ErrLookup › BerriAI/litellm

BerriAI/litellm

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM] · Python · 3,616 source files

Analyzed at 6c2dcb801b on 2026-08-15. 1406 documented errors.

Code / Message	Type	Severity	Tags
Unclassified keys in {PRICES_PATH.name}: {', '.join(unclassi	console	error	litellm, image-variations, provider-config, openai, routing
No Braintrust API token provided. Pass via Authorization hea	http	error	litellm, image-variations, request-transform, openai, custom-config
Braintrust API error: {e.response.text}	http	error	openai, streaming, mid-stream-error, text-completion, litellm
Failed to connect to Braintrust API: {str(e)}	http	error	openai, async, streaming, text-completion, litellm
Failed to parse Braintrust API response: {str(e)}	http	error	openai, response-parsing, text-completion, litellm, internal
Failed to transform Braintrust response: {str(e)}	http	error	openai, containers, api-error, litellm, http
Error: {response.status_code} - {response.text}	exception	critical	openai, evals, authentication, configuration, litellm
Missing Authorization header	http	critical	openai, fine-tuning, authentication, configuration, litellm
Invalid Authorization header format. Expected: Bearer <token	http	error	openai, fine-tuning, async, type-mismatch, litellm
Invalid bearer token	http	critical	openai, fine-tuning, authentication, configuration, litellm
Invalid authorization header format. Expected 'Bearer <token	http	error	openai, fine-tuning, async, type-mismatch, litellm
Invalid API key	http	critical	openai, fine-tuning, authentication, configuration, litellm
Prompt '{prompt_id}' not found. Available prompts: {list(PRO	http	error	openai, fine-tuning, async, type-mismatch, litellm
Prompt '{prompt_id}' not found	http	critical	openai, fine-tuning, authentication, configuration, litellm
Prompt '{prompt.prompt_id}' already exists	http	error	openai, fine-tuning, async, type-mismatch, litellm
Error apply_db_fixes: {str(e)}	exception	error	openai, image-edit, response-parsing, litellm, http
Unknown hook: {hook_name}. Available hooks: {list(ENTERPRISE	validation	warning	openai, dall-e-2, image-generation, parameter-validation, litellm
Violated guardrail policy	http	warning	openai, dall-e-3, image-generation, parameter-validation, litellm
`banned_keywords_list` can either be a list or filepath. Non	exception	warning	openai, gpt-image-1, image-generation, parameter-validation, litellm
File not found. banned_keywords_list={banned_keywords_list}	exception	error	openai, image-variations, dall-e-2, request-transform, litellm
An error occurred: {str(e)}, banned_keywords_list={banned_ke	exception	critical	openai-compatible, predibase, authorization, authentication, secret-leak, litellm
Keyword banned. Keyword={word}	http	warning	enterprise, banned-keywords, content-filter, http-400, pre-call-hook
File not found. blocked_user_list={blocked_user_list}	exception	error	enterprise, blocked-users, file-io, config, startup
An error occurred: {str(e)}, blocked_user_list={blocked_user	exception	error	enterprise, blocked-users, file-io, permissions, startup
User blocked from making LLM API Calls. User={user}	http	warning	enterprise, blocked-users, access-control, http-400, pre-call-hook
Missing google.cloud package. Run `pip install --upgrade goo	exception	error	enterprise, google-moderation, dependency, startup, pip
Violated content safety policy. Category={category}	http	warning	enterprise, google-moderation, content-filter, http-400, threshold
Violated content safety policy	http	warning	enterprise, openai-moderation, content-filter, http-403
Internal Server Error	http	error	enterprise, example, callback-server, fastapi, http-500
model_name not set for LlamaGuard	validation	error	enterprise, llama-guard, config, startup
File not found. file_path={file_path}	exception	error	enterprise, llama-guard, file-io, config, startup
An error occurred: {str(e)}, file_path={file_path}	exception	error	enterprise, llama-guard, file-io, permissions, startup
Violated content safety policy	http	warning	enterprise, llama-guard, content-filter, http-400
Missing `LLM_GUARD_API_BASE` from environment	exception	error	enterprise, llm-guard, environment, config, startup
Invalid content moderation response: {redacted_text}	http	error	enterprise, llm-guard, network, http-500, integration
Violated content safety policy	http	warning	enterprise, llm-guard, content-filter, http-400, prompt-injection
