mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-06 02:48:13 +00:00
325 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
tin-berri
|
2d6b57407d
|
Merge pull request #34578 from BerriAI/litellm_headroom_tokens_saved
fix(guardrails): derive tokens_saved when Headroom compression service omits it |
||
|
yucheng-berri
|
76b0b10908
|
fix(guardrails): add /v1/messages support for Straiker plugin (#34548)
* fix(guardrails): add /v1/messages support for Straiker plugin - Pass prepared response data to Anthropic Messages streaming post-call hooks (litellm/llms/anthropic/chat/guardrail_translation/handler.py) - Normalize Straiker request, tool, finish-reason, and mode fields across Chat Completions, Messages, and Responses APIs * fix(guardrails): gate cross-surface message resolution and cover streaming request data Resolve request messages only for surfaces that have a mapped translation handler. The unguarded fallback tried every registered handler in turn, which raised AttributeError out of the guardrail's error handling on list-shaped `input` bodies, and synthesized a chat message that was never sent for bodies it happened to parse. Prepare request data on the mid-stream Anthropic branch as well, matching the terminal branch and the OpenAI handler, so guardrails that scan before end-of-stream still receive identity metadata. Read usage from Anthropic dict responses so non-streaming /v1/messages reports token counts instead of null. Add regression coverage for the streaming request data on both the terminal and mid-stream branches; reverting either now fails. --------- Co-authored-by: cs-mehta <chandra@straiker.ai> |
||
|
tin-berri
|
842f32dbaa
|
Merge pull request #34458 from BerriAI/litellm_lit4759_guardrail_metadata_bucket
fix(guardrails): keep guardrail information in spend logs when the caller sends its own metadata |
||
|
Tin Chi Lo
|
9bd89290cb |
fix(guardrails): derive tokens_saved when Headroom compression service omits it
The savings readers (extract_compression_saved_tokens, feeding compression_saved_tokens on the daily spend tables) key exclusively on tokens_saved in the guardrail_response stats, but the Headroom guardrail builds those stats as a filtered pass-through of the compression service response and the live service omits tokens_saved. Every compressed request recorded 0 saved tokens on the Cost Optimization dashboard. Derive tokens_saved = tokens_before - tokens_after when the key is absent and both operands are numeric; a service-sent value still wins. The two sibling writers (compresr, native compression interception) already derive it the same way. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> |
||
|
Tin Chi Lo
|
9777e9524a |
fix(guardrails): stop reporting a no-op guardrail as applied on passthrough
On passthrough requests the shared guardrail plumbing still dispatches headroom's pre_call apply_guardrail, but the passthrough translation hands it only `texts` and no `structured_messages`, so it early-returns a no-op. The @log_guardrail_information decorator then synthesized an "allow"/"success" StandardLoggingGuardrailInformation entry, and the unified hook added the guardrail to applied_guardrails, so spend logs reported the compression guardrail as succeeded even though nothing ran. Add a records_own_guardrail_information flag for guardrails that log their own execution (headroom). The decorator skips the synthetic success entry for them, and the unified hook lists such a guardrail in applied_guardrails only when it actually recorded a run. A guardrail that owns its logging must record every outcome it runs, so headroom now records a guardrail_failed_to_respond entry on the fail_open path (compression attempted, service unreachable, request forwarded uncompressed) instead of leaving it unlogged; fail_closed is still recorded by the decorator's error path, and a genuine no-op stays not_run. |
||
|
Tin Chi Lo
|
770f41b5fa |
fix(guardrails): keep guardrail information in spend logs when the caller sends its own metadata
The guardrail-information writer picked its metadata bucket with a hand-rolled precedence that preferred a caller-supplied `metadata` field, while every reader resolves the bucket through `get_metadata_variable_name_from_kwargs`, which prefers `litellm_metadata`. The two rules agree only when the caller sends no `metadata` of its own. Routes in `LITELLM_METADATA_ROUTES` seed `litellm_metadata`, so on /v1/messages and /v1/responses a caller that sends `metadata` sent the entry to a dict nothing reads; the spend log then reported `guardrail_status: not_run` with no `guardrail_information` even though the guardrail ran and the `x-litellm-applied-guardrails` header was present. Give the resolver one owner. `get_or_create_metadata_bucket` moves from the proxy layer into core_helpers next to the resolver it calls, so `litellm/integrations` can reach it without a proxy dependency, and the byte-identical duplicate of `get_metadata_variable_name_from_kwargs` in callback_utils is deleted. The writer now shares that owner with `add_guardrail_to_applied_guardrails_header`, so the response header and the spend log can no longer disagree. Two readers had to move with it or the fix would be a no-op on the affected routes. `_sync_guardrail_info_to_logging_obj`, which bridges request_data into the spend-log payload for passthrough routes, picked the first truthy bucket, so a non-empty caller `metadata` short-circuited it. The otel failure-path span reader `_emit_guardrail_spans_from_request_data` read a hard-coded `metadata` key, which also dropped the span whenever the entry lived in `litellm_metadata`. Model Armor already resolved the bucket for its file-scan results but wrote its text-scan and post-call results, and read them back in `_process_response`, through a hard-coded `metadata` key; on a seeded route that split the record so a file scan's evidence never reached the logger. All four Model Armor sites now use the shared resolver. The unified guardrail hook seeds `litellm_metadata` on every route, so the OpenAI moderation entry lands there too; spend-log output is unchanged because `merge_litellm_metadata` reads both buckets. |
||
|
Noah Nistler
|
8177230a29
|
feat(guardrails): add run_in_parallel opt-in for concurrent pre_call and post_call guardrails (#33770)
* feat(guardrails): add run_in_parallel opt-in for concurrent pre_call guardrails Pre-call guardrails run sequentially because each may mutate the request payload and later guardrails depend on earlier mutations. Deployments with several slow block-only pre_call guardrails (external moderation, Bedrock, LLM-judge) therefore pay the sum of their latencies. during_call guardrails run concurrently but alongside the LLM call, so a violating payload has already been sent, which is unacceptable when the request must never reach the model. This adds a per-guardrail run_in_parallel flag (default off). Guardrails that opt in are pulled out of the sequential loop and run concurrently via asyncio.gather after every sequential (payload-mutating) guardrail has run, so they observe the mutated payload and still form a hard barrier before the LLM call; the first to raise blocks the request. Their returned data is discarded since they are declared block-only. The flag is wired from LitellmParams onto the guardrail instance at the same generic choke point in initialize_guardrail that already sets skip_system_message_in_guardrail, so no per-provider initializer needs to change. * feat(guardrails): extend run_in_parallel opt-in to post_call guardrails post_call_success_hook ran guardrails sequentially for the same reason pre_call did: response-modifying guardrails thread the response forward. But block-only output scanners (which read the response and reject on violation without changing it) serialize for no benefit and add latency. This reuses the existing run_in_parallel flag for the post_call hook. Opted-in post_call guardrails are pulled out of the sequential loop and run concurrently via asyncio.gather after the sequential (response-modifying) guardrails and before the non-guardrail CustomLogger callbacks, so they inspect the final response and still block it from reaching the client if any raises. Their returned response is discarded since they are block-only. The apply_guardrail path sets data["guardrail_to_apply"] immediately before awaiting, and unified_guardrail pops it before its first suspension point, so concurrent guardrails never race on that key under asyncio's cooperative scheduling. * fix(guardrails): await all parallel guardrails and prioritize blocks over reroutes Addresses review feedback on the run_in_parallel opt-in. asyncio.gather propagated the first exception without cancelling or awaiting the siblings, so a block at t=0 left the other guardrails running as unobserved background tasks (wasted external calls plus event-loop warnings), and a fast SensitiveDataRouteException/ModifyResponseException could return a reroute or passthrough before a slower block finished, letting crafted input bypass the block. Both the pre_call and post_call parallel batches now gather with return_exceptions=True so every guardrail runs to completion, then raise any blocking exception ahead of a flow-changing one. The registry choke point wrote bool(None)==False onto every instance when the config omitted run_in_parallel, silently disabling a constructor-set default; it now only writes when the config provides an explicit value. * fix(guardrails): record lifecycle logs for every concurrently-run guardrail The log_guardrail_information decorator skipped its auto-record when it saw that the count of standard_logging_guardrail_information entries in the shared request_data had grown during the wrapped call, taking that as proof the wrapped function had recorded its own richer entry. That heuristic breaks the moment guardrails run concurrently (parallel pre_call/post_call, during_call): a sibling guardrail's append inflates the shared count, so a guardrail that did not self-record wrongly concludes it already did and drops its own entry. The result is that enabling run_in_parallel silently loses per-guardrail lifecycle logs, so the Admin UI Request Lifecycle timeline and downstream loggers (Datadog, Langfuse, OTEL, spend logs) show only one of the concurrent guardrails. Replace the shared-count heuristic with a ContextVar flag set when a guardrail records its own entry. asyncio copies the context into each gathered task, so the flag is isolated per concurrent guardrail while still catching the self-record-then-skip-auto-record case within a single invocation. * test(guardrails): declare run_in_parallel on post_call guardrail mocks The post_call partition reads run_in_parallel on every CustomGuardrail callback. A MagicMock(spec=CustomGuardrail) has no run_in_parallel (it is set in __init__, not on the class) so the attribute access raised, and even a class-level default would return a truthy child mock that wrongly routes the double into the parallel batch. Declare the flag False on the shared mock factories so these pre-existing hook tests exercise the sequential path they assert on. * fix(guardrails): harden run_in_parallel reads and address review feedback Read run_in_parallel via getattr(..., False) in the pre_call and post_call partitions so a third-party CustomGuardrail subclass that overrides __init__ without chaining super().__init__() no longer raises AttributeError on a path that previously worked. Drop the redundant in-function GuardrailEventHooks import in _run_parallel_post_call_guardrails (already imported module-level). Remove the flaky wall-clock upper-bound assertions from the two concurrency tests; the all-start-before-any-end overlap assertion is the timing-independent signal that actually proves concurrency. |
||
|
devin-ai-integration[bot]
|
7257d0fc89
|
fix(guardrails/model_armor): handle None metadata in post_call _process_response (#34390) (#34405)
* fix(guardrails/model_armor): handle None metadata in post_call _process_response
On batch routes data["metadata"] is normalized to None (present key, None
value), so request_data.get("metadata", {}) returned None and _process_response
raised 'NoneType' object has no attribute 'get', 500ing every /v1/batches create
with a post_call Model Armor guardrail (regression from v1.93.0 activating the
post_call hook). Coalesce a falsy metadata to {}
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* Clean up test case documentation
Remove regression comment from test_process_response_with_none_metadata_does_not_crash.
---------
Co-authored-by: yucheng <yucheng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
|
||
|
devin-ai-integration[bot]
|
fa6b209165
|
feat(guardrails): add only_scan_new_messages for per-session incremental scanning (#33278)
* feat(guardrails): add only_scan_new_messages for per-session incremental scanning Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com> * fix(guardrails): use fixed TTL constant and revert unrelated test formatting Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com> * fix(guardrails): run only_scan_new_messages in the unified apply_guardrail path The initial wiring lived in BedrockGuardrail.async_pre_call_hook, but the proxy routes Bedrock through the unified apply_guardrail interface, so the flag had no effect live. Move incremental selection into apply_guardrail: filter the flat texts list against per-session scanned hashes, skip the Bedrock call when nothing is new, and mark hashes only after a successful (non-blocked) scan. Full-context fallback is preserved when there is no session id, the cache is unavailable, or a masking guardrail is configured. Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com> * test(guardrails): cover session-id fallbacks and mark_texts_scanned guards Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com> * fix(guardrails): fall back to full scan when incremental guardrail masks content, use shared cache Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com> * test(guardrails): cover generic agent multi-turn incremental scan Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com> * test(guardrails): cover incremental scan cache resolver fallbacks Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com> * test(guardrails): cover flag interactions and /v1/messages incremental scan semantics * feat(guardrails): make GUARDRAIL_SCANNED_MESSAGES_CACHE_TTL_SECONDS env configurable * test(guardrails): prove skip_system/skip_tool are enforced upstream of incremental scan --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com> Co-authored-by: Yucheng Zhu <yucheng@berri.ai> |
||
|
yucheng-berri
|
049c6836d2
|
fix(model_armor): sanitize error details by default (#33908)
* fix(model_armor): sanitize error details by default Generated with AI Co-Authored-By: Claude Code * fix(model_armor): sanitize handler-raised HTTP errors and redact scanned content in guardrail logging The async HTTP handler raises MaskedHTTPStatusError on any non-2xx via raise_for_status, so the non-200 branch in make_model_armor_request never ran against a live API and the raw upstream body reached callers and logs. Catch the raised error and build the sanitized detail from the response status Replace the empty-dict guardrail logging payload with field-level redaction of the keys that echo scanned content (text, sanitizedText, findings) so guardrail traces keep filter states and block reasons while scanned content stays out Restore the upstream status code in the sanitized error detail, read guardrail metadata from the same key the hooks write, and keep guardrail_status within its typed literal values * fix(model_armor): bound redactor recursion depth and allowlist it in the recursion detector _redact_scanned_content walks provider JSON bounded by _REDACT_MAX_DEPTH=20 and fails closed by returning the redaction sentinel at the cap * fix(model_armor): honor fail_on_error for upstream API failures API failures now raise a dedicated ModelArmorAPIError so hooks can tell them apart from content-block HTTPExceptions; fail_on_error=False lets the request proceed on a Model Armor outage again while fail-closed configs get the same sanitized 400 as before Also addresses review notes: sanitize_error_detail constructor annotation matches the nullable config field, redaction is owned by the metadata write sites so _process_response no longer re-applies it, and the request and response debug log branches move into helpers * test(model_armor): cover fail_on_error routing on during-call, post-call, streaming, and file-scan paths * chore: remove accidentally committed pytest cache files * fix(model_armor): keep sanitize_error_detail coerced across in-memory config reloads update_in_memory_litellm_params assigns raw LitellmParams fields, so a hot reloaded config carrying an explicit null would silently disable sanitization; re-apply the only-explicit-False-opts-out coercion after the update * fix(model_armor): redact matched malicious URIs and reuse the shared recursion depth constant maliciousUriMatchedItems echoes the caller-supplied URL including path and query, so it joins the scanned-content key set; the redactor depth cap now comes from DEFAULT_MAX_RECURSE_DEPTH in litellm constants instead of a local literal * fix(model_armor): keep API failures out of the intervention trace status Fail-closed upstream failures re-raise ModelArmorAPIError instead of converting to HTTPException(400), so the shared guardrail logging keeps recording them as guardrail_failed_to_respond while content blocks stay guardrail_intervened. Callers see the same 500 shape as before this PR, with the sanitized message * chore(model_armor): drop explanatory comment per repository comment policy --------- Co-authored-by: eugene-yao-zocdoc <eugene.yao@zocdoc.com> |
