Test-only. Takes main's version of test_shipped_tool_search_rule_fills_mapped_claude_entries_without_flag, test_cache_control_injection_tool_config_honors_ttl_for_regional_model_lacking_own_pricing and test_get_model_info_gemini; retargets three tests whose rows main changed or removed (gemini-2.0-flash-001 -> gemini-2.5-flash, gpt-5.1-codex-max -> gpt-5.2 for xhigh, gpt-5.1-chat-latest -> gpt-5.1); registers this line's unsupported providers in PROVIDER_LABELS_WITHOUT_A_MODEL_SET; adds extraction mode, main's enum lists and every key main's map uses to test_utils' inline schema, plus main's seedance cost exceptions.
Backport of the router charge-once part of #47625 to stable/1.103.x, from main 6564a490f4 via the stable/1.104.x port 91cb4a55b5.
The batch accounting retry already landed in the earlier #47625 commit; this adds the charge-once helpers moved into router_utils.batch_utils and RouterBudgetLimiting's per-batch marker using the line's duration_in_seconds window. The shared-worker test waits for this line's background Redis push before reading spend.
Backport of #38172 to stable/1.103.x, from main 8327cd6d47 via the stable/1.104.x port 844e02f602.
Prerequisite for #47625: RouterBudgetLimiting reads the provider from the logging payload, so the batch poller's aretrieve_batch events reach router budgets at all. Test file placed at tests/test_litellm/router_strategy/ on this line.
Prerequisite for the #47625 backport to stable/1.103.x, from main 8a33b37c39.
Adds the per-counter batch charge-once marker that #47625 moves into router_utils.batch_utils.
Backport of #47419 to stable/1.103.x.
Cherry-picked from 3124797399 (main), via the stable/1.104.x port c88cf13cd3.
Adapted to the line: the cost-calc threshold changes are applied to this line's loop without the 1.104 base's batch-tier helpers; ModelNotMappedError from #42497 is hand-ported (exception class plus the get_model_info raise and re-raise) so registration lookups can tell an unmapped model from a transient failure; tests whose catalog rows (gpt-6-sol, gpt-6-luna from #42515) are not on this line are retargeted to amazon.nova-micro-v1:0 and gpt-5.6-sol profiles; the test conftest also snapshots _runtime_registered_fields. Billing checked unchanged on this line for a cross-provider alias (keeps cache prices) and for unpriced openai/ft: and bedrock/ap-northeast-1 deployments.
Backport of #47625 to stable/1.103.x.
Cherry-picked from 6564a490f4 (main).
Adapted to the line: the batch accounting retry (track_batch_accounting in proxy_track_cost_callback and its use in check_batch_cost) is ported, while this PR's router-budget charge-once changes in router_utils/batch_utils, budget_limiter and model_max_budget_limiter are left out, since they refactor charge-once code from main (8a33b37c39, 9acf09f60d) that is not on this line. The write-started mark keys on a budget reservation only, as the search free tier is not on this line. Tests use the line's _ProxyDBLogger, and the router-budget and search-allowance assertions are dropped.
Backport of #47190 to stable/1.103.x.
Cherry-picked from 0ede0e10e7 (main).
Ported from the stable/1.104.x hand-port (3b7b5ab319). Carries the small typed table helpers that port relies on (_ManagedObjectRow protocol and the _managed_object_table/_user_table/_token_table/_team_table accessors, from the stable/1.104.x base). The poll-starvation integration test is dropped since its base and harness (#42622, integration/_support/prisma_clients) are not on this line. The 404-recovery unit test resets the litellm callback lists so a callback left by an earlier test cannot shadow it.
Backport of #47184 to stable/1.103.x.
Cherry-picked from 3fb95c8fe3 (main).
Ported from the stable/1.104.x hand-port (f7b0b09e75) onto this line's poller, which keeps LiteLLM_ManagedObjectTable and direct prisma table access. Brings the managed-files postgres_storable_json sanitizer from #45703 that this fix needs. Test files keep the line's content plus this PR's own cases.
Backport of #43935 to stable/1.103.x.
Cherry-picked from d7620c77a1 (main).
Ported from the stable/1.104.x adaptation (54f9259b40): the bridge check lives in litellm/main.py and the effort helpers keep the line's private names. Cost-map edits replay only this PR's reasoning-effort flags (gpt-6-astra and gpt-5.3-codex rows), plus supports_none_reasoning_effort=false on the azure gpt-6.1-sol rows from #46377, which the fix's tests key on. Tests built on gpt-6-sol rows (#42515), the Foundry tools-to-Responses bridge, or a full azure/eu/gpt-6-astra row are dropped since none of those are on this line.
Backport of #43738 to stable/1.103.x.
Cherry-picked from a3552c451b (main).
Prerequisite for #43935: adds the gpt-6.1-sol entry that fix corrects. Cost-map conflict resolved by appending the new entry.
The cost-map schema and its schema test also allow the *_above_272k_tokens_batches keys this row carries, which main already allows.
Backport of #47182 to stable/1.103.x.
Cherry-picked from 1212260ab1 (main).
Test-file conflict resolved by keeping the line's file and appending this PR's tests.
Calls the line's _select_model_name_for_cost_calc, which is the private name on this line.
Backport of #43955 to stable/1.103.x.
Cherry-picked from eb5295b20c (main).