PAGERDUTY_API_KEY is not set	validation	error	enterprise, pagerduty, environment, alerting, startup
Error saving email settings to general_settings: {str(e)}	http	error	enterprise, email, database, prisma, http-500
Database not connected	http	error	database, prisma, litellm-enterprise, email, configuration
Setting tag based guardrail modes is only available in litel	exception	error	licensing, litellm-enterprise, guardrails, configuration
DB not connected. This endpoint needs a database; set DATABA	http	error	database, prisma, litellm-enterprise, audit-logging, configuration
You must be a LiteLLM Enterprise user to use this feature. I	validation	error	licensing, sso, auth, litellm-enterprise, configuration
custom_ui_sso_sign_in_handler is not configured. Please set	validation	error	sso, auth, configuration, litellm-enterprise
🚨🚨🚨 DISABLING LLM API ENDPOINTS is an Enterprise feature	http	error	licensing, route-management, configuration, litellm-enterprise
🚨🚨🚨 DISABLING ADMIN ENDPOINTS is an Enterprise feature 🚨	http	error	licensing, route-management, configuration, litellm-enterprise
Invalid mode: {custom_auth_settings['mode']}	validation	error	auth, configuration, validation, litellm-enterprise
LiteLLM Managed File object with id={file_id} not found	exception	error	managed-files, not-found, delete, litellm-enterprise
Filtering by 'provider' is not supported when using managed	exception	error	managed-batches, unsupported-operation, validation, litellm-enterprise
Filtering by 'target_model_names' is not supported when usin	exception	error	managed-batches, unsupported-operation, validation, litellm-enterprise
LiteLLM Managed {accessor_key} with id={retrieve_object_id}	exception	error	batch, managed-files, data-corruption, unified-id
LLM Router not initialized. Ensure models added to proxy.	exception	critical	configuration, router, files, startup
Unified id does not contain {marker!r}: {file_id[:80]!r}	validation	error	files, batch, unified-id, data-corruption
LiteLLM Managed File object with id={file_id} has no file_ob	exception	error	files, router, batch, managed-files
Failed to retrieve file {file_id} from provider: {str(e)}	exception	error	files, provider, credentials, managed-files
LiteLLM Managed File object with id={file_id} not found. Che	exception	error	files, provider, batch, credentials
soft_budget cannot be negative. Received: {data.soft_budget}	http	error	litellm, budget, validation, enterprise, http-400
soft_budget ({data.soft_budget}) must be strictly lower than	http	error	litellm, budget, validation, enterprise, http-400
Model '{m}' not in team's allowed models. Team allowed model	http	error	litellm, models, team, validation, enterprise, http-400
Project max_budget ({data.max_budget}) exceeds team's max_bu	http	error	litellm, budget, team, hierarchy, validation, enterprise, http-400
Project tpm_limit ({data.tpm_limit}) exceeds team's tpm_limi	http	error	litellm, rate-limit, tpm, team, validation, enterprise, http-400
Project rpm_limit ({data.rpm_limit}) exceeds team's rpm_limi	http	error	litellm, rate-limit, rpm, team, validation, enterprise, http-400
Only premium users can add tags to projects. You must be a L	http	error	litellm, enterprise, licensing, tags, http-403
Project management is an enterprise feature. You must be a L	http	error	litellm, enterprise, licensing, http-403
DB not connected. This endpoint needs a database; set DATABA	http	critical	litellm, database, prisma, configuration, http-500
Only admins or team admins can create projects. Your role is	http	error	litellm, authorization, rbac, team, http-403
`400` Project id = {data.project_id} already exists. Please use a different project id	http	error	litellm, conflict, idempotency, enterprise, http-400
project_id is required	http	error	litellm, validation, request-payload, http-400
Only admins or team admins can update projects	http	error	litellm, authorization, rbac, security, team, http-403
Cannot reassign project to a team you are not an admin of	http	error	litellm, authorization, team, security, http-403
Blocking web crawlers is an enterprise feature. You must be	exception	error	litellm, enterprise, licensing, configuration, startup
module {__name__!r} has no attribute {name!r}	exception	error	litellm, python, attributeerror, lazy-import, imports, versioning
{category} lazy import: unknown attribute {name!r}	exception	error	litellm, python, attributeerror, lazy-import, imports
Utils module lazy import: unknown attribute {name!r}	exception	error	litellm, python, attributeerror, lazy-import, utils