||
|
yucheng-berri
|
9ad8698aab
|
feat: add deepkeep as custom guardrail (#33844)
* adding deepkeep as custom guardrail * adding deepkeep as a custom guardrail * adding deepkeep as a custom guardrail (hooks) * adding litellm/proxy/_experimental/out/ to .gitignore * adding deepkeep as custom guardrail in litellm * removing sentinel_fortress * comparing schema.prisma files * fix(deepkeep): address greptile review comments - extra_headers: fix type annotation (list -> Dict[str, str]) and actually merge them into _build_request_headers() so user-configured headers reach the DeepKeep API - user_api_key_hash: only fall back to user_api_key_token when no explicit hash is already set, avoiding silent overwrite - apply_guardrail: preserve tool_calls and structured_messages in the return value so downstream callers don't lose that content Adds tests for all four fixes. * fix(deepkeep): address greptile review comments - extra_headers: fix type annotation (list -> Dict[str, str]) and actually merge them into _build_request_headers() so user-configured headers reach the DeepKeep API - user_api_key_hash: only fall back to user_api_key_token when no explicit hash is already set, avoiding silent overwrite - apply_guardrail: preserve tool_calls and structured_messages in the return value so downstream callers don't lose that content Adds tests for all four fixes. * fix: add missing __init__.py and allowlist entries for upstream merge - tests/test_litellm/proxy/client/__init__.py: fixes pytest collection collision with tests/test_litellm/models/test_models.py (same basename) - tests/test_litellm/models/__init__.py: same fix - backend/routes/allowlist.py: add /config_overrides/ and /v1/unified_access_group prefixes for new routes added by upstream * fix(ui/tests): resolve frontend-lint failures in new test files - useLogDetails.test.ts: add Wrapper.displayName, replace 'null as any' with null, type resolveCall promise resolver properly - usePaginatedDailyActivity.test.ts: remove unused waitFor import, add Wrapper.displayName, change Record<string,any> to Record<string,unknown> - UsageViewSelect.adminFiltering.test.tsx: replace all props:any with explicit SelectProps/BadgeProps/SelectOption types, replace (X as any).displayName with direct X.displayName assignment no-explicit-any count: 2034 (budget: 2040). Prettier check: clean. * fix(ui): sync proxy/_experimental/out/ exactly to upstream 245 stale JS chunk files from earlier merges were left in the out/ directory but had been deleted in upstream. The Docker image in CI is built by copying this directory verbatim, so the stale artifacts caused the SERVER_ROOT_PATH redirect E2E to fail. Synced by: git checkout upstream/litellm_internal_staging -- out/ (adds new files) + git rm on every file present in HEAD but absent from upstream. * Update litellm/proxy/guardrails/guardrail_hooks/deepkeep/deepkeep.py Co-authored-by: veria-ai[bot] <224490171+veria-ai[bot]@users.noreply.github.com> * fix(makefile): fall back to upstream/litellm_internal_staging for strict-budget gate origin/litellm_internal_staging exists on BerriAI's CI but not on forks that use a different remote name (e.g. Azure DevOps as origin). Fall back to upstream/litellm_internal_staging when the origin ref is absent. * linter reformat * fix(deepkeep): apply guardrail tool/tool_call redactions from API response When DeepKeep returns GUARDRAIL_INTERVENED with redacted tools or tool_calls, the previous code ignored those redactions and forwarded the original (potentially sensitive) values to the model — a guardrail bypass for content embedded in tool schemas or function arguments. Fix: prefer response_json["tools"] / response_json["tool_calls"] when present, falling back to the originals only when the guardrail did not return replacements — consistent with the existing pattern for texts and images. Refactor _build_return_inputs() into a private static helper to keep apply_guardrail() under the PLR0915 statement limit (50). Adds test_apply_guardrail_applies_tool_redactions_from_response to assert that redacted tool payloads from the API response are used. * Update litellm/proxy/guardrails/guardrail_hooks/deepkeep/deepkeep.py Co-authored-by: veria-ai[bot] <224490171+veria-ai[bot]@users.noreply.github.com> * fix(lint): move base-ref fallback into ruff_strict_gate.py; revert Makefile The previous Makefile fix had a shell bug: 'git rev-parse --verify' writes the resolved SHA to stdout, so the $$(...) substitution captured both the SHA and the echo output, handing '--base <sha>\norigin/...' as two tokens to the Python script, causing exit code 1 in CI. Fix: revert Makefile to its original single-line invocation and add _resolve_base() to ruff_strict_gate.py. The function checks whether the requested ref resolves; if not, it tries the 'upstream/' equivalent before falling back to the original ref (letting git emit a clear error). Behaviour in BerriAI CI: origin/litellm_internal_staging resolves → used as before, no change. Behaviour on forks with a different 'origin': falls back to upstream/litellm_internal_staging transparently. * fix(lint): fix UP006/UP045/F401 in changed files; add depth guard to check_any_discipline - Replace Dict/List/Optional/Tuple typing imports with built-in equivalents (UP006, UP045) across files touched in this PR diff, then clean up the now-unused typing imports (F401). - Add _MAX_CONTAINS_ANY_DEPTH guard to check_any_discipline.contains_any() to prevent RecursionError on deeply-nested mypy types. * fix(lint): resolve all three CI lint job failures 1. lint (ruff_strict_gate) — UP006/UP045/F401 violations introduced on changed lines. Fixed Dict/List/Optional/Tuple → built-in equivalents across every file in the PR diff; cleaned up now-unused typing imports. 2. any-discipline — RecursionError in check_any_discipline.contains_any() on deeply-nested mypy types. Upstream fixed this by converting to an iterative stack-based algorithm (merged). Also added deepkeep.py to any-discipline-budget.json via 'make lint-any-budget-update' so the new file's Any count is baselined instead of failing against the zero-baseline default. 3. basedpyright reportMissingParameterType — **kwargs in DeepKeepGuardrail __init__ lacked a type annotation. Added **kwargs: Any. * Update litellm/deepkeep_tilt_config.yaml Co-authored-by: veria-ai[bot] <224490171+veria-ai[bot]@users.noreply.github.com> * fix(lint): black reformat after merge * fix(deepkeep): honour empty-list replacements in _build_return_inputs When DeepKeep returns GUARDRAIL_INTERVENED with an intentional empty replacement (e.g. texts:[], tool_calls:[]) the previous truthiness check treated [] as absent and forwarded the original content downstream — a guardrail bypass for any case where the firewall wants to fully clear a field. Fix: replace all response_json.get(field) truthiness checks with 'is not None' comparisons so that an empty list is respected as a deliberate replacement. Applies to texts, images, tools, tool_calls, and the original-input fallback guards. Adds test_apply_guardrail_honours_empty_list_replacements. * fix(test): replace live httpbin.org call with mocked transport in test_pass_through_with_httpbin_redirect Root cause of OOM: the test made a real HTTP request to https://httpbin.org inside a pytest-xdist worker. Under memory pressure the worker's httpx client and redirect-following logic allocated enough virtual memory to trip the OOM killer (confirmed by ulimit -v 16GB reproducing the crash with 'node down: Not properly terminated' on this exact test). Fix: replace the real network call with a custom httpx.AsyncBaseTransport that returns a pre-built 302 -> 200 response sequence in-memory. The test now runs hermetically with no network dependency and no excess memory allocation. ulimit -v 16GB: 24,284 passed (0 crashes) after this fix. * fix: merge upstream/litellm_internal_staging (197 commits), resolve conflicts 7 conflicts resolved: - 6 Python files: upstream added new code with old-style typing (Optional, Dict, List) on lines where we had ruff-fixed modern syntax (str | None, dict, list). Took upstream's version then re-ran ruff UP006/UP045/F401 --fix to keep both the new content and ruff compliance. - test_openapi_compliance.py: upstream replaced 'role' with 'steps' in output_fields and updated the spec comment. Took upstream's version. Also: added _resolve_base() fallback to type_check_gate.py and removed the hard 'git fetch origin litellm_internal_staging' from the Makefile's lint-basedpyright target (same pattern as ruff_strict_gate.py fix). * fix: merge upstream (41 commits), resolve .gitignore conflict, fix BLE001 - .gitignore: upstream removed package.json/out/ ignore entries; took theirs - deepkeep.py: added '# noqa: BLE001' on catch-all Exception handler (BLE001 rule newly enforced in ruff-strict-budget) - type_check_gate.py: added _resolve_base() fallback for basedpyright gate - Makefile: removed hard 'git fetch origin' from lint-basedpyright target * fix: merge upstream (57 commits), resolve conflicts - Makefile: upstream added lint-fetch-base target; made it tolerant of missing origin/litellm_internal_staging (git fetch || true) - test_websearch_chat_completion.py: took upstream's new assertions and skipif marker - anthropic_cache_control_hook.py: upstream added new code using List/Dict/Tuple which were undefined after our earlier UP006 cleanup; replaced with built-in list/dict/tuple * fix(coverage): revert ruff UP006/UP045 changes on upstream files The previous ruff fixes (Dict→dict, Optional→X|None) on 7 upstream files added ~500 changed lines of pure type-annotation no-ops to our PR diff. codecov/patch penalised these uncovered lines, dropping patch coverage to 51.35% (target 61.83%). Fix: revert these files to exactly match upstream/litellm_internal_staging. The ruff_strict_gate still passes because the violations exist equally in both the base and HEAD (total == base_count → no breach). * fix: merge upstream (130 commits), resolve Makefile + base_email conflicts - Makefile: upstream changed lint deps to $(LINT_DEP_INSTALL)/$(LINT_DEP_BASE); kept our --base removal (handled by _resolve_base in Python scripts) - base_email.py: took upstream's dedup cache addition - deepkeep.py: ruff format after merge * chore: remove lint/format-only changes and non-feature files Revert all lint-infra and black/ruff-reformat-only changes back to upstream/litellm_internal_staging so the PR diff shows only the DeepKeep guardrail feature: - Makefile, scripts/ruff_strict_gate.py, scripts/type_check_gate.py (lint-gate infra) - credential_migration.py + enterprise/* + assorted test files (black-reformat / xdist test-isolation drift) - backend/routes/allowlist.py (merge glue) Remove non-feature local artifacts: build-and-push.sh, deepkeep_tilt_config.yaml, stray __init__.py collision shims, and unrelated UI test files. * fix(lint): add reason to BLE001 noqa to satisfy type-discipline gate (LIT003) The type-discipline budget ratcheted LIT003's ceiling to 292 as upstream fixed reasonless suppressions, so our '# noqa: BLE001' (code but no reason) tipped the total to 293 and failed CI. Add a reason per the required '# noqa: CODE # <reason>' shape. * fix(deepkeep): apply structured_messages redactions returned by the guardrail API _build_return_inputs dropped any structured_messages the DeepKeep API returned and always forwarded the original input, so redactions on that field never took effect. Check the response first, same as texts/images/tools/tool_calls * chore(ui): drop redundant preserve prop from the guardrail form preserve defaults to true in rc-field-form (isMergedPreserve falls back to true when unset), so the explicit prop changed nothing and only widened this PR's blast radius to every guardrail provider in the shared form * fix(deepkeep): stop extra_headers list from crashing the guardrail call and name the real firewall id config key litellm_params.extra_headers is a list of header names to forward, so passing it straight into dict.update raised ValueError and, under fail_closed, took the request down with it. Only merge mapping values and warn otherwise The docstring example and the missing-secret error both said firewall_id, but initialize_guardrail only reads deepkeep_firewall_id, so anyone following them had their value silently ignored * refactor(proxy): drop normalize_callback change; split to its own PR (#33905) Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: Yaniv Israel <yaniv@deepkeep.ai> Co-authored-by: DK-yaniv <164404355+DK-yaniv@users.noreply.github.com> Co-authored-by: veria-ai[bot] <224490171+veria-ai[bot]@users.noreply.github.com> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
yucheng-berri
|
f759c75466
|
feat: add Straiker guardrail integration (#33781)
* feat: add Straiker guardrail integration Implements LLM security guardrails via Straiker with prompt and response inspection, multi-mode execution (pre_call, post_call), and configurable blocking or redaction of flagged content across providers, streaming, images, and tool calls. * fix(guardrails): harden straiker source attribution and error-path consistency Use the operator-configured source for Straiker application attribution instead of a caller-supplied agent_id metadata value, so a caller cannot spoof which application a detection is attributed to. Make _fail reuse _block so a post_call error raises ModifyResponseException like a deliberate post_call block rather than GuardrailRaisedException, and type the blocking helper as NoReturn so the type checker enforces that execution never falls through the BLOCKED branch. Serialize the webhook payload once and send it as raw content to avoid re-serializing on the size check and on every retry. * fix(guardrails): read straiker config and metadata from all supported shapes Handle a dict optional_params in _get_config_value so nested guardrail settings loaded from YAML or the DB (timeout, unreachable_fallback, and the rest) are applied instead of silently falling back to defaults; previously only attribute-style access was supported. Build the webhook metadata bag from the merged metadata so client tags stored under litellm_metadata on routes like /v1/messages reach Straiker the same way identity and application fields already do, and widen the internal-key skip prefix to user_api so proxy-injected budget values are not forwarded. * fix(guardrails): fail safe on straiker interventions without redactions Block instead of passing content through when Straiker returns GUARDRAIL_INTERVENED without replacement texts, so a positive intervention verdict can never silently forward the original flagged content. Fix the streamed-request detection to read the request body from proxy_server_request.body, where the proxy stores it, instead of a top-level body key that is never populated; the previous fallback was dead, so a streamed response whose stream flag was not lifted to the top level would have been redacted rather than blocked while buffering replayed the original chunks. * revert(guardrails): restore straiker caller agent_id application attribution Restore the original behavior where a request-scoped agent_id in metadata sets the Straiker application source, falling back to the configured source. This is the integration's intended per-application attribution; litellm already resolves a key-owned agent_id ahead of any caller-supplied value, so a configured key cannot be spoofed. * revert(guardrails): restore straiker webhook metadata scoping Restore the original behavior where the Straiker webhook metadata bag is built from request-scoped metadata only. Forwarding litellm_metadata was a scope change to what the integration sends to Straiker; keep the author's intended scoping. * fix(guardrails): keep proxy key material out of straiker webhook metadata Widen the internal-key skip prefix from user_api_key_ to user_api so the proxy-injected user_api_key hash and user_api_end_user_max_budget are not copied into the Straiker webhook metadata bag. The narrower prefix missed the bare user_api_key name, leaking the hashed key to the vendor. Keeps the request-scoped metadata source unchanged. --------- Co-authored-by: cs-mehta <chandra@straiker.ai> |
||
|
yuneng-jiang
|
04a5ebb94d
|
chore(ci): merge oss branch (#33784)
* fix(embeddings): accept encoding_format='float' for vertex_ai/gemini embeddings (#33617)
OpenAI SDKs (and litellm's own client since ~1.84) send
encoding_format='float' by default, but the vertex embedding config only
supports ['dimensions'], so get_optional_params_embeddings raised
UnsupportedParamsError at the provider default value. Any
OpenAI-compatible client talking to a litellm proxy with vertex
embedding models got a 400 unless the operator set proxy-wide
drop_params: true.
Float lists are exactly what the vertex API returns, so the param is a
no-op: pop it before validation. Other values (e.g. 'base64') keep the
existing unsupported-param behavior (dropped with drop_params, raise
otherwise).
