litellm/tests/unit/llms/anthropic
devin-ai-integration[bot] b195d15b93
fix(vertex_ai,azure_ai)!: auto-add the compaction, thinking display, and tool change betas on Claude routes (#44747)
* fix(vertex_ai): forward and auto-add the compact-2026-09-04 beta on Claude routes

* test(vertex_ai): prove the compact-2026-09-04 beta reaches the wire through both Claude handlers

* fix(vertex_ai): move a client-sent body compact-2026-09-04 beta to the request header

* refactor(vertex_ai): build the Claude beta set without mutation and inject the client in the messages wire test

* fix(vertex_ai): keep client body betas in the body and answer 400 on a malformed anthropic_beta

* fix(rust): allow the compact-2026-09-04 beta on vertex_ai in the Rust beta table

The beta header config now maps compact-2026-09-04 for vertex_ai, so the Rust
table that mirrors it must stop rejecting that beta there, and the Rust Vertex
messages route adds it for a compaction request like the Python route does.

* fix(vertex_ai): keep client body betas out of the Vertex body next to litellm betas, honor drop_params, and send the compaction beta on count_tokens

Litellm's own betas replace a client's body anthropic_beta again, as on main, so a body beta
Vertex rejects no longer turns a 200 into a 400. A malformed beta drops under drop_params and
names its field otherwise. inline-tools-2026-09-15 joins compact-2026-09-04 as header-only, since
Vertex rejects both in the body. Vertex count_tokens sends compact-2026-09-04 when the request
carries compaction.

* fix(logging): log and bill Anthropic messages compaction responses on the Rust route

The Rust route hands the served Anthropic body to the logger, which validates it
against AnthropicResponse. That model had no compaction content block and no
compaction stop reason, so a compaction reply raised and wrote no spend row.

* fix(vertex_ai,azure_ai): forward compact-2026-09-04 to Azure AI Foundry, merge Vertex body betas, and redact compaction summaries

Azure AI Foundry needs the compact-2026-09-04 header for compaction, a replayed compaction block, and count tokens, so the beta map, the native compaction providers, and the Rust beta table now allow it there. Vertex keeps a client's body betas next to the ones litellm adds, as the Anthropic route does, and turn_off_message_logging now redacts compaction summaries too

* fix(vertex_ai,azure_ai): auto-add thinking display and tool change betas, redact streamed compaction summaries

Folds the header changes from #44103 into this PR. Vertex AI and Azure AI Claude
routes now add thinking-display-updates-2026-08-18 when thinking.display is
"updates" and mid-conversation-tool-changes-2026-07-01 when a tool_addition
block is present, matching the Anthropic and Bedrock routes.

With turn_off_message_logging on, compaction summaries from streamed messages
and streamed chat completions are now redacted in spend logs and callback
payloads, like the non-streamed response already was.

* fix(vertex_ai,azure_ai,rust): add tool change betas on count tokens and Rust messages, bill Rust server tool replies

Vertex and Azure count tokens now add mid-conversation-tool-changes-2026-07-01 when the history carries a tool_addition or tool_removal block, through one shared helper with the compaction beta.

The Rust /v1/messages route adds thinking-display-updates-2026-08-18 and mid-conversation-tool-changes-2026-07-01 when a request uses them, on the providers that accept each beta.

Rust-route logging parses the served body with the Anthropic response parser, so web_search, pause_turn, mcp_tool_use and container_upload replies get a spend row.

Legacy enabled thinking keeps display updates on anthropic too, and the Vertex transform reads drop_params through drops_unsupported_params.

* style(rust): rewrap beta map test line with cargo fmt

* test(rust): expect the display beta on Databricks, which main's beta list now accepts

---------

Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
2026-10-30 09:28:19 -07:00
..
batches feat(anthropic): workload identity federation and pluggable identity sources (#44448) 2026-10-03 17:08:30 -07:00
chat fix(logging): warn when drop_params drops a requested reasoning level on the remaining paths (#48933) 2026-10-30 08:48:43 -07:00
files chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
messages fix(logging): warn when drop_params drops a requested reasoning level on the remaining paths (#48933) 2026-10-30 08:48:43 -07:00
pass_through refactor(anthropic): rename llms/anthropic/pass_through to llms/anthropic/messages (#48510) 2026-10-27 10:08:25 -07:00
__init__.py test(unit): add package markers to migrated unit test directories 2026-09-20 11:53:14 +00:00
anthropic_docs_refusal.py fix(anthropic): keep refusal stop_reason and stop_details on the logged response (#46104) 2026-10-14 14:42:49 -07:00
test_anthropic_common_utils.py fix(vertex_ai,azure_ai)!: auto-add the compaction, thinking display, and tool change betas on Claude routes (#44747) 2026-10-30 09:28:19 -07:00
test_anthropic_count_tokens_transformation.py fix(count_tokens): count a history that carries a compaction block (#44784) 2026-10-30 00:11:55 -07:00
test_anthropic_files_and_batches.py feat(anthropic): workload identity federation and pluggable identity sources (#44448) 2026-10-03 17:08:30 -07:00
test_anthropic_output_format_filter.py fix(bedrock): use native structured output on Haiku 5.5 and Sonnet 5.5, and fix Fable 5 and Sonnet 4.6 schema 400s (#46870) 2026-10-16 20:57:23 -07:00
test_anthropic_prompt_cache_prediction.py fix(logging): warn when drop_params drops a requested reasoning level on the remaining paths (#48933) 2026-10-30 08:48:43 -07:00
test_anthropic_prompt_cache_pricing.py refactor(anthropic): move prompt cache pricing helper out of the proxy package (#45753) 2026-10-10 20:32:34 +00:00
test_anthropic_reasoning_effort.py refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
test_anthropic_schema_filter.py fix(bedrock): use native structured output on Haiku 5.5 and Sonnet 5.5, and fix Fable 5 and Sonnet 4.6 schema 400s (#46870) 2026-10-16 20:57:23 -07:00
test_anthropic_structured_output.py test: move tests/test_litellm/llms into tests/unit/llms (#43191) 2026-09-25 12:43:23 -07:00
test_anthropic_wif.py fix(anthropic): fail closed when a token-file or inline-token federation credential is missing a rule or organization id (#45178) 2026-10-07 18:08:19 -07:00
test_azure_ai_cache_pricing.py test: move tests/test_litellm/llms into tests/unit/llms (#43191) 2026-09-25 12:43:23 -07:00
test_cost_calculation_dict_safety.py feat(anthropic): workload identity federation and pluggable identity sources (#44448) 2026-10-03 17:08:30 -07:00
test_count_tokens_oauth.py fix(count_tokens): count a history that carries a compaction block (#44784) 2026-10-30 00:11:55 -07:00
test_message_sanitization.py fix(anthropic): stop injecting empty-content placeholder into tool-call-only assistant turns (#34822) 2026-10-24 13:48:29 -07:00