LLM client cache lazy import: unknown attribute {name!r}	exception	error	litellm, python, attributeerror, lazy-import, caching, http-clients
HTTP handlers lazy import: unknown attribute {name!r}	exception	error	litellm, python, attributeerror, lazy-import, httpx, internals
GCP IAM authentication failed	exception	error
azure-identity is required for Azure AD Redis authentication	exception	error
Azure AD authentication failed for Redis	exception	error
Either 'REDIS_URL' or both 'REDIS_HOST' and 'REDIS_PORT' mus	validation	error
Either 'host' or 'url' must be specified for redis.	validation	error
REDIS_CLUSTER_NODES environment variable is not valid JSON.	validation	error
Both 'sentinel_nodes' and 'service_name' are required for Re	validation	error
google-cloud-iam is required for GCP IAM Redis authenticatio	exception	error
Failed to fetch agent card from {self.base_url}. Tried paths	exception	error
A2A SDK is required for localhost retry handling. Install it	exception	error
Cannot retry A2A localhost URL fix: no agent card is availab	exception	error
Cannot retry A2A localhost URL fix: the client was not creat	exception	error
The 'a2a' package is required for A2A agent invocation. Inst	exception	error
A2A send_message failed: no response received from agent.	exception	error
A2A send_message failed: non-streaming message/send expects	exception	error
A2A send_message failed: no response received after retry at	exception	error
A2A send_message_streaming failed: no response received afte	exception	error
request is required for completion bridge	validation	error
request is required	validation	error	a2a, litellm, validation, request-required
Either a2a_client or api_base is required for standard A2A f	validation	error	a2a, litellm, config, missing-endpoint
litellm_params is required for BedrockAgentCoreA2AConfig (mu	exception	error	a2a, litellm, bedrock-agentcore, validation, litellm-params
litellm_params is required for LangFlowA2AConfig (must conta	exception	error	a2a, litellm, langflow, validation, litellm-params
api_base is required for PydanticAIProviderConfig	exception	error	a2a, litellm, pydantic-ai, missing-endpoint, validation
api_base is required for Pydantic AI agents	exception	error	a2a, litellm, pydantic-ai, streaming, missing-endpoint
api_base is required for Pydantic AI agents	exception	error	a2a, litellm, pydantic-ai, handler, missing-endpoint
Task {task_id} ended with state: {state}	exception	error	a2a, litellm, pydantic-ai, task-failed, polling, agent-state
Task {task_id} did not complete within {max_attempts * poll_	exception	error	a2a, litellm, pydantic-ai, timeout, polling
litellm_params is required for WatsonxOrchestrateA2AConfig (	exception	error	a2a, litellm, watsonx-orchestrate, validation, litellm-params
'username' is required in litellm_params when auth_mode='cp4	exception	error	a2a, litellm, watsonx-orchestrate, authentication, cp4d, config
WXO: No run_id in response: {run_data}	exception	error	watsonx-orchestrate, a2a, schema-drift, api-response
WXO run ended with non-success status '{status}': {run_data}	exception	error	watsonx-orchestrate, a2a, run-failure, status
'cp4d_host' is required in litellm_params for WXO agents	exception	error	watsonx-orchestrate, configuration, validation, cp4d
'instance_id' is required in litellm_params for WXO agents	exception	error	watsonx-orchestrate, configuration, validation, instance-id
'wxo_agent_id' is required in litellm_params for WXO agents	exception	error	watsonx-orchestrate, configuration, validation, agent-id
'api_key' is required in litellm_params for WXO agents	exception	error	watsonx-orchestrate, configuration, validation, authentication
Invalid value passed in for aget_assistants. Only bool or No	exception	error	assistants, api-misuse, type-validation, python
Invalid value passed in for async_create_assistants. Only bo	exception	error	assistants, api-misuse, type-validation, python
Invalid value passed in for async_delete_assistants. Only bo	exception	error	assistants, api-misuse, type-validation, python
Setting user/encoding format is not supported by {custom_llm	exception	error	assistants, embeddings, unsupported-params, provider-compat
'models' param not in kwargs	exception	error	batch-completion, api-misuse, validation, python
'models' must be a string or list of strings	exception	error	batch-completion, type-validation, api-misuse, python
Output file id is None cannot retrieve file content	exception	error	batches, openai, state-validation, polling