Adapted to the line: the transformation lives under anthropic/experimental_pass_through, the integration tests live under tests/integration/providers, and the CLI-beta wire assertion change is dropped since that test is not on the line.
The github_copilot safeguards test uses the line's authenticator mock, since per-user Copilot sessions are not on this line.
Backport of #45686 to stable/1.103.x.
Cherry-picked from 1aee1a21ed (main).
Adapted to the line: unit test ported into tests/test_litellm; the databricks wire-test additions and the bridge-flag test edit are dropped since neither base test is on this line.
Backport of #45659 to stable/1.103.x.
Cherry-picked from fa7ad80a62 (main).
Adapted to the line: unit tests ported into tests/test_litellm; the databricks chat wire-test additions are dropped since that file is not on this line.
Backport of #45151 to stable/1.103.x.
Cherry-picked from 46d440ae96 (main).
Adapted to the line: the model-catalog Rust crate is not on this line so its two files are dropped; tests live under tests/test_litellm; conflicts resolved by keeping the line's fields plus the over-100k fields this PR adds.
Prerequisite from #39861 ported minimally: the standard above-threshold loop skips *_batches keys, so a non-batch request over 100k is not billed at the batch tier. The batch long-context tier tests are dropped since this line's batch cost path has no long-context tiers, and the runtime profile test calls the line's private _is_adaptive_thinking_model.
Backport of #45108 to stable/1.103.x.
Cherry-picked from 5cd1126870 (main).
Prerequisite for #45151: adds the claude-haiku-5-5 entries that fix corrects. Cost-map conflicts resolved by appending the new entries; schema test lives under tests/test_litellm on this line.
The cost-map schema and its schema test also allow cache_creation_input_token_cost_batches, cache_read_input_token_cost_batches and supports_anthropic_compaction, which these entries carry and main already allows.
Backport of #44460 to stable/1.103.x.
Cherry-picked from f81a3f5243 (main).
Conflict: took main's terminal_event declaration over the line's completed_event comment form.
* fix(logging): claim the async success dedup flag before the first await
Nested @client wrappers on the chat -> Responses bridge schedule two async
success tasks on one logging object. The dedup flag was checked at the top
of _async_success_handler_body but only set after several awaits; the
worker-thread base64 offload for messages >= 256 KiB yields there, so the
second task passed the same check and the request was logged twice
(two SpendLogs rows, key/team/daily spend counted twice).
Fixes#44500
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
* fix(logging): serialise async success handlers per logging object instead of claiming early
Claiming the dedup flag before the first await (previous commit) let a first
handler that is cancelled before its callbacks run (e.g. by the logging
worker's per-coroutine timeout) suppress the second one, losing the request's
success accounting. Serialise non-streaming handlers on the same Logging
object with an asyncio.Lock kept in a module-level WeakKeyDictionary: the
second handler waits, then skips if the first logged, or logs itself if the
first raised or was cancelled first. Streaming chunk logging is not locked.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
* test(integration): pin one spend row and one key charge for large bridged chat completions
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): wait for the large request's spend row before asserting
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(logging): use fixed timestamps in async success dedup tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(logging): trim the async success dedup lock comment
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(logging): reset background interaction dedupe under the success dedup lock
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(logging): use a fixed start time in the interactions logging helper
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix: claim the async success log at schedule time instead of locking the handler
Nested @client wrappers (chat over the Responses bridge, Anthropic Messages over the chat adapter) exit with one shared Logging object and each queued their own async success handler. The handler checked has_logged_async_success before its awaited work and set it after, so both could pass the check and the request was logged and billed twice.
_schedule_async_success_logging now claims the log on the Logging object synchronously through claim_async_success_log, and a later wrapper returns without enqueuing. There is no await between the check and the decision, so no lock is needed. The per-object asyncio.Lock, the WeakKeyDictionary that held it and the locked block in async_log_background_interaction_completion are gone.
Tests: the regression test moves to tests/unit/test_utils.py and drives two _dispatch_success_logging exits with one Logging object through the logging worker, asserting one log with the inner result. It fails without the claim. The cancelled-handler test is dropped since a second wrapper no longer retries. The background interaction completion test stays.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(logging): pin the background completion event order and name the innermost wrapper in the claim docstrings
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): send one bridged request and assert the inner Responses result is the logged one
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
(cherry picked from commit 157d96dcd0)
The two redaction tests raised the deprecated InvalidStatusCode, which the
websockets 15 asyncio client never raises, and asserted the raw 403 close
code that the handshake refusal path replaced with 1008. The refusal path
builds its close reason from the status code alone, so there is no secret
to redact there, and the handshake refusal tests already cover the error
event and the 1008 close.
Those refusal tests only passed when run after a sibling test had imported
websockets.asyncio.client, since websockets lazy-loads its exceptions
submodule. Importing InvalidStatus, Response, and Headers from their own
submodules makes them pass in any order.
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
(cherry picked from commit 38f0eb876b)
* fix(realtime): surface an upstream handshake refusal as an error event and policy close
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(realtime): tidy the handshake refusal e2e
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(realtime): keep upstream exception text out of the Azure client error
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(realtime): map handshake refusal close codes with a lookup
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
(cherry picked from commit 2bab39e374)
The line's integration conftest refuses any owned test missing from
contracts.json, so the backported #46099 and #46109 tests get covers marks
and manifest entries here; main has no manifest.