Fixes #33173
Co-authored-by: Mihidum Hettiyahandi <55163074+mihidumh@users.noreply.github.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* feat(guardrails): add Singulr guardrail integration for LiteLLM gateway (#31302)
* singulr guardrail support for litellm gateway
* Update litellm/proxy/guardrails/guardrail_hooks/singulr/singulr.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix comments
* improvement
* fix: resolve review comments and implement requested improvements
* fix:Guardrail bypass through uninspected messages
* fix:tool text scanning
* fix: Legacy function definitions bypass scanning by adding indirect message scaning
* chore: remove unintended basedpyright budget file
* fix:Response schema bypasses guardrail scanning (response_format.json_schema)
* chore: restore basedpyright-code-budget.json and update lint baselines
Restores the file deleted in
|
||
|
devin-ai-integration[bot]
|
0d7b0f708b
|
fix(model_armor): restore reference attachments via skip_unscannable_attachments and remove the attachment count cap (#33554)
* fix(model_armor): add skip_unscannable_attachments to allow reference-only attachments through * fix(model_armor): wire skip_unscannable_attachments through guardrail config * fix(model_armor): make max_file_attachments configurable and scan overflow instead of dropping * fix(model_armor): remove the per-request attachment count cap and scan all attachments --------- Co-authored-by: yucheng <yucheng@berri.ai> |
||
|
yuneng-jiang
|
ff06119aa9
|
Merge pull request #32853 from BerriAI/litellm_/guardrail-monitor-details-fix-8845d6
fix(guardrails): show YAML-defined guardrails in the Guardrail Monitor |
||
|
devin-ai-integration[bot]
|
b907378f02
|
feat(guardrails): forward optional metadata on POST /guardrails/apply_guardrail (#33067)
Clients calling the standalone apply_guardrail endpoint had no way to pass per-request configuration to custom guardrail implementations. This adds an optional metadata field to ApplyGuardrailRequest and forwards it to CustomGuardrail.apply_guardrail via request_data, only when the client sends it. The messages guard is aligned to the same is-not-None semantics so an explicitly-sent empty list is forwarded instead of silently dropped. The Admin UI's Guardrail Test Playground gains an optional Metadata JSON input (validated client-side) wired through applyGuardrail in networking.tsx, so parameterized guardrails can be exercised from the dashboard. Tests cover metadata alone, metadata with messages, explicit empty values, the omitted-field passthrough, and the UI panel's parse/error behavior Co-authored-by: Yassin Kortam <yassin@berri.ai> |
||
|
yucheng-berri
|
587b8aca9b
|
feat(guardrails): add Compresr guardrail for query-aware context compression (#33295)
* feat(guardrails): add Compresr guardrail for query-aware context compression Adds a first-class guardrail that compresses bulky message content (tool outputs, RAG chunks, search results) through the Compresr API before the request reaches the LLM, via the apply_guardrail / structured_messages hook so it covers /chat/completions, /v1/messages, and /v1/responses (the latter through the texts channel, mirrored only when the replacement is unambiguous; anything ambiguous is left uncompressed). Distinct from whole-conversation compressors: - Query-aware: each message is compressed against the intent that produced it (a tool output against its originating tool call's name + arguments, resolved via tool_call_id; otherwise the last user message). - Recoverable: each compressed message carries a hash marker and the request gains a compresr_retrieve tool, so the model can pull the original content back through the agentic loop when the compressed version is not enough. Originals are cached in-process, scoped to the caller's virtual-key hash plus the request's litellm_call_id, with a TTL and a per-call byte cap; recovery is skipped when no caller scope is available so one caller can never read another's originals. The store is per-process, so multi-worker deployments need sticky routing (or enable_retrieval=false). Fail-closed by default (fail_open configurable), SSRF-validated api_base (alternate IP-literal encodings included), cross-tenant-isolated recovery store, and upstream errors redacted from client-facing responses. The outbound client follows redirects and re-resolves DNS per request, so the api_base host/IP checks are defense-in-depth, not a full SSRF guarantee; this is documented as a known limitation. Requests where nothing was actually compressed are returned untouched (same object identity) so handlers skip the write-back. Auto-discovered via the guardrail_hooks registry. * fix(guardrails): cap Compresr recovery store total memory The recovery store bounded bytes per call and entry count, but had no aggregate cap: 256 tracked call ids at the 10 MiB per-call default could retain ~2.5 GiB per worker. A flood of requests with distinct x-litellm-call-id values and large compressible tool outputs could exhaust a shared proxy worker. Add a global byte budget (_MAX_TOTAL_STORE_BYTES, 256 MiB) across all entries. A running total is maintained on every insert/eviction so the cap is enforced without re-encoding the whole store on the request path; oldest entries are evicted once the budget is exceeded, always keeping the most-recent entry so recovery still works for the request populating the store. +2 regression tests. * fix(guardrails): gate and bound Compresr recovery loop Two hardening fixes to the compresr_retrieve agentic loop: 1. Only run the loop when a retrieve call resolves to recovery state this guardrail actually created for the request. Previously the gate checked only that the caller-supplied tool list contained a compresr_retrieve function and that the model emitted a call, so a caller could define their own same-named tool and force an extra provider round-trip with nothing to recover. The plan now returns run_agentic_loop=False when no requested hash resolves. 2. Bound the follow-up against retrieval amplification: each distinct hash is expanded at most once (repeats get a short marker) and at most _MAX_RETRIEVALS_PER_LOOP calls are honored, so prompting the model to call compresr_retrieve many times with the same marker cannot balloon the follow-up. _retrieve_original now returns None on miss. +3 regression tests; two existing security tests updated to assert the stronger veto behavior (forged/cross-tenant hashes now stop the loop entirely instead of returning a not-found follow-up). * fix(guardrails): warn when Compresr recovery is skipped without auth scope When enable_retrieval is on (the default) but the proxy has no per-key auth, the request has no caller scope, so recovery is silently disabled: content is compressed but the compresr_retrieve tool is never injected and the originals are dropped, with no runtime indication. Emit a one-shot call-time warning so operators can see recovery is being suppressed and configure virtual-key auth. +1 regression test. * style(guardrails): tighten Compresr guardrail comments Condense the verbose multi-line inline comments and the api_base docstring to concise form. No behavior change. * fix(guardrails): keep injected tool on Responses API + bound recovery markers by byte cap Two fixes for reviewer-flagged defects in the Compresr guardrail: - Responses API: _merge_tools_after_guardrail iterated only over the request's original tools, dropping any tool a guardrail appended (the compresr_retrieve recovery tool) whenever the request already had tools. Keep the appended tools so recovery works on /v1/responses. - Recovery markers: markers + originals were built for every compressed target before the per-call byte cap trimmed the store, so an evicted original left a marker the model could never retrieve. Attach recovery only while the store (existing entries under the same key + this call's originals) stays within the cap, so a shipped marker is always retrievable -- including on a later turn that reuses the store key. Adds regression tests for both paths. * refactor(guardrails): extract _existing_originals to keep apply_guardrail under the complexity gate The byte-cap fix added a branch to apply_guardrail, tipping it past the C901 complexity ceiling. Move the store lookup into a small helper; no behavior change. * fix(guardrails): harden Compresr SSRF blocklist, re-arm no-scope warning, tolerate odd tool shapes * fix(guardrails): rerun input guardrails on Compresr retrieval follow-up * chore: remove unrelated deepkeep files committed by mistake --------- Co-authored-by: charafkamel <charafkamel@live.com> |
||
|
yucheng-berri
|
e3546c20af
|
feat(bedrock guardrails): add resource-less InvokeGuardrailChecks (detect-only) mode (#33299)
* feat(bedrock guardrails): add resource-less InvokeGuardrailChecks (detect-only) mode Adopted from #30830 by OS-joaocastilho; the original PR was merged into litellm_oss_staging_230626, which never landed, so this re-lands it on litellm_internal_staging Beyond the original diff, this fold includes the review fixups that were made on the staging branch (warn on unrecognized check keys, keep empty known checks as enable-with-defaults, fail fast when the checks block has no usable keys, tz-aware datetimes, stricter typing) and adapts the block path to the ModifyResponseException contract from LIT-4186, which replaced GuardrailInterventionNormalStringError after the original PR was written * fix(bedrock guardrails): only evaluate configured checks in violation collection An unsolicited score in the InvokeGuardrailChecks response (e.g. a future API revision returning checks the user never requested) previously fell through to the default 0.5 threshold and could block a request the user only asked to scan with other checks. Violation collection now skips any check absent from the configured checks block * fix(bedrock guardrails): fail closed on truncated PII results and tighten checks-path typing Truncated sensitiveInformation results now count as a violation when the PII check is configured: Bedrock omitted detections that were never scored, so sub-threshold visible entries no longer let the request pass. Also blocks on score == threshold per the documented contract (regression test added), rejects checks combined with guardrailVersion, turns a malformed 200 body into a logged guardrail_failed_to_respond 500 instead of a raw ValidationError, types the checks parameter and violations (BedrockChecksConfigModel, BedrockChecksViolation) instead of dict/object, types _sign_and_post against AWSPreparedRequest, hoists stdlib imports, and builds checks messages without intermediate mutation * fix(bedrock guardrails): tag all InvokeGuardrailChecks INPUT content as user Bedrock excludes system content from prompt-attack evaluation (per the AWS guardrails docs), so mapping a caller-supplied system/developer message onto the system role let a caller hide a prompt injection from the promptAttack check by self-labeling its role. At the proxy every INPUT message is caller-controlled, so all of it is now tagged as untrusted user input, which also matches AWS guidance to tag untrusted content as user input. OUTPUT stays assistant. Removes the now-unused role map; the input-message test asserts the new tagging as a regression * fix(bedrock guardrails): pass prepared request headers to httpx without dict coercion httpx accepts botocore's HTTPHeaders mapping directly, and wrapping it in dict() broke the existing test_bedrock_guardrail_make_api_request_passes_api_key which supplies a bare Mock as the prepared request (dict(Mock) calls Mock.keys()) --------- Co-authored-by: OS-joaocastilho <144790013+OS-joaocastilho@users.noreply.github.com> |
||
|
yucheng-berri
|
b2202cb1aa
|
feat(guardrails): streaming text transformation in generic_guardrail_api (#33110)
* feat(guardrails): support streaming text transformation in generic_guardrail_api * chore(guardrails): address PR review feedback * fix(guardrails): fail closed on tool-call and prefix-rewrite leaks in streaming transform * fix(guardrails): address Bugbot review on streaming transform correctness * fix(guardrails): coerce holdback in handler for in-process guardrails * fix(guardrails): harden streaming transform (holdback coercion, tool-call passthrough, n>1 finish_reason) * test(guardrails): targeted _mode_matches coverage for all guardrail_mode shapes * fix(guardrails): inspect streamed tool calls and harden incremental_diff edge cases * test: move ComplianceChecker mode tests to the compliance PR * fix(guardrails): strip content from tool-call passthrough so streamed text can't bypass the transform * fix(guardrails): four correctness fixes for incremental_diff streaming path Four bug fixes on top of the OSS PR's incremental_diff streaming text transformation, all inside the incremental_diff code paths only. No existing block_only, non-streaming, or pre_call behavior is touched. Fix #1 — Mixed content+tool_call finish_reason ordering _tool_call_passthrough_chunk now takes an optional finish_reason_per_choice map. For a choice carrying both delta.content and delta.tool_calls, finish_reason is stripped from the passthrough and recorded on the map so the final synthetic text chunk delivers it. Without this, SSE-compliant clients stopping at finish_reason drop the guardrailed text — defeating the redaction the whole feature exists for. (Greptile P1 twice, Veria.) Fix #2 — Choice index sort in _process_streaming_transform indices/texts_to_check were derived from dict insertion order. For n>1 streams where choice 1 emits before choice 0, guardrail-returned texts aligned to the input order mapped back to the wrong choice indices on write-back — wrong text goes to wrong choice. Sort raw_by_index.keys() up front so realignment is deterministic. (Bugbot Medium.) Fix #3 — Cross-chunk pre-tool-call text flush With default streaming_sampling_rate=5, text chunks followed by a pure tool-call chunk carrying finish_reason='tool_calls' would emit the passthrough with finish_reason before any transformed text delta had fired. Same failure mode as fix #1 but cross-chunk. Now we flush any accumulated text via _round(is_final=False) BEFORE yielding the tool-call passthrough. (Greptile P1.) Fix #4 — Terminator chunk for deferred finish_reason on empty mutated_text _build_transform_chunk returned None early when mutated_text_per_choice was empty. If a mixed content+tool_call chunk had deferred its finish_reason (via fix #1) and the guardrail then suppressed the text (empty return), the deferred finish_reason was never delivered. Now on is_final=True with empty mutated_text_per_choice, we emit a terminator carrying finish_reason per choice from finish_reason_per_choice. (Bugbot High.) Also normalized Optional[X] → X | None across the OSS PR's added surface via ruff UP045 autofix to keep the strict-rule gate within budget. Pure mechanical typing style change, no semantic effect. Regression tests for all four fixes: - test_mixed_chunk_finish_reason_arrives_after_transformed_text (#1) - test_text_flush_precedes_tool_call_passthrough (#3) - test_final_finish_reason_flushed_when_guardrail_suppresses_text (#4) - test_transform_sends_texts_sorted_by_choice_index (#2) All fixes reachable only when streaming_transform_mode == 'incremental_diff' is configured (via _run_incremental_transform_stream) or when a StreamTransformSink is present (via _process_streaming_transform). Verified scope-clean: no changes to block_only, non-streaming, pre_call, moderation, or sibling guardrails. --------- Co-authored-by: Marton Schneider <marton@schneider.co.nl> |
||
|
yucheng-berri
|
78e5c43301
|
feat(lasso): send source.type=litellm for Used By attribution (#33090)
Co-authored-by: Or Gershoni <org@lasso.security> |
||
|
yucheng-berri
|
ff2b690dd4
|
fix(guardrails): walk custom_tool_call_output items in _content_utils (#32969)
* fix(guardrails): walk custom_tool_call_output items in _content_utils * Change _OUTPUT_ITEM_TYPES to Frozenset type * fix(guardrails): use builtin frozenset generic for _OUTPUT_ITEM_TYPES annotation Frozenset is not a defined name (typing exports FrozenSet, the builtin is frozenset), so module import raised NameError and broke every proxy test suite. The builtin generic is valid on the supported python floor (3.10) and keeps the UP006 ruff-strict budget at its ceiling, which the typing alias would exceed |
||
|
yucheng-berri
|
f61fd2fb6d
|
fix(xecguard): sanitize scan result before recording it for logging (#32935) | ||
|
yucheng-berri
|
f947ef14a2
|
fix(xecguard): use StandardLoggingGuardrailInformation in logging hook (#32911)
XecGuard's async_logging_hook wrote a bare dict to standard_logging_object["guardrail_information"] while the typed contract is Optional[List[StandardLoggingGuardrailInformation]]. Readers that iterated the field walked dict keys, raised on info.get, or silently dropped the entry from guardrail usage tracking and spend-log writes Construct the typed entry and append it to the existing list or create a new one, matching the shared helper pattern. Record the configured guardrail name instead of a hardcoded "xecguard" and pass the GuardrailEventHooks enum for guardrail_mode |
||
|
yucheng-berri
|
e7f41442d0
|
feat(guardrails): add pre_mcp_call support to Content Filter (#32936)
* feat(guardrails): add pre_mcp_call support to Content Filter * test(guardrails): cover canonical MCP key gate under pre_mcp_call mode * fix(guardrails): scan MCP arguments per value and gate mixed-mode scans by call type * fix(guardrails): cap MCP argument scan depth and register the walker with the recursion detector * test(guardrails): update LIT-4226 UI settings tests for content filter pre_mcp_call support * fix(guardrails): use builtin generics in MCP scan annotations to satisfy strict-rule budget Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
|
yucheng-berri
|
69c5839cc0
|
fix(guardrails): filter Add-Guardrail mode dropdown per provider (#32712)
* fix(guardrails): filter Add-Guardrail mode dropdown per provider The GET /guardrails/ui/add_guardrail_settings endpoint returned every GuardrailEventHooks value in one flat supported_modes list, so the Admin UI rendered pre_mcp_call as a selectable Mode for every guardrail. Saving Content Filter or Tool Permission with pre_mcp_call then failed with a 400 because those guardrails' server-side supported_event_hooks list excludes it. Expose each guardrail's supported hooks as a get_supported_event_hooks classmethod on CustomGuardrail (mirrors the existing get_config_model pattern) and have the endpoint iterate guardrail_class_registry to build a supported_modes_by_provider map. The UI Mode dropdown filters by that map when the selected provider is known and falls back to the global list otherwise. __init__ now sources its own supported_event_hooks list from the classmethod so the two sides can't drift. Also register BedrockGuardrail, ToolPermissionGuardrail, lakera, lakera_v2, and presidio in guardrail_class_registry so they participate in the map (they were previously only in guardrail_initializer_registry and had no class-registry entry). Behavior change: guardrails that previously had no supported_event_hooks declared (aim, javelin, azure/text_moderation, cato_networks, crowdstrike_aidr, headroom, hiddenlayer, lasso, noma, onyx, prompt_security, qualifire, repelloai, zscaler_ai_guard, aporia_ai, lakera_ai, lakera_ai_v2, mcp_jwt_signer, model_armor, presidio) now validate the configured mode at instantiation. Existing configs where the mode was silently a no-op will fail at proxy startup with a clear validation error rather than running as a broken guardrail. Resolves LIT-4226 * fix(guardrails): add LITELLM_STRICT_GUARDRAIL_MODES escape hatch, preserve current mode in edit form Address Greptile P1 (startup break) and P2 (edit form UX): LITELLM_STRICT_GUARDRAIL_MODES defaults to true (raise on unsupported event_hook, unchanged behavior for the guardrails validated pre-PR). Setting it to false logs a warning and continues, giving deployments an opt-out while they fix configs that now surface as errors instead of silently no-op'ing. Regression test covers both modes. Edit form now surfaces the currently-saved mode even when it is not in the filtered per-provider list, so a legacy row (e.g. content_filter saved with pre_mcp_call before this fix) no longer disappears from the dropdown; the option renders with a 'not supported by <provider>' note so the user knows to pick another. * fix(guardrails): correct audited hook lists, prune stale modes on provider switch, clean form lint Audited every get_supported_event_hooks classmethod against the hooks each guardrail's own tests exercise and its handler methods. Five were too narrow and their tests caught it in CI: rubrik gains pre_call, presidio gains during_call and pre_mcp_call, prompt_security, onyx and qualifire gain during_call. The remaining classes match either their original __init__ declarations or their exercised modes exactly. Cursor review fixes: the Add form now drops selected modes the new provider does not support when the user switches providers, so a pre_mcp_call selection cannot ride along into a provider that rejects it at save; the edit form handles list-shaped stored modes instead of treating mode as always a string. Extracted shared toModeArray and getSupportedModesForProvider helpers into guardrail_info_helpers so both forms use one implementation, typed the remaining any usages in both forms, removed nested ternaries, and committed the ratcheted-down eslint metrics and pruned suppressions |
||
|
Yuneng Jiang
|
799a559871
|
fix(guardrails): show YAML-defined guardrails in the Guardrail Monitor
The /guardrails/usage/{overview,detail,logs} endpoints resolved guardrails only
from the litellm_guardrailstable Prisma table, so guardrails defined in
config.yaml (which live only in IN_MEMORY_GUARDRAIL_HANDLER) were invisible:
detail 404'd, overview omitted them or rendered them as Custom/Guardrail
orphans, and logs missed their logical-name alias.