duration needs to be one of ["daily", "weekly", "monthly", "	exception	error	budget-manager, validation, configuration, python
Either a chat completion object or the text response needs t	exception	error	budget-manager, cost-tracking, validation, python
cache key is None	exception	error	caching, cache-key, validation, configuration
Missing expected key in embedding response: {e}	exception	error	caching, embeddings, provider-compat, schema-drift
input must be a string or a list	validation	error	caching, embeddings, type-validation, python
Please install litellm with `litellm[caching]` to use disk c	exception	error	caching, disk-cache, dependencies, installation
collection_name must be provided, passed None	exception	error	qdrant, semantic-cache, configuration, validation
similarity_threshold must be provided, passed None	exception	error	qdrant, semantic-cache, configuration, validation
Qdrant url must be provided	exception	error	qdrant, configuration, environment, semantic-cache
Error from qdrant checking if /collections exist {collection	exception	error	qdrant, http, authentication, network, semantic-cache
Quantization config must be one of 'scalar', 'binary' or 'pr	exception	error	qdrant, quantization, validation, configuration
Error while creating new collection	exception	error	qdrant, collection, semantic-cache, initialization
Redis circuit breaker is open — skipping {name}	exception	warning	redis, circuit-breaker, resilience, network, transient
Redis client does not support Lua script registration	validation	error	redis, lua, dependency, version, initialization
Redis client cannot set cache. Attribute not found.	exception	error	redis, cache-write, dependency, version
similarity_threshold must be provided, passed None	validation	error	redis, semantic-cache, configuration, validation
Missing required Redis configuration: {missing_var}. Provide	validation	error	redis, semantic-cache, environment, configuration
Failed to generate embedding: {e}	validation	error	redis, semantic-cache, embedding, authentication, openai
similarity_threshold must be provided, passed None	validation	error	valkey, semantic-cache, configuration, validation
valkey-semantic does not support cluster-mode-enabled (multi	validation	error	valkey, semantic-cache, cluster, elasticsearch-aws, configuration
Missing required Valkey configuration. Provide host and port	validation	error	valkey, semantic-cache, environment, configuration
Valkey semantic-cache index '{self.index_name}' already exis	validation	error	valkey, semantic-cache, embedding, dimension-mismatch, index
Unexpected responses stream payload	validation	error	responses-api, streaming, bridge, type-mismatch, internal
Stream ended without a completed response	validation	error	responses-api, streaming, bridge, incomplete-response, sync
Stream completed response is invalid	validation	error	responses-api, streaming, bridge, invariant, version
model is required	validation	error	validation, bridge, internal-api, kwargs
custom_llm_provider is required	validation	error	validation, bridge, internal-api, provider-resolution
messages is required	validation	error	validation, bridge, messages, internal-api
optional_params is required	validation	error	validation, bridge, optional-params, internal-api
litellm_params is required	validation	error	validation, bridge, litellm-params, internal-api
headers is required	validation	error	validation, bridge, headers, internal-api
model_response is required	validation	error	validation, bridge, model-response, internal-api
logging_obj is required	validation	error	validation, bridge, logging, internal-api
tool call not supported: {tool_call}	validation	error	tool-calls, transformation, responses-api, bridge
Unexpected response type: {type(raw_response)}	validation	error	transformation, responses-api, type-validation
Error in response: {raw_response.error}	validation	error	responses-api, provider-error, in-band-error
{model} unable to complete request: {raw_response.incomplete	validation	error	responses-api, token-limit, content-filter, transformation
Unknown items in responses API response: {output_items}	validation	error	responses-api, transformation, output-items, version-drift
Invalid image URL: {content_image_url}	validation	error	vision, image-url, validation, transformation
Chat provider: Empty parsed_chunk	validation	error	streaming, chunk-transformer, validation
