Gate the reasoning_effort translation on the cost-map flag or the model name containing
claude, so unmapped Claude serving endpoints keep translating. Flag the newer Claude
entries that were missing it. Expose supports_anthropic_thinking_payload as a public
helper next to the other supports_* wrappers instead of importing the private factory.
Drop the adaptive-only guard, since the adaptive flags only ever match Claude ids, and
add regression tests for an unmapped Claude endpoint and an adaptive Claude model
The Databricks chat transformation only parsed reasoning out of FMAPI-style
reasoning content blocks, so external models behind Databricks AI Gateway that
return the OpenAI-style top-level reasoning_content string lost it, both in the
final message and in every streamed delta. Fall back to the shared OpenAI
reasoning helper when no reasoning block exists, and keep the delta's own
reasoning_content when streaming.
Databricks Model Serving validates assistant messages with additionalProperties=false, so replaying
a thinking turn translated by the Anthropic Messages adapter 400s with
'messages.N.thinking_blocks: Extra inputs are not permitted'. Drop litellm's internal fields in
DatabricksConfig._transform_messages via a shared common_utils helper.
Resolves LIT-6762
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The 20% promotion that runs to 2027-01-31 covers every gemini model, not
just the 2.5 pair, so a constant naming two of them implied the other four
were exempt. Six covered entries live in the registry: two store the
discounted rate and four store list, which is a pre-existing overcharge
this branch does not touch, since it only adds cache fields and derives
them from each entry's own input rate. Name both groups for what they
store, pin the expiry, and tighten the tolerance to 2e-4.
The two gemini 2.5 entries price a factor of 1.25 under the published DBU
table because the published figures exclude a 20% promotion that runs to
2027-01-31. The previous constant name and test called them an older vintage
awaiting a refresh, which would have led a future reader to scale them up and
overcharge. Pin the discount and the cache relationship instead.
databricks-claude-fable-5 was the only fable-5 entry in the registry
declaring supports_vision false, and the only one of the five new
entries to do so.
Only the five new models were pinned against the published DBU table,
so the 26 cache literals added to pre-existing entries were checked by
nothing independent. Extend the table to all 33 entries carrying cache
rates and assert both cache fields against it for the 31 that take the
published rates, leaving the two older-vintage gemini-2-5 entries to
their existing guard.
Also widen the cache-declaration guard to both cache fields, and
replace the single-model equals-input assertion with one that covers
all 14 entries publishing no cache rates.
Cache rates were derived as ratios of the dollar input rate (1.25x write,
0.1x read) while input and output derive from the published DBU table
times $0.070. Databricks publishes cache write and cache read DBU per
model, and those are not exact multiples of the input DBU, so the two
rules disagreed by up to 0.1 percent.
Rewrites 43 cache literals across 31 entries to published_cache_DBU x
$0.070. Skips databricks-gemini-2-5-pro and databricks-gemini-2-5-flash,
whose input and output rates predate the current table by a 1.25x
increase; their cache rates stay tied to their own input rate so each
entry remains internally consistent.
Replaces the ratio assertions with a test pinning the absolute published
DBU figures for the five new models, and adds a test pinning the
older-vintage exception. Corrects the metadata note on the five new
entries, which claimed the reference-only *_dbu_cost_per_token fields
drive cost calculation.
The shared cost calculator treats a missing cache rate as free, so routing
Databricks through it billed cached tokens at zero on the 14 entries that
publish no cache pricing. On a 10,000 token prompt with 8,000 cache reads
that is $0.0010000 against the correct $0.0050001, a fivefold undercharge.
Those entries now declare cache rates equal to their input rate, which is
what a model with no caching discount should charge, and a test pins every
priced Databricks entry to declaring cache rates so no future entry can
regress into it.
Also repoints the provider-neutral generalization test off an id the new
Opus 5 entry now shadows, adds backup-to-main parity tests for the five new
entries, pins that Databricks Claude is never auto-injected with cache
control despite reporting caching support, and trims the Sonnet 5 pricing
note, which is served on an unauthenticated route.
The introductory DBU rates run through 2026-08-31 and pricing carries no
expiry date, so a static introductory entry would undercharge by a third
from September 1 and let spend outrun enforced budgets. Ship the standard
rates, which match Sonnet 4.5 and 4.6, and keep the introductory numbers
in the entry notes.
Also give the new cost calculator tests full type annotations.