Add config-owned accessors (list_config_guardrails, get_config_guardrail_by_id)
to the in-memory handler and use them in the usage endpoints, mirroring the
union/fallback already used by list_guardrails_v2 and get_guardrail_info. Also
preserve guardrail_info when storing a config guardrail (type/description were
dropped at initialize time) and read the Prisma-row / dict / LitellmParams
shapes uniformly.
Resolves LIT-2529
|
||
|
yucheng-berri
|
5cf269088c
|
fix(proxy): capture logging_obj before post_call_failure_hook pops it in ModifyResponseException streaming path (#32665)
* fix(guardrails/bedrock): honor disable_exception_on_block by raising ModifyResponseException The Bedrock-specific GuardrailInterventionNormalStringError predates the unified guardrails refactor and no proxy code path handles it, so a block with the flag set surfaced as an uncaught Exception -> HTTP 500 in pre_call mode and was silently discarded in during_call mode (model call proceeded in the parallel asyncio.gather; the block hook's data["mock_response"] mutation happened after route_request had already unpacked kwargs). Convert the block to ModifyResponseException at the raise site inside make_bedrock_api_request. That exception is the industry-standard proxy contract already caught in proxy_server, anthropic_endpoints, response_api _endpoints, and pass_through_endpoints; it turns into a 200 response with finish_reason=content_filter and the block message as content, which is exactly what the flag was documented to yield. Post-call blocks attach the LLM response to original_response so the synthetic reply reports the upstream call's real token usage instead of zero. Deletes the now-orphaned GuardrailInterventionNormalStringError class and the dead create_guardrail_blocked_response / mock_response plumbing in the Bedrock hooks; updates the existing tests that had locked in the buggy contract. Resolves LIT-4186 * chore(guardrails/bedrock): drop dead str branch in _update_messages_with_updated_bedrock_guardrail_response Follow-up to the disable_exception_on_block fix. That method used to receive either a BedrockGuardrailResponse or a plain string (the block message, when the flag was set). Now that a block always raises ModifyResponseException before this method runs, the string branch is unreachable; tighten the type to BedrockGuardrailResponse and delete the guard. * fix(guardrails/bedrock): streaming post_call block yields synthetic stream instead of surfacing as SSE 500 Regression from the LIT-4186 refactor: pre-refactor, the streaming post_call iterator caught GuardrailInterventionNormalStringError locally and replaced the assembled response with a synthetic content-filter message, then re-emitted it as chunks via MockResponseIterator. After the refactor the exception was re-raised as ModifyResponseException, which async_streaming_data_generator serializes as a proxy 500 error frame because the SSE response headers are already flushed by the time the block fires. Non-streaming paths still let ModifyResponseException propagate to the endpoint handler (which converts it into a 200). Streaming can't do that, so keep the local synthesis: on the exception, rebind the assembled response to a ModelResponse whose single choice carries the block message as content and finish_reason=content_filter, and let the downstream MockResponseIterator emit it as chunks. Same shape a non-streaming block produces. Adds a mapped-file regression test that mutation-kills the raise behavior and locks in the synthetic-stream contract. * fix(guardrails/bedrock): preserve upstream usage on streaming post_call block Non-streaming post_call blocks report the upstream LLM call's real token usage via ModifyResponseException.original_response, which the endpoint handler unwraps through _blocked_response_usage. Streaming post_call synthesizes its own ModelResponse locally (the exception can't escape the SSE generator), and previously left .usage unset, so the client saw accurate billing on non-streaming blocks and zero on streaming blocks -- silent revenue leak. Copy the assembled response's .usage onto the synthetic block response before yielding. Pre-refactor code had the same gap (create_guardrail_blocked_response never set usage); this is a net improvement, not a regression fix. * fix(proxy): capture logging_obj before post_call_failure_hook pops it in ModifyResponseException streaming path post_call_failure_hook removes litellm_logging_obj from request_data before iterating callbacks (it's not serialisable). The streaming branch of the ModifyResponseException handler read it from _data after that call, so it always received None and CustomStreamWrapper.__init__ crashed with AttributeError: NoneType has no attribute model_call_details. Capture it before the hook runs so the streaming path gets a valid object. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * test(proxy): add regression for streaming ModifyResponseException logging_obj capture Covers the bug where logging_obj was read from request_data after post_call_failure_hook had already popped it, causing CustomStreamWrapper to crash with AttributeError. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * test(proxy): drive real chat_completion in ModifyResponseException streaming logging_obj regression The original test inlined the fix pattern (capture before pop) in its own body rather than calling the actual chat_completion handler in proxy_server.py, so a revert of the fix left the test passing. Confirmed via mutation check: reverting the two-line source fix and re-running left the test green. Rewrite the test to drive chat_completion directly: - patch _read_request_body so chat_completion sees the seeded dict - patch ProxyBaseLLMRequestProcessing.base_process_llm_request to raise ModifyResponseException with the same request_data - patch proxy_logging_obj so post_call_failure_hook mutates the dict the way production does (pops litellm_logging_obj) - intercept CustomStreamWrapper.__init__ and assert logging_obj is the non-None object seeded in request_data Mutation-verified: reverting the source fix now surfaces the exact production crash inside CustomStreamWrapper's __init__ (AttributeError: NoneType has no attribute model_call_details) rather than a silently-passing test. Addresses Greptile P1 on PR #32665. --------- Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> |
||
|
yucheng-berri
|
6eed38bcfb
|
fix(guardrails/bedrock): honor disable_exception_on_block by raising ModifyResponseException (#32289)
* fix(guardrails/bedrock): honor disable_exception_on_block by raising ModifyResponseException The Bedrock-specific GuardrailInterventionNormalStringError predates the unified guardrails refactor and no proxy code path handles it, so a block with the flag set surfaced as an uncaught Exception -> HTTP 500 in pre_call mode and was silently discarded in during_call mode (model call proceeded in the parallel asyncio.gather; the block hook's data["mock_response"] mutation happened after route_request had already unpacked kwargs). Convert the block to ModifyResponseException at the raise site inside make_bedrock_api_request. That exception is the industry-standard proxy contract already caught in proxy_server, anthropic_endpoints, response_api _endpoints, and pass_through_endpoints; it turns into a 200 response with finish_reason=content_filter and the block message as content, which is exactly what the flag was documented to yield. Post-call blocks attach the LLM response to original_response so the synthetic reply reports the upstream call's real token usage instead of zero. Deletes the now-orphaned GuardrailInterventionNormalStringError class and the dead create_guardrail_blocked_response / mock_response plumbing in the Bedrock hooks; updates the existing tests that had locked in the buggy contract. Resolves LIT-4186 * chore(guardrails/bedrock): drop dead str branch in _update_messages_with_updated_bedrock_guardrail_response Follow-up to the disable_exception_on_block fix. That method used to receive either a BedrockGuardrailResponse or a plain string (the block message, when the flag was set). Now that a block always raises ModifyResponseException before this method runs, the string branch is unreachable; tighten the type to BedrockGuardrailResponse and delete the guard. * fix(guardrails/bedrock): streaming post_call block yields synthetic stream instead of surfacing as SSE 500 Regression from the LIT-4186 refactor: pre-refactor, the streaming post_call iterator caught GuardrailInterventionNormalStringError locally and replaced the assembled response with a synthetic content-filter message, then re-emitted it as chunks via MockResponseIterator. After the refactor the exception was re-raised as ModifyResponseException, which async_streaming_data_generator serializes as a proxy 500 error frame because the SSE response headers are already flushed by the time the block fires. Non-streaming paths still let ModifyResponseException propagate to the endpoint handler (which converts it into a 200). Streaming can't do that, so keep the local synthesis: on the exception, rebind the assembled response to a ModelResponse whose single choice carries the block message as content and finish_reason=content_filter, and let the downstream MockResponseIterator emit it as chunks. Same shape a non-streaming block produces. Adds a mapped-file regression test that mutation-kills the raise behavior and locks in the synthetic-stream contract. * fix(guardrails/bedrock): preserve upstream usage on streaming post_call block Non-streaming post_call blocks report the upstream LLM call's real token usage via ModifyResponseException.original_response, which the endpoint handler unwraps through _blocked_response_usage. Streaming post_call synthesizes its own ModelResponse locally (the exception can't escape the SSE generator), and previously left .usage unset, so the client saw accurate billing on non-streaming blocks and zero on streaming blocks -- silent revenue leak. Copy the assembled response's .usage onto the synthetic block response before yielding. Pre-refactor code had the same gap (create_guardrail_blocked_response never set usage); this is a net improvement, not a regression fix. |
||
|
yucheng-berri
|
e84a19acd5
|
fix(guardrails): walk Responses-API text taxonomy in shared content helpers (#32542)
* fix(guardrails): walk Responses-API text taxonomy in shared content helpers
Every guardrail sharing litellm/proxy/guardrails/_content_utils.py silently
drops all text on the /v1/responses path. AIM turns it into a loud 422 (
{"error":"No messages in the request"}); every other guardrail (Lakera v2,
Cato, Lasso, Repello, IBM, Azure Content Safety, enterprise secret
detection) scans an empty payload and lets the request through unscanned.
Three defects, all in _content_utils.py:
1. _iter_text_parts_in_content recognised only part.type == "text", but the
Responses API uses input_text (request) and output_text (assistant).
2. _coerce_input_to_messages gated on "every item has a role key"; any
Responses input list containing a function_call or function_call_output
item failed the check and was wrapped as one opaque blob.
3. build_inspection_messages forwarded any role through, including a bare
tool role missing tool_call_id, which validators like AIM's /fw/v1/analyze
reject with a schema error.
Fix walks the actual Responses item taxonomy (message, function_call,
function_call_output, bare content parts and strings), recognises
{text, input_text, output_text} everywhere, and coerces any role outside
{system, user, assistant} to user in the outbound inspection payload.
* style: ruff-format changed guardrail files
* test(guardrails): cover function_call_output string form; drop em-dash in new docstring
* fix(guardrails): map function_call_output straight to user role
Avoids ever materialising a schema-invalid bare tool message. The
downstream role-safety coercion in build_inspection_messages still
guards genuinely caller-supplied non-standard roles (developer,
function, custom values); add a regression test covering that path
so the coercion has real coverage after this simplification.
* test(guardrails): pin chat-completions tool-role coercion in build_inspection_messages
* docs(test): soften AIM-specific claims in LIT-4294 test docstrings
Ryan's review flagged that several test docstrings assert AIM's
/fw/v1/analyze validates + rejects specific schema violations. That
behavior is customer-reported in the LIT-4294 writeup, not directly
verified by us. Rephrase to attribute the AIM 422 to the customer's
writeup and describe the underlying constraint as the OpenAI chat
schema; any downstream API that validates against that schema rejects
the same shape.
* refactor(guardrails): move unsupported-role coercion into AIM only
The generic coercion in build_inspection_messages collapsed any role
outside {system, user, assistant} to user for every caller of the
helper. Combined with the pre-existing apply_redacted_messages_back
write-back behavior in Lakera/AIM/Cato, that turned a loud OpenAI 400
on chat-completions tool-message masking into a silent semantic
corruption of the outbound request (role tool with tool_call_id got
rewritten to bare role user, dropping the assistant + tool_calls
sibling).
AIM specifically requires the coercion because its /fw/v1/analyze
validates the payload against the OpenAI chat schema; other guardrails
either do not validate roles or do their own reconstruction. Move the
coercion to AimGuardrail._build_aim_inspection_messages so the shared
helper keeps caller roles intact and no new cross-guardrail role
corruption is introduced. The pre-existing apply_redacted_messages_back
structural flatten remains as separate follow-up work.
function_call_output items still synthesise role user in the shared
helper because they have no natural role field, which is a different
concern from coercing a caller-supplied role.
* refactor(guardrails): preserve role fidelity in shared _content_utils
Shared inspection helpers should extract text and preserve semantic
role signals; role coercion for third-party schema safety stays inside
the guardrail that needs it (AIM).
Three shared-helper changes:
- Bare content-part dicts (input_text/output_text) with an explicit role
keep it; only role-less parts default to user.
- Responses message items already had their role preserved; the
behavior is now covered by an explicit test.
- function_call_output items default to role tool (semantic equivalent
of the chat-completions tool message shape) instead of role user, so
Responses and chat completions produce symmetric inspection payloads.
A caller-supplied role on the item is still preserved.
AIM's schema-safe coercion in _build_aim_inspection_messages already
handles the resulting role tool: it collapses to user before the POST
to /fw/v1/analyze so AIM's OpenAI-schema validator does not reject the
bare tool message (no tool_call_id can survive the flatten). Added a
regression test in test_aim.py covering that path.
|
||
|
yucheng-berri
|
528fa380f5
|
fix(guardrails): forward grayswan scan id header (#32544)
* fix(guardrails): forward grayswan scan id header
* test(guardrails): cover grayswan scan id forwarding
* fix(guardrails): prevent overwriting existing metadata headers when extracting scan id
* test(guardrails): cover header merging logic
* chore(guardrails): fix formatting
* test(guardrails): enforce case preservation
* chore(guardrails): corrected grayswan type annotations
* fix(guardrails): sanitized grayswan header metadata
* test(guardrails): covered grayswan logging headers
* fix(guardrails): guard grayswan header lookup against None and drop dead comment
- Fall back to {} when proxy_server_request is explicitly None so
request_data.get(...).get('headers') never raises AttributeError.
- Remove the commented-out user_api_key_auth pop; it was inert and
greptile called it out as ambiguous.