Chat provider: Invalid chunk type {type(parsed_chunk)}	validation	error	streaming, chunk-transformer, deserialization
Chat provider: Invalid function argument delta {parsed_chunk	validation	error	streaming, tool-calls, chunk-transformer, delta
Chat provider: Invalid text delta {parsed_chunk}	validation	error	streaming, chunk-transformer, delta, text
Unsupported call_type={call_type!r} for compression. Expecte	validation	error	compression, call-type, validation, configuration
Container provider config not found for: {resolved_custom_ll	validation	error	litellm, containers, provider-support, validation
container operations are not supported for {custom_llm_provi	validation	error	litellm, containers, provider-support, validation
Container provider config not found for provider: {custom_ll	validation	error	litellm, containers, provider-support, validation
Container provider config not found for provider: {resolved_	validation	error	litellm, containers, provider-support, id-decoding
Invalid arg. Model cannot be none.	exception	error	litellm, cost-calculation, validation, model-name
prompt_characters must be provided for tts calls. prompt_cha	validation	error	litellm, cost-calculation, tts, speech, validation
cost for tts call is None. prompt_cost={_prompt_cost}, compl	validation	error	litellm, cost-calculation, tts, pricing-data
Model is None and does not exist in passed completion_respon	validation	error	litellm, cost-calculation, model-name, usage
usage object and custom_llm_provider must be provided for re	validation	error	litellm, cost-calculation, realtime, usage
response must be of type OCRResponse got type={type(response	validation	error	litellm, cost-calculation, ocr, type-validation
OCR response usage_info is None	validation	error	litellm, cost-calculation, ocr, usage
OCR response pages_processed is None	validation	error	litellm, cost-calculation, ocr, usage, pricing-data
Model not found in cost map. Tried checking {models_to_check	exception	error	litellm, cost-calculation, image-generation, pricing-data
No pricing information found for model {model}. Tried checki	exception	error	litellm, cost-calculation, image-generation, pricing-data
Model not found in cost map for model={model}	exception	error	litellm, cost-calculation, video-generation, pricing-data
model is required	validation	error	validation, tts, speech, model, input-validation
custom_llm_provider is required	validation	error	validation, tts, provider, routing
input is required	validation	error	validation, tts, input, speech
optional_params is required	validation	error	validation, tts, optional-params
litellm_params is required	validation	error	validation, tts, litellm-params, routing
headers is required	validation	error	validation, tts, headers, dead-code
logging_obj is required	validation	error	validation, tts, logging, type-check
Unmapped response type. Got type: {type(result)}	exception	error	tts, speech, streaming, response-type, type-check
No audio part found in the response	validation	error	tts, speech, audio, model-capability, response-parsing
CREATE eval is not supported for {custom_llm_provider}	validation	error	evals, provider-support, openai, validation
LIST evals is not supported for {custom_llm_provider}	validation	error	evals, provider-support, openai, validation
GET eval is not supported for {custom_llm_provider}	validation	error	evals, provider-support, openai, validation
UPDATE eval is not supported for {custom_llm_provider}	validation	error	evals, provider-support, openai, validation
DELETE eval is not supported for {custom_llm_provider}	validation	error	evals, provider-support, openai, validation, deletion
CANCEL eval is not supported for {custom_llm_provider}	validation	error	evals, provider-support, openai, validation, cancel
CREATE run is not supported for {custom_llm_provider}	validation	error	evals, runs, provider-support, openai, validation
LIST runs is not supported for {custom_llm_provider}	validation	error	evals, runs, provider-support, openai, validation
GET run is not supported for {custom_llm_provider}	validation	error	evals, runs, provider-support, openai, validation
CANCEL run is not supported for {custom_llm_provider}	validation	error	evals, runs, provider-support, openai, validation, cancel
DELETE run is not supported for {custom_llm_provider}	validation	error	evals, provider-support, validation
Missing botocore to use AWS SigV4 authentication. Run 'pip i	exception	error	mcp, aws, import-error, dependencies