Databricks cost calculation multiplied every prompt token by the input rate, so
a cache read cost the same as an uncached token. Route it through
generic_cost_per_token, which already understands cache reads and cache writes,
and add the cache rates the registry was missing.
Adds Claude Opus 4.7, Opus 4.8, Opus 5, Sonnet 5 and Fable 5 on Databricks.
* 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
chunk_parser built ModelResponseStream without passing usage, so the
cache_read_input_tokens and cache_creation_input_tokens that Databricks
returns for Anthropic models never reached the cost calculator. Every
streamed request was billed at the full input rate even when served
from cache.
ModelResponseStream already coerces a usage dict into Usage, which maps
those keys into prompt_tokens_details, so passing the chunk's usage
through is sufficient.
Addresses Greptile P2 feedback: reject an adaptive thinking payload for non-Claude Databricks models instead of silently emitting a shape the Gemini endpoint can't parse, and scope the local-cost-map fixture to the tests that need it rather than autouse.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(databricks): split parallel tool calls so each tool message follows tool_calls
Databricks OpenAI-compatible serving (e.g. GPT models) 400s with "messages with
role 'tool' must be a response to a preceeding message with 'tool_calls'" when an
assistant turn makes parallel tool calls. LiteLLM faithfully sends one assistant
message holding all tool_calls followed by one 'tool' message per result, so every
result after the first is preceded by another 'tool' message rather than the
assistant tool_calls message, which Databricks rejects.
Re-emit each result immediately after an assistant message that carries only its
matching tool_call, turning assistant(tool_calls=[A, B]), tool(A), tool(B) into
assistant(tool_calls=[A]), tool(A), assistant(tool_calls=[B]), tool(B). The
rewrite is a no-op when the turn is already valid (single call), the group is
incomplete, or ids don't line up, so no tool call is ever dropped. Scoped to
non-Claude models, matching the existing OpenAI-shaped transformation path.
* style(databricks): use builtin list generics in parallel tool-call split
Switch the List[...] annotations introduced by _split_parallel_tool_calls
to lowercase list[...] so the UP006 strict-rule budget stays within its
ceiling.
* fix(vertex): stream Model Garden Gemma/Qwen responses correctly through /v1/messages
* test(vertex): cover _CombinedChunkSplitter defensive branches
* test(databricks): rename test file to avoid duplicate basename collision
* fix(databricks,anthropic): defensive token defaults; document single-mode splitter
Address greptile P2 concerns:
- databricks: default usage token fields to 0 when constructing
ChatCompletionUsageBlock from a partially populated usage block — matches
the defensive pattern used in ollama/vertex_ai/cohere/bedrock.
- _CombinedChunkSplitter: clarify in the docstring that an instance is
single-mode (sync or async, not both), since the two iteration paths hold
independent upstream iterator references.
Co-authored-by: Claude <claude@anthropic.com>
---------
Co-authored-by: Steven Kessler <9701252+stvnksslr@users.noreply.github.com>
Co-authored-by: Claude <claude@anthropic.com>
- Use custom_endpoint=False so Databricks SDK auth fallback works
(custom_endpoint=True was blocking it). The api_base returned by
databricks_validate_environment is discarded since get_complete_url
builds the URL separately.
- Remove unused verbose_logger import
- Remove unused json import in tests
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Databricks supports the Responses API natively for GPT models, but litellm
was falling back to the completion transformation handler which converts
responses requests to chat completion calls, losing response schema enforcement.
This adds DatabricksResponsesAPIConfig that passes responses API requests
directly to Databricks' /responses endpoint for GPT models, while non-GPT
models (Claude, Llama, etc.) continue using the completion transformation path.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add OAuth M2M (Machine-to-Machine) authentication via DATABRICKS_CLIENT_ID and DATABRICKS_CLIENT_SECRET
- Add Databricks SDK auto-auth with automatic credential discovery
- Add sensitive data redaction for secure logging (tokens, API keys, secrets)
- Add custom user_agent parameter for partner attribution in Databricks telemetry
- Support user_agent in LiteLLM Proxy via config.yaml litellm_params
- Add 49 mocked unit tests for all new functionality
- Add 13 E2E tests for real-world validation (skipped in CI)
- Update documentation with new features and examples
* update databricks pricing and add DBU<>USD test
* Refactor test_databricks_pricing.py
Removed unnecessary sys.path modification and cleaned up comments.