---------
Co-authored-by: Theodore Drzewinski <93957989+tediferJones@users.noreply.github.com>
|
||
|
yucheng-berri
|
f4623a1325
|
fix(model_armor): scan MCP tool calls for pre_mcp_call / during_mcp_call modes (#32296)
ModelArmorGuardrail.async_pre_call_hook and async_moderation_hook hardcoded their inner should_run_guardrail event type to pre_call / during_call. The central dispatcher already remaps call_mcp_tool -> pre_mcp_call/during_mcp_call and passes the outer gate, but Model Armor's redundant inner gate then rejected MCP calls for a guardrail configured with mode pre_mcp_call/during_mcp_call, so tool-call content was silently skipped. Remap call_mcp_tool -> pre_mcp_call/during_mcp_call in both hooks, matching the existing behavior of the noma and cisco guardrails. Adds regression tests covering both hooks (scan runs on MCP calls, still skipped for chat traffic). Generated with AI Co-Authored-By: Claude Code Co-authored-by: eugene-yao-zocdoc <eugene.yao@zocdoc.com> |
||
|
ryan-crabbe-berri
|
4428c1b681
|
fix(guardrails): send only new messages since last assistant turn to CrowdStrike AIDR (#31974)
Previously, every guardrail request forwarded the full conversation history to CrowdStrike AIDR. In a multi-turn conversation this means every prior message gets re-scanned on every new call, even though those messages were already evaluated in earlier turns. CrowdStrike AIDR internally has a conversation boundary optimization in place for just this scenario (ref. <https://aidr-docs.crowdstrike.com/docs/aidr/apis#messages-array-optional---array-of-message-objects-containing-a-conversation-segment-with-the-ai-system>). However, it is nevertheless wasteful to send so much data to the API when only a subset of it will be processed. It also risks hitting the documented 1 MiB request size limit. So now we filter down to system messages plus either the messages after the last assistant turn, or the last assistant message itself when that is what is being guarded. We also preserve the original, full message history within the guardrail in order to stitch back any transformations. Co-authored-by: Kenan Yildirim <kenan@kenany.me> |
||
|
Krrish Dholakia
|
01dfbf7ebb |
fix(guardrails): address review comments on headroom fail_open
- Prevent fail-open from registering user-supplied hashes as valid for CCR retrieval; _call_compress now returns (messages, compressed_ok) so apply_guardrail skips hash extraction and tool injection when compression did not succeed - Remove Optional wrapper from HeadroomGuardrailConfigModel.unreachable_fallback to match BaseLitellmParams typing - Add fail_open tests for non-JSON response, missing messages key, and empty message list paths - Add regression test verifying fail_open does not authorize attacker-planted hashes - Regenerate dashboard API types Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|
Cursor Agent
|
53d2331c70
|
fix: catch litellm.Timeout in HeadroomGuardrail to support fail_open on timeouts
async_handler.post catches httpx.TimeoutException and re-raises it as litellm.Timeout (a subclass of openai.APITimeoutError). The except blocks in _call_compress and _call_retrieve only listed httpx exception types, so litellm.Timeout propagated uncaught and bypassed the unreachable_fallback=fail_open path. Add litellm.Timeout to both except clauses and add regression tests for the fail_closed and fail_open timeout paths. |
||
|
Krrish Dholakia
|
00dffcd075 |
fix(guardrails): catch httpx.HTTPStatusError in headroom compress call
litellm's async httpx client already calls raise_for_status() internally, so a non-2xx /v1/compress response surfaced as an uncaught httpx.HTTPStatusError instead of going through the guardrail's status_code check. Caught live by running the guardrail against a mock headroom endpoint that returns 500: unreachable_fallback=fail_open silently failed to forward the request until this fix. |
||
|
Krrish Dholakia
|
659127bd0d |
feat(guardrails): add unreachable_fallback fail-open option to headroom guardrail
Reuses the existing unreachable_fallback flag (already implemented by generic_guardrail_api, akto, vigil_guard, repelloai) so headroom compression failures can forward the request uncompressed instead of blocking it with a 502. |
||
|
Sameer Kankute
|
321345d4c8
|
feat: litellm oss staging (#31935)
* fix(prometheus): bound per-request budget metric emission with a timeout (#31632) * fix(prometheus): bound per-request budget metric emission with a timeout Wrap the per-request budget-metric gather in asyncio.wait_for so a slow Redis or DB lookup cannot consume the whole LoggingWorker watchdog and get the success-logging event cancelled. On timeout the emission is skipped in isolation; budget gauges are still refreshed by the periodic cron. The timeout is configurable via PROMETHEUS_BUDGET_METRICS_PER_REQUEST_TIMEOUT and defaults to 5.0 seconds, falling back to the default on an invalid value instead of raising * fix(prometheus): reject non-finite and non-positive budget-metrics timeout env float() accepts 0, negatives, nan and inf, which bypass the fallback: a value <= 0 makes asyncio.wait_for time out immediately and skip every per-request emission, and inf reintroduces the unbounded wait the timeout was meant to bound. Validate the parsed value is finite and greater than zero before using it, otherwise fall back to the default * fix: report the blocked LLM response's real token usage (#31217) When a guardrail blocks a post-call response, the synthetic violation response reported hard-coded zero usage, discarding the token usage the upstream call had already consumed. Fix the root cause rather than re-counting tokens: - Add an optional `original_response` field to ModifyResponseException. - The unified guardrail's post-call success hook attaches the blocked LLM response to the exception. - The /v1/messages and OpenAI-format (/v1/chat/completions, /v1/completions) block handlers report `original_response.usage` directly. Pre-call blocks never invoked the LLM, so usage is zero. Mock-based tests cover the helper (returns original usage / zero), the success hook attaching original_response, and the endpoint reporting it end-to-end. Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(guardrails): buffer + cleanly terminate streamed responses on block (#31389) Streaming moderation improvements for the unified guardrail post-call streaming iterator hook: - streaming_buffer_until_moderated: withhold all chunks until end-of-stream moderation passes, then release the original response (clean) or only the block message (blocked) -- the original content is never delivered on a block. Snapshot chunks with a shallow list() copy (end-of-stream builds a separate assembled response; chunks aren't mutated in place). - Clean Anthropic SSE on block: synthesize a well-formed termination sequence instead of a bare data: {"error": ...} blob that truncates the stream. Provider-specific synthesis lives in AnthropicMessagesHandler via build_block_sse_chunks (format-agnostic routing stays in the hook). - Mid-stream blocks continue the in-progress message (close open content block, append block message, terminate) rather than emitting a second message_start, which clients reject. Standalone envelope only when no chunks were sent (buffered path). - ModifyResponseException imported under TYPE_CHECKING + locally at runtime to avoid a module-level cyclic import. Adds regression tests for buffering (content withheld on block) and mid-stream continuation (single message_start). Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: report real usage on streaming blocks, disable buffered mode for content-rewriting guardrails - _standalone_block_chunks and _block_continuation_chunks now read real token usage from ModifyResponseException.original_response instead of hardcoding zero, matching the non-streaming _blocked_response_usage path. Shared helper moved to guardrail_translation/utils.py. - streaming_buffer_until_moderated is now forced off when the guardrail has mask_response_content=True, since buffered replay releases the withheld original chunks verbatim -- unsafe for a guardrail that rewrites content (e.g. PII masking). - Fix inverted streaming-flag precedence comment. * style: ruff format after greploop fixes * fix: handle Anthropic streaming guardrail blocks * fix(responses): check terminal event type for streaming guardrail end-of-stream detection _check_streaming_has_ended assumed responses_so_far held ModelResponse objects with .choices, but for the Responses API the accumulated chunks are raw SSE event dicts, causing an AttributeError on every call * fix: preserve Anthropic blocked stream usage --------- Co-authored-by: FERNANDO IZAR <fizar@me.com> Co-authored-by: Joseph Barker <156112794+seph-barker@users.noreply.github.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> |
||
|
Krrish Dholakia
|
50b936c75e
|
feat(guardrails/headroom): add CCR (compress-cache-retrieve) via agentic loop (#31681)
* feat(guardrails/headroom): add CCR (compress-cache-retrieve) support via agentic loop
When Headroom's /v1/compress returns messages containing hash markers
(hash=[a-f0-9]{24}), inject a headroom_retrieve tool into the request.
When the LLM calls that tool, intercept via async_should_run_agentic_loop
and async_build_agentic_loop_plan, call GET /v1/retrieve/{hash} on the
Headroom sidecar, and replay the LLM with the original content as a tool
result -- all transparent to the caller.
* style: run ruff format on headroom guardrail and tests
* fix(guardrails/headroom): detect headroom_retrieve calls in both OpenAI and Anthropic response formats
* test(guardrails/headroom): add test for Anthropic content block format detection in CCR loop
* ci: trigger CI checks
* fix(guardrails/headroom): replace List/Dict with list/dict to fix UP006 ruff violations
* fix(guardrails/headroom): replace except Exception with except ValueError to fix BLE001
* fix(guardrails/headroom): add Responses API output format detection for CCR tool calls
* refactor(guardrails/headroom): extract format-specific helpers to fix C901 complexity
* fix(guardrails/headroom): scope CCR retrieval to hashes produced by current request
Previously any LLM-supplied hash in a headroom_retrieve tool call was
forwarded to the Headroom retrieve API, letting a crafted tool call
fetch arbitrary cached content. Validate the hash against the set
produced by compressing the current request's messages before calling
retrieve.
* fix(guardrails/headroom): track issued hashes server-side, fix Responses API replay shape
Hash validation now also checks an in-memory cache of hashes actually
returned by /v1/compress, not just whether the hash text appears
somewhere in the request's messages. The message-text check alone is
forgeable: an attacker can plant a hash-shaped string in their own
prompt and have it treated as valid.
Responses API follow-up now emits function_call/function_call_output
items keyed by call_id instead of chat-style assistant/tool messages,
since the Responses API does not accept the latter as input. Also
fixes call_id/id field priority when extracting tool calls from
Responses API output, since call_id (not id) is what must match
between the function_call and its output.
* fix(guardrails/headroom): drop redundant quoted type annotations
UP037 flags quotes on annotations that are already lazily evaluated
via `from __future__ import annotations`.
* test(guardrails/headroom): add missing pytest.mark.asyncio decorators
Functional under asyncio_mode=auto, but every other async test in the
file has the decorator for consistency.
* fix(guardrails/headroom): scope CCR hashes per call_id, fix Anthropic replay shape
Two real gaps found in review:
1. The instance-wide issued-hash cache combined with a message-text
check did not actually scope retrieval to the request that produced
the hash. A hash issued for request A stays in the shared cache
until TTL expiry, and the message-text check is satisfied by any
request whose own messages happen to echo that hash string. Request
B could plant A's hash in its own prompt and retrieve A's content.
Fixed by keying the issued-hash cache by litellm_call_id, matching
the pattern already used in compression_interception: a hash is
only honored when it was issued under the exact call_id resolving
for the current request.
2. The Anthropic Messages replay path fell through to the chat-style
assistant/tool-message builder, which Anthropic does not accept.
Anthropic requires the tool_use block echoed in an assistant message
paired with a tool_result block in a user message, keyed by
tool_use_id. Added a dedicated branch for this shape.
* docs: note proactive API-fragmentation helper convention
Add a bullet to the coding-conventions list: look for or add a shared
helper when logic branches on API surface (chat completions vs
Anthropic Messages vs Responses API), instead of duplicating
format-detection per module.
* fix(guardrails/headroom): fix Anthropic tool-shape detection, extract shared cross-API tool util
Live e2e testing against the real Anthropic API surfaced two bugs the
mocked unit tests couldn't catch because they used MagicMock responses
instead of realistic response shapes:
1. has_headroom_retrieve_tool only recognized OpenAI-shaped function
tools. By the time an Anthropic Messages response reaches the
agentic-loop gate, the tool this guardrail injected has already been
transformed into Anthropic's native shape (type: "custom", top-level
"name"), so the gate never fired for real Anthropic requests.
2. AnthropicMessagesResponse is a TypedDict, so real responses are
plain dicts at runtime, not objects with attribute access. The
extractors and format detectors used bare getattr(), which silently
returns nothing for dict responses instead of reading the actual
key.
Extracted the cross-API-surface tool-call extraction and tool-presence
check into litellm/litellm_core_utils/prompt_templates/factory.py
(get_tool_calls_from_response, has_tool_with_name) so this format
fragmentation is handled in one place instead of being duplicated
per-guardrail, and reused the existing repair-aware
parse_tool_call_arguments from common_utils instead of a naive
json.loads. headroom.py now delegates to these shared helpers.
Confirmed live against the real Anthropic API: the retrieve loop now
fires and successfully retrieves the correct hash's content through
the full compress -> tool-call -> retrieve -> replay round-trip.
* fix(guardrails/headroom): fix ruff-strict UP006/I001 budget violations
Use lowercase list/dict generics in the new factory.py tool-call
helpers instead of typing.List/Dict, drop the now-unused Tuple import
in headroom.py, and reorder the new factory import ahead of the
llms.custom_httpx import to satisfy import sorting.
* fix(guardrails/headroom): match Anthropic tools without a type field
Anthropic's documented client tool format is just name + input_schema;
type: "custom" is only one possible value, not a requirement. Match
any non-OpenAI-shaped tool on its top-level name instead of requiring
type == "custom".
|
||
|
tin-berri
|
a0b26d2c3c
|
Revert "fix(presidio): stream SSE output incrementally instead of buffering t…" (#31764)
This reverts commit
|
||
|
Yassin Kortam
|
94936a3922
|
fix(presidio): stream SSE output incrementally instead of buffering the whole response (#31503)
The Presidio streaming post-call hooks (_stream_apply_output_masking for apply_to_output and _stream_pii_unmasking for output_parse_pii) collected every upstream chunk, reassembled the full completion with stream_chunk_builder at end-of-stream, ran Presidio over it, then emitted one reconstructed SSE chunk. Time-to-first-token collapsed to the total generation time and token-by-token streaming was lost whenever Presidio output handling was enabled. With the default presidio_filter_scope both, an apply_to_output masking instance is always created, so even the unmask configuration buffered the stream. Both paths now transform and forward chunks as they arrive. The unmask path replaces placeholder tokens per chunk, holding back only the trailing run that could still grow into a token so a placeholder split across SSE chunks (<PER + SON_1>) is still rewritten atomically. The mask path emits a prefix only when masking it in isolation matches the corresponding prefix of masking the whole buffer, with a lookahead margin still buffered past the cut, so an entity straddling the cut is detected and held until complete; past _PRESIDIO_STREAM_MAX_BUFFER the run is bounded without splitting an entity. Tool-call and legacy function-call argument fragments are accumulated per choice and transformed once the choice closes, content is buffered independently per choice index for correct n>1 streaming, raw Anthropic SSE bytes and /v1/responses events pass through with any held content flushed first so events never reorder, and a masking error redacts only the affected chunk (fail closed, keeping finish_reason) while the stream continues. Resolves LIT-3222 |
||
|
yucheng-berri
|
1815636e1c
|
feat(guardrails): expose streaming knobs on generic_guardrail_api (#31730)
* feat(guardrails): expose streaming knobs on generic_guardrail_api Wire streaming_end_of_stream_only and streaming_sampling_rate through optional params, initialize_guardrail, and get_config_model so the generic guardrail API participates in UnifiedLLMGuardrails streaming checks with configurable cadence and end-of-stream-only mode. * fix(guardrails): use builtin type[] in get_config_model return Avoids a new UP006 violation that tripped the ruff strict-rule budget gate on the PR lint job. * fix(guardrails): default optional streaming knobs to None Non-None Pydantic defaults on GenericGuardrailAPIOptionalParams made _get_config_value treat unset nested fields as explicit values, which shadowed top-level litellm_params streaming flags whenever any other optional_params key was present. Real defaults stay in the constructor. * fix(guardrails): address review nits on generic_guardrail_api streaming Validate streaming_sampling_rate >= 1 in the constructor and Pydantic optional_params (ge=1), and add /v1/responses streaming coverage through the unified post-call hook so Responses API usage is exercised alongside chat completions. * fix(guardrails): read nested streaming config from dict optional_params Guardrail API/UI delivers optional_params as a plain dict, so getattr was silently ignoring streaming_sampling_rate and streaming_end_of_stream_only. Handle both dict and model shapes in _get_config_value with regression tests. * fix(guardrails): clear ruff findings in generic_guardrail_api tests/types * style(guardrails): ruff format generic_guardrail_api modules --------- Co-authored-by: Marton Schneider <marton@schneider.co.nl> |
||
|
yucheng-berri
|
10849c880b
|
fix(guardrails): scan file and document attachments with Model Armor (#31655)
The Model Armor guardrail only sent text extracted from user messages to sanitizeUserPrompt, so harmful content inside attached PDFs, Office docs, and CSVs reached the LLM unscanned. A file-only message had no extractable text, so the pre-call and moderation hooks returned early and the document was never submitted to Model Armor at all. Wire inline document/file scanning into async_pre_call_hook and async_moderation_hook. extract_file_attachments walks message content blocks (OpenAI type:file file_data and Anthropic type:document source), decodes the base64 bytes, maps the MIME type to a Model Armor byteDataType, and skips remote URLs, bare file_id references, oversize files past the 4 MB limit, and unsupported types. Each attachment is sent through the byte API and a MATCH_FOUND blocks the request before it reaches the LLM. Resolves LIT-4084 |
||
|
Krrish Dholakia
|
99b1a323c1
|
feat(guardrails): add headroom guardrail for message compression (#31407)
* feat(guardrails): add headroom guardrail for message compression Adds a headroom guardrail that compresses request messages via POST /v1/compress before they reach the LLM. The guardrail implements apply_guardrail so it runs on the unified guardrail path; it receives pre-built structured_messages (OpenAI format) from the translation layer, calls the headroom compression service, and returns the compressed messages as structured_messages. Set x-headroom-bypass: true on the request to skip compression. Also adds structured_messages write-back support to the OpenAI and Anthropic translation handlers: when apply_guardrail returns structured_messages, those are written to data["messages"] directly (OpenAI) or reverse-translated via anthropic_messages_pt (Anthropic) instead of falling through to the existing text-patch path. This is a prerequisite for any guardrail that needs to replace the full message list rather than patch individual text spans. * fix(guardrails/headroom): add @log_guardrail_information to populate guardrail_information in spend logs * style: fix ruff format violations * fix(lint): replace deprecated typing aliases with builtin generics (UP006/UP037) * fix(guardrails): only write back structured_messages when guardrail actually changed them * fix(guardrails/headroom): raise 502 when compression returns empty message list * fix(guardrails/headroom): catch transport errors and fix stale debug log * fix(guardrails/anthropic): strip system messages before anthropic_messages_pt reverse-translation * fix(guardrails/anthropic): strip cache_control from thinking blocks after write-back * debug(headroom): add INFO logging to trace guardrail execution * debug(headroom): use print() for immediate visibility * debug(headroom): print request_data keys to diagnose metadata dict mismatch * fix(guardrails/anthropic): propagate guardrail info to logging_obj.metadata for spend log * fix: use model_call_details litellm_params metadata on Logging object * fix(guardrails/anthropic): write guardrail info to litellm_params attr not model_call_details copy * fix: read slg_info from litellm_metadata when metadata key absent * fix: write slg_info to both litellm_params attr and model_call_details copy * chore: remove debug prints; fix now verified end-to-end * refactor(guardrails): move spend-log sync to shared helper in custom_guardrail.py - Add _sync_guardrail_info_to_logging_obj in custom_guardrail.py; call it from both async and sync wrappers in @log_guardrail_information, fixing guardrail_information=null in spend logs for all passthrough routes (/v1/messages, /v1/responses, etc.) in one place - Remove the 35-line inline sync block from the anthropic translation handler - Wrap response.json() in try/except in headroom.py to 502 on HTML/truncated responses - Drop redundant headers.get(BYPASS_HEADER.lower()) — header key already lowercase - Add regression tests for _sync_guardrail_info_to_logging_obj * fix(lint): reduce _sync_guardrail_info_to_logging_obj complexity below C901 threshold * fix(lint): simplify _sync_guardrail_info_to_logging_obj to reduce McCabe complexity * fix(lint): extract _append_slg_to_litellm_params to reduce McCabe complexity * fix(lint): extract _write_back_structured_messages to reduce process_input_messages complexity |
||
|
yucheng-berri
|
e99151bb95
|
feat(guardrails): make the Generic Guardrail resilient to built-in tools and errors (adopted from #31286) (#31461)
* fix(guardrails): stop Generic Guardrail API 500 on built-in tools
Requests carrying built-in tools (code_interpreter, file_search, ...) crashed
the Generic Guardrail with a 500. GenericGuardrailAPIRequest.tools validated
each tool against ChatCompletionToolParam, whose base TypedDict requires a
function block, so a tool like {"type": "code_interpreter"} raised a Pydantic
ValidationError before the request was ever sent.