No AWS credentials found. Provide aws_access_key_id and aws_	validation	error	mcp, aws, credentials, configuration
stdio_config is required for stdio transport	validation	error	mcp, stdio, configuration, validation
streamable_http_client is not available. Please install mcp	exception	error	mcp, http-transport, dependencies, version-mismatch
logging_obj is required	validation	error	files-api, logging, internal-api-misuse
File content stream does not support sync iteration	exception	error	files-api, streaming, sync-async-mismatch
File content stream does not support async iteration	exception	error	files-api, streaming, sync-async-mismatch
Failed to transform streaming response	validation	error	google-genai, streaming, adapter
Error calling litellm.acompletion for generate_content: {e}	validation	error	google-genai, error-wrapping, adapter
Error calling litellm.completion for generate_content: {e}	validation	error	google-genai, error-wrapping, adapter
Invalid completion response: no choices found	validation	error	google-genai, response-validation, adapter
Invalid completion response: no message found in choice	validation	error	google-genai, response-validation, adapter, tool-calls
litellm_logging_obj is required, but got None	validation	error	google-genai, logging, internal-api-misuse
Use AsyncGoogleGenAIGenerateContentStreamingIterator for asy	exception	error	google-genai, streaming, sync-async-mismatch
Unable to get Image Response. Please pass a valid llm_provid	validation	error	images, provider-support, configuration
image generation config is not supported for {custom_llm_pro	validation	error	image-generation, provider-config, validation, litellm
Model needs to be set for black_forest_labs	exception	error	image-generation, black-forest-labs, required-parameter
Model needs to be set for bedrock	exception	error	image-generation, bedrock, aws, required-parameter
Unmapped LLM provider for this endpoint. You passed model={m	exception	error	image-generation, custom-provider, registration, litellm
Invalid image variation provider: {custom_llm_provider}. Sup	validation	error	image-variations, unsupported-provider, validation
image variation provider has no known model info config - re	validation	error	image-variations, provider-config, version-skew
API key is required for OpenAI image variations	validation	error	image-variations, openai, authentication, api-key
API base is required for OpenAI image variations	validation	error	image-variations, openai, api-base, configuration
API key is required for Topaz image variations	validation	error	image-variations, topaz, authentication, api-key
API base is required for Topaz image variations	validation	error	image-variations, topaz, api-base, configuration
image edit is not supported for {custom_llm_provider}	validation	error	image-edit, unsupported-provider, provider-config
module {__name__!r} has no attribute {name!r}	exception	error	import, attribute-error, lazy-import, python
Missing webhook_url from environment	exception	error	alerting, webhook, environment-variables, slack
Trying to Customize Email Alerting {CommonProxyErrors.not_p	validation	error	alerting, email, licensing, premium, proxy-config
Missing SLACK_WEBHOOK_URL from environment	validation	error	alerting, slack, webhook, environment-variables, digest
Time range must be specified in days, e.g., '7d'	validation	error
Invalid webhook url value for: {webhook_url}. Got type={type	validation	error
Invalid webhook url value for: {webhook_urls}. Got type={typ	validation	error
'litellm.argilla_transformation_object' is required, to log	exception	error
'argilla_transformation_object' must be a dictionary, to log	exception	error
All values in argilla_transformation_object must be a key in	exception	error
Invalid Argilla API Key given. _credentials_api_key=None.	exception	error
api_key and api_base are required for Arize Phoenix prompt i	validation	error
PHOENIX_API_KEY must be set when using Phoenix Cloud (app.ph	validation	error
Invalid identifier {identifier!r}: contains disallowed chara	validation	error
Invalid identifier {identifier!r}: path traversal detected	validation	error
api_key is required	validation	error
api_base is required	validation	error
Access denied to prompt version '{prompt_version_id}'. Check	exception	error
Authentication failed. Check your Arize Phoenix API key and	exception	error
Failed to fetch prompt version '{prompt_version_id}': {e}	exception	error
Error fetching prompt version '{prompt_version_id}': {e}	exception	error
