 30 unit
tests and an Ollama example config.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(mavvrik): advance metricsMarker on empty-content deliver
When deliver() receives empty content (no spend data for a date), it now
registers with Mavvrik and PATCHes the metricsMarker before returning
instead of short-circuiting. Dates with zero spend no longer stall marker
advancement, preventing unnecessary catch-up API calls on subsequent runs.
* style: black format mavvrik_destination
* fix: handle empty mavvrik exports and lar1 reset
* test: add regression test for _reset_custom_routing_strategy
* fix(test): mock async destination.deliver in mavvrik export window test
* style: ruff format spend_management_endpoints after merge
* fix(router): apply LAR-1 strategy atomically so invalid thresholds don't leave partial state
apply_lar1_routing_strategy set router.routing_strategy to "lar1" before
constructing LAR1RoutingStrategy, whose __init__ validates thresholds via
_normalize_thresholds and raises on a misconfigured (out-of-order or
out-of-range) set. On a live update_settings call with bad thresholds the
router was left advertising routing_strategy="lar1" with no custom selector
bound, while the previous strategy's selectors stayed registered.
Build (and validate) the strategy before mutating any router state, so a
threshold error leaves the router exactly as it was. Add a regression test
that asserts a failed switch keeps the prior strategy intact.
---------
Signed-off-by: David J. M. Karlsen <david@davidkarlsen.com>
Co-authored-by: Bytechoreographer <Bytechoreographer@users.noreply.github.com>
Co-authored-by: Claude Opus 4 (1M context) <noreply@anthropic.com>
Co-authored-by: Rick <26716961+Bytechoreographer@users.noreply.github.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: shin-berri <shin-laptop@berri.ai>
Co-authored-by: yuneng-jiang <yuneng@berri.ai>
Co-authored-by: Yassin Kortam <yassin@berri.ai>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Co-authored-by: Krrish Dholakia <krrish+github@berri.ai>
Co-authored-by: xbrxr03 <abrarhabib03@gmail.com>
Co-authored-by: hayden <sktpghks138@gmail.com>
Co-authored-by: Kent <72616338+kingdoooo@users.noreply.github.com>
Co-authored-by: Wassim Badraoui <98709649+Wassbdr@users.noreply.github.com>
Co-authored-by: Wassbdr <wassim.badraoui07@gmail.com>
Co-authored-by: Neimar Avila <neimar.avila@gmail.com>
Co-authored-by: Neimar Avila <19142978+neimaravila@users.noreply.github.com>
Co-authored-by: Jerry-Scintilla <jerrycaocao@126.com>
Co-authored-by: AlexBGoode <me.at.forum@gmail.com>
Co-authored-by: Carsten Boloz <cdboloz1@gmail.com>
Co-authored-by: jesco <team@srswti.com>
Co-authored-by: Praveen Ghuge <pghuge@digitalex.io>
Co-authored-by: Jim Smith <j.h.smith@ieee.org>
Co-authored-by: David J. M. Karlsen <david@davidkarlsen.com>
Co-authored-by: Vedant Agarwal <43557509+Vedant-Agarwal@users.noreply.github.com>
Co-authored-by: Srivatsa Kamballa <skamb10@uic.edu>
Co-authored-by: Ahmad Shahzad <107808273+shzdehmd@users.noreply.github.com>
Co-authored-by: Jeremy Chapeau <113923302+jychp@users.noreply.github.com>
Co-authored-by: KRISH SONI <67964054+krishvsoni@users.noreply.github.com>
Co-authored-by: Ayush Shekhar <106994833+ayushh0110@users.noreply.github.com>
Co-authored-by: dav nguyxn <hoangson091104@gmail.com>
Co-authored-by: Tal Marian <tal.marian@island.io>
Co-authored-by: Hemant K <51333870+hemant1026@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Yash Raj Pandey <55940078+devYRPauli@users.noreply.github.com>
Co-authored-by: Zang Peiyu <166481866+factnn@users.noreply.github.com>
Co-authored-by: bhumikadangayach <139267865+bhumikadangayach@users.noreply.github.com>
Co-authored-by: Ewertonslv <ewertoncom297@gmail.com>
Co-authored-by: carlsonchik <carlsonchik@users.noreply.github.com>