Type the field with a permissive GuardrailToolParam model (type required,
extra=allow) so built-in tools validate and their config is forwarded to the
guardrail intact instead of being stripped.
* feat(guardrails): add complete fail-open (fail_on_error) to Generic Guardrail
The Generic Guardrail already honored unreachable_fallback, which fails open
only on network-unreachable errors. This wires up the existing generic
fail_on_error config (so far implemented only by Model Armor) so that
fail_on_error=false degrades any guardrail error to a critical-log warning and
lets the request proceed as if the guardrail were absent.
Only a valid guardrail response can act: a parsed BLOCKED decision still raises,
while endpoint errors, malformed responses, and internal serialization or
validation errors all fall through when fail_on_error=false. To cover that last
class, the request construction now runs inside the protected block, so the kind
of validation error that previously surfaced as a 500 is caught here too.
Defaults to true (fail closed), matching today's behavior; turning it off is an
explicit availability-over-security choice and is logged at critical level on
every bypass.
* test(guardrails): cover fail_on_error on the response path
The existing fail_on_error tests all drive the request path. Add response-path
(input_type=response) coverage: an endpoint error proceeds unchanged under
fail_on_error=false, and a valid BLOCKED decision still raises. Guards against a
future regression that special-cases input_type in the error handling.
* style(guardrails): black-format the fail-open guard expression
CI runs black (line-length 88) over litellm/; the unreachable_fail_open
assignment exceeded it. Wrap it to satisfy the formatter.
* fix(guardrails): validate tools into GuardrailToolParam at the call site
Changing the request field to List[GuardrailToolParam] left the construction
passing List[ChatCompletionToolParam] (list is invariant), which tripped the
basedpyright reportArgumentType budget gate. Validate each tool explicitly,
which is what Pydantic did implicitly, so the types line up with no Any or
suppression and the serialized payload is unchanged.
* fix(guardrails): make fail-open log message accurate for non-network errors
The fail-open path is now shared by fail_on_error, so it fires for any guardrail
error, not just unreachability. The log said 'unreachable' even for an HTTP 400
or a malformed response; reword to 'error' (the status code and exception are
already logged). Addresses the Greptile review's only finding.
* fix(guardrails): align GenericGuardrailAPIResponse.tools with GuardrailToolParam
Greptile flagged that the request side moved to GuardrailToolParam but the
response side still annotated tools as List[ChatCompletionToolParam], which
mandates a function block and contradicts the new built-in-tools support.
Update the response annotation (and the now-unused import) so the two sides
agree. Runtime is unchanged; from_dict stores the raw dicts and the only
consumer assigns through to GenericGuardrailAPIInputs without inspecting
the elements.
---------
Co-authored-by: Itay Ovadia <itay@sun.security>
|
||
|
Sameer Kankute
|
4c25b7a13d
|
chore: litellm oss staging (#30745)
* fix(proxy): bump health-check max_tokens default to 16 for GPT-5 compatibility (#30708) OpenAI GPT-5 models require max_completion_tokens >= 16. Health checks were using 5 (proxy/health_check.py) and 10 (health_check_helpers.py), causing failures on GPT-5 models. Fixes #23836 * fix: increase health check max_tokens from 5 to 16 (#23836) (#26610) GPT-5 models enforce a minimum of 16 for max_output_tokens. The current default of 5 still causes health checks to fail for these models. Bump the non-wildcard default to 16 — the smallest value that satisfies all known provider minimums while keeping health checks lightweight. Also tightens the wildcard test assertion from a weak disjunctive check to strict key-absence. Co-authored-by: Sameer Kankute <sameer@berri.ai> * fix: ensure checks show gemini-3-flash-preview supports responseJsonS… (#30696) * fix: ensure checks show gemini-3-flash-preview supports responseJsonSchema. * fix: remove async keyword from test. * fix: make Bedrock Mantle Responses routing data-driven per model (#30700) * Make Bedrock Mantle Responses routing data-driven per model Route Bedrock Mantle models to the native Responses API based on each model's price-map capability signal instead of a hardcoded model-name heuristic, and derive the OpenAI-compatible base path segment per model. Responses dispatch now selects the native config when the model advertises responses support (/v1/responses in supported_endpoints, or mode=responses), both overridable via register_model and proxy model_info. This enables native Responses for gpt-oss-120b/20b and the gemma-4 family while keeping chat-only models (gpt-oss safeguard, nvidia, mistral, ...) on the existing chat-completions emulation. Capability is per-model, so gpt-oss-120b routes natively while gpt-oss-safeguard-120b does not despite sharing the gpt-oss substring. The wire path is a separate concern, driven by the existing use_openai_responses_path flag rather than a model-name match: gpt-5.x and gemma-4-* on /openai/v1, everything else (incl. gpt-oss) on /v1. The chat config now derives its base from the same flag, fixing gemma-4 chat-completions requests that previously went to /v1 instead of /openai/v1. Cost maps: add supported_endpoints to the gpt-oss entries (responses for the non-safeguard variants, chat-only for safeguard) and supported_endpoints + use_openai_responses_path to all three gemma-4 entries. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * Address review: move capability helper into bedrock_mantle package Move the Responses capability check out of utils.py into litellm/llms/bedrock_mantle/common_utils.py as mantle_supports_responses, alongside its companion wire-path helper mantle_base_segment. Both are now pure functions of (model, model_cost): the price-map mode/supported_endpoints read replaces the get_model_info call, so the rules are unit-testable without patching global state and the Bedrock Mantle package is self-contained. Use str | None instead of Optional[str] on the new signatures to satisfy the ruff UP045 strict-rule gate. Add direct unit tests for both helpers. Fix test_register_model_restore_undoes_existing_key_overwrite: gpt-oss-120b now legitimately supports Responses, so it can no longer be the "None after restore" vehicle; use the chat-only safeguard variant, which isolates the register/restore effect from the model's own capability. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: Sameer Kankute <sameer@berri.ai> * fix(proxy): fail fast on non-PostgreSQL DATABASE_URL instead of hanging on startup (#30366) * 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(dashscope): treat an explicit 0.0 tier cost as a real price, not missing (#30653) The tiered cost calculator resolved a tier's per-token cost with `tier.get(cost_key) or tier.get(fallback_cost_key, 0)`. Because `or` short-circuits on any falsy value, a tier that legitimately prices a component at 0.0 (e.g. a free-cache-read tier with cache_read_input_token_cost: 0.0, or a free-reasoning tier) is treated as missing and silently billed at the full fallback rate (input_cost_per_token / output_cost_per_token). The flat-pricing path in the same module already handles this correctly with an `is None` guard. Resolve tier costs through a small helper that mirrors it, so 0.0 is honored at both the in-range and overflow sites. No shipped model currently has a 0.0 tier cost, so this is a latent defect; the fix makes the tiered path consistent with the flat path and prevents over-charging the first time such a tier appears. Adds unit tests covering the in-range and overflow paths, and drops an unused import flagged by ruff in the touched test file. * feat(proxy): show session-aggregate cost and duration in request logs (#25708) (#30507) * fix(anthropic): don't leak tool 'type' into OpenAI function parameters schema (#30618) In the messages->chat/completions bridge, translate_anthropic_tools_to_openai merged every non-mapped tool key into the function parameters dict. The Anthropic tool 'type' (e.g. 'custom') thus overwrote parameters.type ('object' -> 'custom'), and providers reject it ('custom' is not a valid JSON-Schema type). Exclude 'type' from the passthrough. Fixes #30557. * fix(proxy): stop IAM-refresh engine restart from cascading reconnects (#29176) (#30183) An RDS IAM token refresh recreates the Prisma client, which SIGKILLs the running query-engine and spawns a new one. That planned kill was indistinguishable from a crash, and three reconnect paths used two uncoordinated locks, so a single refresh triggered a cascade of engine kill/respawn cycles: 1. `_safe_refresh_token` (holds `_reconnection_lock`) -> recreate -> kill old engine, spawn new one. 2. The engine-death watcher sees that kill, assumes a crash, and calls `attempt_db_reconnect(force=True)` (a different lock, `_db_reconnect_lock`) -> recreate again -> kills the fresh engine. 3. In-flight queries failing during the swap are classified as transport errors and trigger their own `attempt_db_reconnect` -> recreate again. Fix coordinates planned restarts across the wrapper and the watcher: - PrismaWrapper records the old engine PID in `_expected_engine_deaths` before killing it; all four watcher death-detectors (waitpid thread, pidfd, already-dead probe, os.kill poll) consume that PID and skip the reconnect instead of treating it as a crash. - `recreate_prisma_client` now serializes through `_reconnection_lock` and bumps a monotonic `_engine_generation`. Callers pass `expected_generation` as an optimistic-lock token, so racing/cascading recreates collapse into a single restart (losers no-op). This closes the two-lock gap. - The direct reconnect path probes the writer with SELECT 1 before recreating; a healthy connection (e.g. engine already replaced by a refresh) skips the recreate entirely. - `_safe_refresh_token` coalesces: it skips when the current token still has more than the refresh buffer of runway, so stacked triggers (proactive loop + __getattr__ fallback) don't each restart the engine. An `on_engine_replaced` hook re-arms the watcher on the new PID. RoutingPrismaWrapper forwards `expected_generation` and skips recreating the reader when the writer recreate was skipped. * feat(bedrock): support file content retrieval for batch output files (#30595) Implements transform_file_content_request and transform_file_content_response in BedrockFilesConfig so GET /v1/files/{id}/content works for Bedrock batch files. The request transform resolves the file id (direct s3:// URI or base64 unified id) to its S3 object, validates bucket and key prefix against the server-configured bucket, and SigV4-signs an S3 GetObject using the same credential and region resolution as the existing upload path. The credential and region params are validated into a typed model at the boundary, so the only untyped values left are the botocore signing primitives. Also fixes the proxy managed-files path: CredentialLiteLLMParams now carries s3_bucket_name (previously dropped when building deployment credentials) and the managed-files hook passes the deployment credential snapshot when routing afile_content, so unified-id content retrieval works with per-model bucket config instead of only the AWS_S3_BUCKET_NAME env var. Preserves managed-file access control: the proxy file-content endpoint now rejects raw cloud-storage ids (s3://, gs://), which would otherwise skip the owner/team check that only runs for unified ids and let a caller read another tenant's batch output by its object key. Managed outputs are reachable only through their unified file id. The afile_content "not found" error now reports the caller's unified id rather than the resolved internal S3 URI. Fixes #16186, #15563 * fix(oci): make Cohere {{trace}} judges work (tool param types + agentic tool-calling continuation) (#30646) * fix(oci): map Cohere tool array/object params to lowercase builtins OCI's Cohere backend returns HTTP 500 on a tool parameter typed as a bare "List", which is what OCI_JSON_TO_PYTHON_TYPES produced for JSON-schema arrays. MLflow {{trace}} judges trip this: their tools (get_root_span, get_span) take an attributes_to_fetch array. The lowercase builtins list/dict are accepted; only the bare "List" 500s ("Dict" happens to be tolerated, but both are lowercased for consistency). Verified live against us-chicago-1 (cohere.command-a-03-2025 and command-latest). Adds a unit regression on the transformed parameterDefinitions plus a gated integration test exercising an array-param tool end to end. * fix(oci): make Cohere agentic tool-calling continuation work Two bugs broke the OCI Cohere tool-calling loop that MLflow {{trace}} judges drive once a tool has been executed and its result is fed back. Request side: litellm pulled the last user message into the top-level `message` and emitted the tool result as a TOOL entry in chatHistory. OCI rejects that ("cannot specify message if the last entry in chat history contains tool results"), and an empty message alone is rejected too ("message must be at least 1 token long or tool results must be specified"). OCI carries the current turn's results in a dedicated top-level `toolResults` field. The Cohere transform now sends an empty message, keeps the user turn in chatHistory, and puts the results in `toolResults`, matching the langchain-oracle reference. Tool results are no longer represented as chatHistory entries. Response side: tool-grounded answers come back with citations carrying `documentIds` (camelCase) and no `document_ids`, which made the required `CohereCitation.document_ids` field fail validation and sink the whole response parse. Those citations are never surfaced, so the field (and CohereSearchQuery's generation_id) is now optional. Verified live against us-chicago-1 (cohere.command-a-03-2025 and command-latest), single and multi-round tool loops. Adds unit regressions on the transformed request shape and on citation parsing, plus gated integration tests for the continuation. * feat: integrate Repelloai Argus guardrail (#30673) * feat(guardrails): add RepelloAI Argus guardrail integration (#1) * feat(guardrails): add RepelloAI Argus guardrail integration Add a new guardrail hook backed by RepelloAI Argus, with dashboard-managed asset policies enforced via an asset_id and X-API-Key auth. * fix(guardrails): harden RepelloAI Argus guardrail - scan streaming responses on output (was bypassing the guardrail) - log blocked verdicts as guardrail_intervened instead of success - treat auth/config errors (401/403/404/422) as misconfiguration that always blocks, not a fail-open-able unreachable error - default unreachable_fallback to fail_closed and read it directly; block on unknown/malformed verdicts so an API change can't silently disable enforcement - type unreachable_fallback as a Literal, drop the duplicate config model, expose unreachable_fallback in the config schema, and stop leaking the raw provider response / exception strings to the client * fix(guardrails): address RepelloAI Argus review feedback - support ARGUS_API_KEY (with REPELLOAI_API_KEY fallback) - make asset_id required in the config model - normalize unreachable_fallback so only fail_open opens; block on 400 misconfig - correct the shared unreachable_fallback field description * docs(guardrails): add RepelloAI Argus docs page and dashboard listing - add docs page covering config, env vars, modes, verdicts, failure semantics - list RepelloAI Argus in the Guardrail Garden with provider/logo mappings - add a regression test for the provider logo and display-name resolution * fix(guardrails): keep RepelloAI asset_id optional in config model A required asset_id leaked onto the shared LitellmParams (which inherits RepelloAIGuardrailConfigModel), breaking validation for every other guardrail. Keep it optional like sibling models; the guardrail __init__ still raises when asset_id is missing, which is the real enforcement. * Add comment for last user turn scanning * feat(guardrails): harden repelloai scanning * feat(guardrails): expand repelloai scanning to include tool definitions Add extraction of tool definitions and tool call arguments to the RepelloAI guardrail scanning. Improves detection coverage by including function schemas and parameters in the prompt sent to the guardrail service. Also captures detailed error responses in logs and adds guardrail header to streaming responses. * refactor(guardrails): fix and harden repelloai schema text extraction - Fix duplicate text in _iter_schema_text: previously all dict values were re-queued onto the stack even after scalar/list keys were already extracted explicitly, causing names/descriptions to appear twice in the scanned prompt - Extract schema key frozensets to module-level constants so they are not reconstructed on every call - Change _iter_schema_text from @classmethod to @staticmethod (cls unused) - Narrow _call_analyze stage param from str to Literal["prompt", "response"] - Add HttpxResponse type annotation to _raise_for_config_error - Add LLMResponseTypes annotation to async_post_call_success_hook response param * fix(guardrails): resolve pyright type errors in repelloai guardrail - Narrow async_handler.post return from Response|None to Response with explicit None guard before calling raise_for_status/json - Fix list comprehension returning str|None by switching to explicit loop with isinstance guard so pyright tracks the narrowing - Cast model_dump() result to Dict since hasattr does not narrow object type in pyright * fix(guardrails/repello): include Responses API instructions field in prompt scan The /v1/responses top-level `instructions` field was not included in _extract_prompt_text, allowing a caller to bypass guardrail policy checks by putting blocked content in `instructions` while keeping `input` benign. * feat: add api_key to config model and read prompt from data dict * fix(guardrails/repello): plug input_text and tool-call response bypass gaps Responses API input content parts with type 'input_text' were silently dropped by build_inspection_messages (which only handles type='text'), allowing callers to send blocked content via that path without triggering the pre-call scan. Fix: add _extract_input_text_parts to RepelloAIGuardrail and call it when walking the Responses API input messages. Post-call scanning skipped responses whose choices contained only tool_calls or function_call (message.content=None), letting models put blocked output in function arguments undetected. Fix: _extract_chat_completion_text now calls _extract_tool_call_args_from_message on each choice message. Also replace typing.Dict/List with builtin dict/list to clear TID251 strict ruff violations introduced by this file. * fix(guardrails/repello): scan Responses API function_call output arguments Output items with type 'function_call' in a /v1/responses response were skipped by _extract_responses_api_text; only 'message' items were walked. A model could return blocked content in function_call.arguments undetected. Now extract arguments from function_call output items before scanning. * refactor(guardrails/repello): clean up typing and remove lint-any workarounds - Replace Optional[X]/Union[X,Y] with X|None/X|Y union syntax throughout - Use dict[str, object] instead of bare dict in all signatures - Remove **kwargs from __init__; declare guardrail_name, event_hook, default_on explicitly - Replace getattr(litellm_params, ...) with direct attribute access now that LitellmParams inherits RepelloAIGuardrailConfigModel - Add _event_hook_from_mode() to convert str|list[str]|Mode to typed GuardrailEventHooks - Use TypeAdapter.validate_json() instead of response.json() + manual dict construction - Add _is_object_dict/_is_object_list TypeGuard helpers to narrow object types without Any - Remove cast() workarounds and typed intermediate variables that existed only for the now-removed lint-any CI check - Drop _AddLiteLLMCallback Protocol; budget has sufficient slack for the one reportUnknownMemberType - Fix GuardrailConfigModel missing type arg: GuardrailConfigModel[BaseModel] * fix(guardrails/repello): suppress LIT007 on TypeGuard helpers and add streaming scan-skip warning - Add guard-ok suppressions to _is_object_dict and _is_object_list to satisfy the LIT007 hard-zero budget gate - Emit verbose_proxy_logger.warning when the streaming hook finds no inspectable text after assembly, matching observability of pre/post hooks * refactor: modifications for lint check * feat: add Pinstripes as an OpenAI-compatible provider (#30567) * feat: add Pinstripes as an OpenAI-compatible provider Pinstripes (https://pinstripes.io) is an OpenAI-compatible inference provider serving open-source models (GLM-4.5-Air, Qwen3, DeepSeek, etc.) with per-token pricing and no subscriptions. Changes: - `litellm/llms/openai_like/providers.json`: register pinstripes with base_url, api_key_env, and max_completion_tokens→max_tokens mapping - `litellm/types/utils.py`: add `PINSTRIPES = "pinstripes"` to LlmProviders - `litellm/constants.py`: add to openai_compatible_providers and openai_compatible_endpoints lists - `litellm/litellm_core_utils/get_llm_provider_logic.py`: auto-detect provider when api_base is "https://pinstripes.io/v1" - `provider_endpoints_support.json`: document supported endpoints - `tests/`: 7 unit tests covering provider registration, resolution, URL auto-detection, api_base override, and Router config Usage: import litellm response = litellm.completion( model="pinstripes/ps/glm-4.5-air", messages=[{"role": "user", "content": "Hello"}], api_key=os.environ["PINSTRIPES_API_KEY"], ) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(pinstripes): resolve Greptile P1 review comments - Add api_base_env: PINSTRIPES_API_BASE to providers.json so env var override works - Set responses: false in provider_endpoints_support.json — not actually wired up - Remove docs/my-website/docs/providers/pinstripes.md — belongs in litellm-docs repo Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(pinstripes): add api_base_env and correct responses capability - Add api_base_env: PINSTRIPES_API_BASE to providers.json - Set responses: false in provider_endpoints_support.json Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(pinstripes): wire up Responses API — add supported_endpoints Adds supported_endpoints: ["/v1/chat/completions", "/v1/responses"] so JSONProviderRegistry.supports_responses_api returns true correctly, matching what provider_endpoints_support.json advertises. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * feat(pinstripes): enable embeddings endpoint Pinstripes serves nomic-embed-text-v1.5 and bge-m3 via /v1/embeddings. Add /v1/embeddings to supported_endpoints and set embeddings: true. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(pinstripes): use 4-space indentation in model_prices_and_context_window.json Matches the file's existing convention. Flagged by Greptile review. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(pinstripes): set a2a: false — A2A protocol not implemented All comparable JSON-configured providers (tensormesh, parasail, empiriolabs, libertai, neosantara) have a2a: false. Pinstripes does not implement the Google A2A protocol, so this should be false to match. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: inference_provider <max@redactedlab.com> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(rag): attach existing OpenAI file ids (#30628) * fix(rag): attach existing OpenAI file ids * chore: use modern typing in rag ingest fix * chore: retrigger ci * fix(anthropic-messages): apply cache_control_injection_points on /v1/messages path (#30341) cache_control_injection_points was only consumed by the chat/completions prompt-management hook; on the native Anthropic /v1/messages path it was forwarded unused, so deployment-level cache injection was silently dropped (cache_creation_input_tokens stayed 0 for Anthropic-native clients). Add AnthropicCacheControlHook.apply_to_anthropic_messages_request to inject cache_control at block level for system / tools / message locations (the only forms /v1/messages accepts), wire it into the native anthropic_messages handler, and pop the param so it does not leak upstream as an unknown field. A {location: message, role: system} config is redirected to the top-level system prompt so the same YAML works on both endpoints. Injection respects Anthropic's 4-block cache_control limit shared across system, tools, and messages: client-supplied markers count toward the cap and are never overwritten, a slot is reserved per Bedrock tool_config point, and injection stops once the budget is exhausted. Locations this path cannot represent (tool_config) are forwarded downstream instead of being silently consumed, mirroring get_chat_completion_prompt's remaining_points pass-through. Built on litellm_internal_staging. Refs BerriAI/litellm#30293 * fix(proxy): release budget reservation when a request is cancelled mid-flight (#30522) * fix(proxy): release budget reservation on cancel when no chunk was delivered The pre-call budget reservation increments the cross-pod spend counter by a request's worst-case cost, then reconciles it on success (cost callback) or error (failure hook). A client disconnect or timeout cancels the request and surfaces as CancelledError / GeneratorExit, which neither path catches, so the reservation leaks. Under a retry storm the leaked holds accumulate, pin the counter above real spend, and return spurious 429 "Budget has been exceeded" to keys whose spend is far below budget; the counter only recovers when its TTL lapses, so the failure is intermittent and self-healing. Release the reservation in async_streaming_data_generator (which the Anthropic and Google SSE generators delegate to) on the (CancelledError, GeneratorExit) path, alongside the existing max_parallel_requests release. release_budget_ reservation_on_cancel runs under asyncio.shield so it completes despite the in-progress cancellation, is guarded by the reservation's finalized flag, and swallows a failing release so it cannot replace the in-flight cancellation. The refund is gated on whether a chunk reached the client. The flag is set immediately before the yield, after the slow-path hook await: an async generator suspends at the yield, so a GeneratorExit on disconnect after a delivered chunk sees it True (keep the hold), while a cancellation during the slow-path await leaves it False (refund, nothing sent). A non-streaming cancellation delivers nothing and a completed non-streaming response is reconciled by the success callback, so neither needs a release here. Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * fix(proxy): reconcile a cancelled reservation to input cost, not zero A streaming request cancelled before the first chunk previously reconciled its reservation to zero and finalized it. But by the time the generator is consuming the response the provider call was already dispatched, so the input tokens were billed even though no chunk reached the client, and the success/failure cost callbacks are skipped on cancellation. Refunding to zero let a caller send an expensive request and abort pre-token to dodge the input charge. Compute the request's input-token cost at reservation time and reconcile the cancelled reservation to it instead of zero. The worst-case output portion of the reservation is still released (so a legitimate mid-flight cancellation no longer pins the counter and 429s the key), while the input the provider already processed is charged. --------- Co-authored-by: Bytechoreographer <Bytechoreographer@users.noreply.github.com> Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * fix(caching): encode object name in GCS cache GET path (#30378) GCS cache reads always missed when gcs_path was set. The GET methods interpolated the object name directly into the URL path, while the GCS JSON API requires it to be URL-encoded (a "/" must be sent as %2F). With gcs_path configured the object name is "<prefix>/<sha256>", so the raw slash produced a malformed object path and GCS returned 404. httpx does not raise on 4xx, so the status_code == 200 check fell through and get/async_get returned None, silently missing on every read. Without gcs_path the key has no slash, which is why this went unnoticed. Wrap the object name with urllib.parse.quote(..., safe="") in get_cache and async_get_cache. Apply the same encoding to the name= query parameter in set_cache and async_set_cache so the key written matches the key read back. Adds regression tests asserting the GET path and SET query are encoded (%2F) when gcs_path is set, for both sync and async paths; these fail on the unpatched code. Fixes #30377 * chore: add soniox stt-async-v5 model (#30672) * fix(proxy): include model group aliases in v1 model info (#30626) * Include model group aliases in v1 model info * Fix model info alias implementation * removed extra blank line * chore: rerun CI * fix(lint): remove redundant noqa directive in proxy_cli.py * fix: address greptile review - restore bedrock_mantle auth symbols, guard OCI empty message list, validate DIRECT_URL scheme * Revert "fix: address greptile review - restore bedrock_mantle auth symbols, guard OCI empty message list, validate DIRECT_URL scheme" This reverts commit |
||
|
Yassin Kortam
|
78a7d0b210
|
feat(guardrails): surface OpenAI moderation violation_categories on guardrail traces (#30659)
The OpenAI moderation guardrail (and the ai-platform-moderation guardrail built on it) stamped the whole moderation model response into the guardrail trace as guardrail_response. That blob carries the full category_scores map plus categories and category_applied_input_types, which on OTEL backends that index span attributes (for example ELK, which caps indexed attribute values at 1024 chars) overflows the limit and gets truncated, so the violated categories cannot be reliably searched. Extract the flagged category names from the moderation response and pass them through tracing_detail to add_standard_logging_guardrail_information_to_request_data, mirroring the Bedrock hook. Both the legacy and v2 OTEL integrations already read violation_categories off the standard logging guardrail information and emit it as a short, queryable guardrail_violation_categories attribute, so dashboards can group and filter by violation category without parsing the large guardrail_response blob. Resolves LIT-3801 |
||
|
Sameer Kankute
|
1ccc1e5b23
|
chore: litellm oss staging160626 (#30527)
* feat(ui): gate "Default Credentials" hint on /ui/login behind env flag (#30234) Adds LITELLM_HIDE_DEFAULT_CREDENTIALS_HINT (and an equivalent general_settings.hide_default_credentials_hint) that suppresses the "By default, Username is admin and Password is your set LiteLLM Proxy MASTER_KEY" info card rendered on /ui/login and /fallback/login. Motivation: in production deployments operators set UI_USERNAME / UI_PASSWORD (or SSO), and the hardcoded hint becomes factually incorrect and is flagged by security scanners (Tenable WAS plugin 114625) as information disclosure. There is currently no way to suppress it without forking the dashboard. Behaviour: - Default is unchanged (hint shown), so existing deployments are unaffected. - New field hide_default_credentials_hint on the well-known UI config endpoint, populated from the env var or general_settings. - LoginPage.tsx conditionally renders the Alert based on the flag. Refs: BerriAI/litellm#30232 * fix(router): clean pattern_router state on upsert/delete (#29601) * fix(router): clean pattern_router state on upsert/delete PatternMatchRouter.add_pattern was append-only, and neither Router.upsert_deployment nor Router.delete_deployment removed the existing entry. Rotated-out api_keys stayed in the routing rotation for wildcard deployments (model_name with `*`) until proxy restart, silently defeating key rotation as an admin operation. The same leak applied to provider_default_deployment_ids and per-team pattern routers, and the patterns list grew unboundedly on every edit * test(router): direct unit tests for _remove_deployment_from_wildcard_state router_code_coverage.py greps test files for AST Call nodes and flagged the helper as untested because the existing coverage only exercised it transitively through upsert/delete. Adds two direct tests that pin the helper's contract (cleans across global pattern router, per-team routers with empty-router pop, and provider_default_deployment_ids; noop on falsy model_id) * fix(router): address Greptile review on pattern_router cleanup Widen PatternMatchRouter.remove_deployment annotation to Optional[str]; the implementation already handles None via the falsy guard and the unit test exercises it directly. Move _remove_deployment_from_wildcard_state up one level in upsert_deployment so it runs whenever the prior deployment is on the router, not only when the model_id is present in the fast-mapping index. The scenario is currently unreachable (get_deployment shares the same index), but the cleanup is idempotent so this is defensive against any future divergence between those code paths. * fix(router): widen _remove_deployment_from_wildcard_state to Optional[str] Moving the call out of the inner `deployment_id in deployment_fast_mapping` block in the previous commit lost mypy's narrowing of `deployment_id` from Optional[str] to str, tripping the lint CI. The helper already handles None via its falsy guard, so widening the annotation matches the actual contract. * fix(router): make delete_deployment wildcard cleanup symmetric with upsert After the previous commit moved _remove_deployment_from_wildcard_state out of the inner index-map guard in upsert_deployment, delete_deployment was still calling it only inside `if deployment_idx is not None`. Greptile flagged the asymmetry: under a desynced index_map, delete would silently leave the stale wildcard credential in pattern_router. Moves the cleanup call to the top of the try block, mirroring the upsert path. Cleanup is idempotent so the change is a no-op on the happy path. Adds a regression test that simulates the desync by removing the entry from model_id_to_deployment_index_map and asserts delete still clears pattern_router. * fix(pricing): add 1h cache-write cost for Anthropic Sonnet 4.5/4.6 (#30474) The native anthropic claude-sonnet-4-5/4-6 price-map entries were missing cache_creation_input_token_cost_above_1hr (and the >200K long-context sub-tier for 4.5), so 1-hour-TTL cache writes were costed at the 5-minute rate. Adds 6e-06 regular (and 1.2e-05 long-context) = 2x base input, matching the vertex_ai/azure_ai/bedrock siblings and the older claude-sonnet-4-20250514 entry. Adds a regression test. * fix(proxy): cancel upstream gemini request and release httpx connection on client disconnect (#30075) * fix(proxy): cancel upstream gemini request and release httpx connection on client disconnect - add _check_request_disconnection to common_request_processing; wrap llm_call as asyncio.Task so it can be cancelled; catch CancelledError and raise HTTPException(499) when client disconnects before LLM responds (non-streaming path) - pass raw httpx.Response into ModelResponseIterator in make_call/make_sync_call so the iterator holds a reference to the underlying connection - implement ModelResponseIterator.aclose() and .close(): close the line iterator then explicitly call response.aclose()/response.close() to release the httpx connection when the client drops mid-stream; errors are debug-logged, not raised - add tests for _check_request_disconnection (cancels task, graceful on exception, does not cancel when client stays connected) and base_process_llm_request 499 behavior; add TestModelResponseIteratorCleanup verifying aclose/close propagation through CustomStreamWrapper * fix(proxy): record 499 on streaming disconnect and cancel orphaned gather tasks Wire streaming generator cleanup to log client_disconnected with error_code 499 in spend logs, cancel pending during_call_hook tasks when the LLM call is cancelled on disconnect, and align the 600s poll limit comment with proxy_server. * fix: extract client disconnect logging helper to satisfy PLR0915 * fix: resolve mypy and code-quality CI failures for client disconnect logging Cast client disconnect error_information for mypy, only await pending gather tasks to avoid masking LLM errors, and add tests for the new logging helper and gather cleanup. * fix(proxy): harden gather cleanup so finally cannot mask LLM errors * fix(proxy): shield streaming disconnect logging and strip spoofable metadata Move streaming disconnect recording into a shielded cancel scope, add gather cleanup regression coverage for guardrail-converted cancels, and strip client_disconnected/error_information from user metadata at the proxy boundary. * fix(proxy): only map CancelledError to 499 for client disconnect Track when the disconnect poller cancels the LLM task and re-raise other CancelledError paths so graceful shutdown is not reported as HTTP 499. * fix(proxy): remove dead _check_request_disconnection helper Non-streaming client disconnect is handled by staging's cancel_on_disconnect path via _await_llm_call_cancelling_on_disconnect. Drop the unused is_disconnected poller and its unit tests; rename the remaining integration tests to TestDisconnectGatherCleanup. * feat(mistral): add mistral-medium-3-5 to model_prices_and_context_wind.. (#29303) * feat(mistral): add mistral-medium-3-5 to model_prices_and_context_window.json Mistral's docs page lists mistral-medium-3-5 as a new model offering. Pricing/specs sourced from Mistral's published model metadata: - input: $1.50 / 1M tokens - output: $7.50 / 1M tokens - context: 262,144 tokens - capabilities: vision, function calling, structured outputs, assistant prefill Adds entry: `mistral/mistral-medium-3-5`, mirroring the pattern used for the rest of the Mistral family. test(mistral): add model_info test for mistral-medium-3-5 + sync backup cost map - Mirror mistral/mistral-medium-3-5 entries into litellm/model_prices_and_context_window_backup.json so the bundled model cost map matches the canonical model_prices_and_context_window.json. - Add tests/test_litellm/test_mistral_medium_3_5_model_metadata.py covering pricing tiers, capability flags, context window, provider routing, and parity between the main and backup cost maps. - Point 'source' at the live Mistral models documentation page. * fix(ui): three small UI fixes — Gemini api_base + credential form reset + Mode badge (#30419) * fix(ui): three small UI fixes — Gemini api_base field + credential form reset + Mode badge Three independent fixes; bundled because they all touch the credential-form / logging-callbacks area. 1. expose api_base field on Google AI Studio credential form The runtime gemini provider supports custom api_base via `vertex_llm_base._check_custom_proxy`; the UI just needs to expose the field. Adds api_base to the Google_AI_Studio credential form ordered before api_key (matching OpenAI/Anthropic conventions). Default value matches the canonical Google AI Studio endpoint that LiteLLM's gemini provider talks to when api_base is unset, so leaving the default in the form behaves identically to leaving it blank. 2. reset credential form state when switching providers Switching the Provider select in AddCredentialModal / EditCredentialModal left the previous provider's field values populated. The form then submitted a mixed payload (e.g. Azure deployment fields under an OpenAI credential), producing confusing failures. Extract `getProviderFieldDefaults` helper and reset the form to it on provider change. Unit-tested via the extracted helper because Antd Select's portal/dropdown behaviour is unreliable in jsdom. 3. logging callbacks table reads backend `type` for Mode badge (#35) The `/get_callbacks` proxy endpoint returns each callback as `{name, type, variables}` where `type` is `"success"` or `"failure"`. The same callback name can appear twice (one per event class) and the two entries fire on disjoint events. `LoggingCallbacksTable` ignored `type` and read `record.mode` (always undefined), so every row fell back to the "Success" badge. A `generic_api` callback registered for both classes showed up as two identical "Success" rows + React duplicate-key warning. Read `record.type` first (fall back to `record.mode` for newly- added not-yet-server-acknowledged rows). Composite rowKey `${name}-${type ?? mode ?? 'success'}`. Removed leftover debug `console.log`. * fix(ui): drop api_base default_value to preserve Gemini v1alpha auto-routing Greptile P2 (PR #30419, threads on lines 1255-1256 of provider_create_fields.json): the api_base field's `default_value` was hard-coded to "https://generativelanguage.googleapis.com/v1beta". This: 1. Bakes v1beta into every credential record saved through the form, even when the user never touched the field. If LiteLLM's internal gemini default URL ever changes, those persisted credentials keep hitting the stale path. 2. Bypasses `_get_gemini_url`'s automatic version routing for Gemini 3+ models. That helper picks v1alpha for Gemini 3+ and v1beta for older models when api_base is unset. With the default pre-filled (and `_check_custom_proxy` then taking over because api_base is non-empty), Gemini 3+ requests get pinned to v1beta and may fail or behave unexpectedly — purely because the user accepted the visible default. Fix: set `default_value` to `null` and move the canonical URL guidance into the `placeholder` (visible to the user, never persisted) and an expanded tooltip. UX is unchanged — the URL is still shown in the greyed-out input — but the auto-version-routing path stays default. Updated test_google_ai_studio_provider_fields_expose_api_base to assert the new contract (`default_value is None`, `placeholder` carries the canonical URL), with a comment pointing at the Greptile threads as the rationale so future contributors don't accidentally re-introduce the default. 26/26 tests in the file pass. JSON validates (`json.load` clean). * feat(azure_ai): add gpt-5.5 to model cost map (#30428) * feat(azure_ai): add gpt-5.5 to model cost map Adds azure_ai/gpt-5.5 and its dated snapshot azure_ai/gpt-5.5-2026-04-23 to both the canonical and bundled cost maps. gpt-5.5 is generally available on Azure AI Foundry; pricing mirrors the openai gpt-5.5 entry, matching the established azure_ai convention (verified identical for gpt-5.4), in the azure tier structure (base / above-272k / priority). supports_minimal_ reasoning_effort is false, the capability that changed from gpt-5.4. Fixes #30306 * Update tests/test_litellm/test_gpt_5_5_model_metadata.py Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> --------- Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * fix: guard check_and_fix_namespace against None key (#30435) * fix: guard check_and_fix_namespace against None key When user_id is None, the cache key can be None, causing AttributeError: 'NoneType' object has no attribute 'startswith' in check_and_fix_namespace. Add an early return for None key to prevent the error and the ERROR-level log noise it produces on every unauthenticated request. Fixes #30424 * fix: update type annotations for check_and_fix_namespace - key: str -> Optional[str] (now handles None input) - return: str -> Optional[str] (returns None when input is None) Addresses Greptile review concern about type signature mismatch. * fix: revert check_and_fix_namespace type signature to str to fix MyPy downstream errors * fix: update type annotations for check_and_fix_namespace - Change signature from str -> str to Optional[str] -> Optional[str] - Remove type: ignore comment on None return - Add None guard in async_set_cache_sadd before passing to helper Addresses review feedback from Sameerlite on type mismatch. * Revert "fix: update type annotations for check_and_fix_namespace" This reverts commit |
||
|
Yassin Kortam
|
9fa74ad8b4
|
fix(guardrails): stop re-initializing DB guardrails on every poll (#30542)
* fix(guardrails): stop re-initializing DB guardrails on every poll InMemoryGuardrailHandler._has_guardrail_params_changed compared the in-memory LitellmParams against the raw dict loaded from the DB. The in-memory side carries every field default and coerces enums via model_dump(), while the DB side only holds the keys originally stored, so the two shapes never compared equal and the guardrail was rebuilt on every poll cycle. Each rebuild created a fresh instance, but delete_in_memory_guardrail only removed the old callback from litellm.callbacks. Request handling promotes guardrail callbacks into the success/failure/async lists, so the previous instance stayed referenced there and instances accumulated. Normalize both sides through LitellmParams(...).model_dump() before diffing, and purge the callback from every callback list on delete. * refactor(guardrails): narrow params-normalization fallback to ValidationError The comparison normalizer caught a bare Exception and silently fell back to the raw dict, which hid the cause and quietly degraded the affected guardrail back to re-initializing on every poll. Catch only the ValidationError that LitellmParams construction can raise, log a warning so the offending row is diagnosable, and let any other error surface instead of being swallowed. * refactor(callbacks): add remove_callback_from_all_lists helper to manager Move the knowledge of which callback lists a callback can be promoted into out of the guardrail registry and into LoggingCallbackManager, where the rest of the callback-list bookkeeping already lives. delete_in_memory_guardrail now delegates to the new helper instead of iterating the lists itself. |
||
|
Yassin Kortam
|
ec9353cb69
|
feat(guardrails): add Cisco AI Defense integration (#28249) (#30338) | ||
|
Sameer Kankute
|
ccc20b121f
|
fix(responses): presidio PII masking for Azure WebSocket and streaming (#30003)
* fix(responses): Presidio PII masking for Azure WebSocket and streaming
Wire Presidio into native Responses WebSocket forwarding and fix streaming output unmasking so masked tokens are restored for HTTP and WS clients.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Fix unused imports in responses handlers
* fix(responses): address Greptile review - Azure WebSocket model URL and PII logging
- Add model_in_websocket_url() to BaseResponsesAPIConfig (default True) so
providers can opt out of ?model= being appended to WebSocket URLs.
- Override model_in_websocket_url() to return False for Azure, since Azure
sends the model in the response.create body, not the URL query string.
- Use this flag in llm_http_handler to conditionally append ?model=.
- Pass masked message to _store_input() instead of the original PII-containing
message so logging destinations do not receive unmasked PII.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(responses): mask nested response.create input format for Presidio PII
Handle the nested {"type":"response.create","response":{"input":[...]}}
format in _mask_response_create. Previously only the flat top-level input
was masked; the nested shape bypassed Presidio and forwarded raw PII
upstream. Now both shapes are normalized and masked before forwarding.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* style: apply black formatting to llm_http_handler and streaming_iterator
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* style: suppress PLR0915 on async_responses_websocket
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(responses): add apply_to_output masking on Responses API WebSocket path
Previously the WebSocket guardrail filter excluded callbacks with
apply_to_output=True, leaving model-generated PII unmasked before
returning to the client.
- Collect apply_to_output callbacks separately in llm_http_handler and
pass them to ResponsesWebSocketStreaming as output_guardrail_callbacks.
- Add _mask_response_completed method that calls check_pii(output_parse_pii=False)
on text blocks in response.completed events, masking model output PII.
- backend_to_client now chains unmask (pii_tokens) → mask (apply_to_output)
before forwarding each event to the client.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(responses): unmask PII tokens in streaming delta events and warn on guardrail init failure
- Rename _unmask_response_completed -> _unmask_response_event and extend
it to also unmask response.output_text.delta (and other delta types)
so real-time streaming clients receive original values, not PII tokens.
- Split the broad except-and-swallow into ImportError (expected in SDK-only
environments) vs Exception (unexpected — now logs a warning so operators
know masking is disabled).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(responses): enforce authorized model on WebSocket frames and remove proxy import
Security: add _enforce_authorized_model to ResponsesWebSocketStreaming that
overwrites both flat and nested model fields in every response.create frame
with the connection-authorized model, preventing deployment-substitution
attacks where an authenticated user sends a different model name in the frame
body after connecting with an allowed model.
Layering: remove the _OPTIONAL_PresidioPIIMasking isinstance check and proxy
import from the SDK handler. Use duck-typed checks (callable check_pii +
get_presidio_settings_from_request_data) so any guardrail implementing the
interface works, not just Presidio.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(responses): add _unmask_pii_text to duck-typed contract and mask delta frames
- Add callable(_unmask_pii_text) check to the guardrail_callbacks filter so
a custom guardrail missing that method cannot cause an AttributeError and
silently kill the WebSocket session.
- Extend _mask_response_completed to also mask response.output_text.delta
(and other delta types) for apply_to_output callbacks, so real-time
streaming clients do not receive unredacted model-generated PII in deltas.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* Fix Responses WebSocket guardrail edge cases
* fix(responses): log masked output and suppress deltas when apply_to_output active
- Move _store_event to after _mask_response_completed so logs receive the
redacted form, not raw model output containing PII.
- Suppress delta event forwarding when output_guardrail_callbacks are
present: per-fragment Presidio cannot catch PII that spans multiple
chunks (e.g. "alice@" + "example.com"). Clients receive only the
fully-masked response.completed, which Presidio scans on complete text.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(responses): mask and suppress response.output_item.done for apply_to_output
response.output_item.done carries completed item text in item.content[*].text
before response.completed arrives, allowing unmasked PII to reach the client.
- _unmask_response_event: unmask input-PII tokens in item.content[*].text
- _mask_response_completed: run check_pii on item.content[*].text for
apply_to_output callbacks (same as response.completed handling)
- backend_to_client suppression: also skip response.output_item.done when
output_guardrail_callbacks are active; client receives only the
fully-masked response.completed
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(types): cast response_obj to ResponsesAPIResponse to satisfy mypy
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* Revert "fix(types): cast response_obj to ResponsesAPIResponse to satisfy mypy"
This reverts commit d5969557628f9aff58948b9d37cc64d577f95a15.
* Revert "fix(responses): mask and suppress response.output_item.done for apply_to_output"
This reverts commit 219fd54ea3446f4399fde40c07ba0617e2834573.
* fix(types): accept dict responses in guardrail output write-back
Streaming response.completed events pass a dict response object, so widen
_apply_guardrail_responses_to_output to match its existing runtime handling.
Co-authored-by: Cursor <cursoragent@cursor.com>
* perf(responses): skip Presidio masking on suppressed WebSocket delta events
Delta events are dropped wholesale when apply_to_output masking is active,
so masking them first issued a wasted check_pii call per fragment. Move the
suppression check ahead of the unmask/mask passes; the event type is
invariant across both, so client-visible behavior is unchanged.
* test(responses): cover Responses WebSocket PII masking hooks
Add regression tests for the native Responses WebSocket guardrail path:
input masking and model enforcement in _mask_response_create, token
unmasking in _unmask_response_event, apply_to_output masking and delta
suppression in _mask_response_completed/backend_to_client, and the
get_websocket_url / model_in_websocket_url defaults for the base and
Azure configs. Raises diff coverage above the codecov patch target.
* fix(responses): suppress text-bearing done events under output PII masking
When apply_to_output masking is active on a native Responses WebSocket,
response.output_text.done, response.content_part.done, and
response.output_item.done carry the full model output before the masked
response.completed arrives, so an authenticated client could read
unmasked PII from those events. Suppress them alongside delta events; the
client receives only the fully-masked response.completed.
* refactor(responses): drop dead delta branch in WebSocket output masking
Delta events are suppressed in backend_to_client before _mask_response_completed
runs when output masking is active, so the method's delta-handling branch was
unreachable. Restrict it to response.completed and cover the Responses API
unmask path with a Pydantic ResponseCompletedEvent regression test.
* fix(presidio): flush buffered chat chunks on mixed unmask stream
_stream_pii_unmasking buffered ModelResponseStream chunks but returned
early once a /v1/responses event was seen, silently dropping the buffered
chat chunks. Flush them in order before switching to passthrough, mirroring
_stream_apply_output_masking, and cover it with a regression test.
* fix(responses): mask instructions and tool-call arguments in WebSocket PII path
Presidio masking on the native Responses WebSocket path left two gaps. On the
request side _mask_response_create only walked the input containers, so PII
placed in the instructions field of a response.create frame was forwarded
upstream and logged unmasked even with output_parse_pii enabled. Now both the
flat and nested instructions strings are masked alongside input.
On the response side _mask_response_completed only masked content text blocks,
so model-produced PII inside function-call arguments could reach the client when
apply_to_output was enabled, both via the standalone
response.function_call_arguments.done event and via the function_call output
items in response.completed. The done event is now suppressed under output
masking and completed function-call arguments are run through check_pii before
forwarding or logging.
* fix(responses): suppress reasoning_summary_text.done under output PII masking
* fix(responses): mask function_call_output.output in WebSocket PII path
response.create input items of type function_call_output carry
user-controlled text in output, not content, so the Presidio masking
pass forwarded that text upstream unmasked. Mask the output field
(string or list of text blocks) alongside content.
* fix(responses): mask reasoning summary PII in WebSocket output path
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
|