Prompt version '{prompt_version_id}' not found	validation	error
Failed to load prompt version '{prompt_version_id}' from Ari	exception	error
Template '{template_id}' not found	validation	error
Prompt template '{prompt_id}' not found	validation	error	arize-phoenix, prompt-management, configuration, valueerror
prompt_id is required for Arize Phoenix prompt manager	validation	error	arize-phoenix, prompt-management, validation, valueerror
Error compiling prompt '{prompt_id}': {e}	validation	error	arize-phoenix, prompt-management, exception-wrapping, valueerror
AZURE_SENTINEL_DCR_IMMUTABLE_ID is required. Set it as an en	validation	error	azure, azure-sentinel, logging-callback, environment-variables, configuration
AZURE_SENTINEL_ENDPOINT is required. Set it as an environmen	validation	error	azure, azure-sentinel, logging-callback, environment-variables, configuration
AZURE_SENTINEL_TENANT_ID or AZURE_TENANT_ID is required. Set	validation	error	azure, azure-sentinel, entra-id, environment-variables, configuration
AZURE_SENTINEL_CLIENT_ID or AZURE_CLIENT_ID is required. Set	validation	error	azure, azure-sentinel, service-principal, environment-variables, configuration
AZURE_SENTINEL_CLIENT_SECRET or AZURE_CLIENT_SECRET is requi	validation	error	azure, azure-sentinel, secrets, environment-variables, configuration
Missing required environment variable: AZURE_STORAGE_ACCOUNT	validation	error	azure, azure-storage, logging-callback, environment-variables, configuration
Missing required environment variable: AZURE_STORAGE_FILE_SY	validation	error	azure, azure-storage, logging-callback, environment-variables, configuration
bitbucket_config is required for BitBucket prompt integratio	validation	error	bitbucket, prompt-management, configuration, valueerror
Invalid file path {file_path!r}: contains URL special charac	validation	warning	bitbucket, path-validation, security, url-encoding
Invalid file path {file_path!r}: path traversal detected	validation	warning	bitbucket, path-traversal, security, validation
workspace, repository, and access_token are required	validation	error	bitbucket, configuration, authentication, validation
Access denied to file '{file_path}'. Check your BitBucket pe	exception	error	bitbucket, http-403, permissions, authentication
Authentication failed. Check your BitBucket access token and	exception	error	bitbucket, http-401, authentication, credentials
Failed to fetch file '{file_path}': {e}	exception	error	bitbucket, http-error, rate-limit, exception-wrapping
Error fetching file '{file_path}': {e}	exception	error	bitbucket, network, connectivity, exception-wrapping
Access denied to directory '{directory_path}'. Check your Bi	exception	error	bitbucket, http-403, permissions, authentication
Failed to list files in '{directory_path}': {e}	exception	error	bitbucket, http-error, rate-limit, retry
Error listing files in '{directory_path}': {e}	exception	error	bitbucket, network, dns, proxy
Failed to get repository info: {e}	exception	error	bitbucket, api-client, configuration
Failed to get branches: {e}	exception	error	bitbucket, branches, api-client
Failed to get file metadata for '{file_path}': {e}	exception	error	bitbucket, metadata, permissions
Error getting file metadata for '{file_path}': {e}	exception	error	bitbucket, network, proxy, metadata
Failed to load prompt '{prompt_id}' from BitBucket: {e}	exception	error	bitbucket, prompts, configuration
Template '{template_id}' not found	validation	error	bitbucket, prompts, rendering, validation
Prompt template '{prompt_id}' not found	validation	error	bitbucket, prompts, validation
prompt_id is required for BitBucket prompt manager	validation	error	bitbucket, prompts, validation, programming-error
Error compiling prompt '{prompt_id}': {e}	validation	error	bitbucket, prompts, jinja2, error-wrapping
Missing keys={missing_keys} in environment.	exception	error	braintrust, environment-variables, observability, configuration
CloudZero configuration missing. Please set CLOUDZERO_API_KE	validation	error	cloudzero, environment-variables, configuration, cost-analytics
Database not connected. Connect a database to your proxy - h	exception	error	cloudzero, database, prisma, postgres
limit must be an integer	validation	warning	cloudzero, validation, type-error, database
Error retrieving usage data: {e}	exception	error	cloudzero, database, postgres, prisma
CodeInterpreterInterception: no sandbox available. Provide a	validation	error	code-interpreter, sandbox, configuration, tools
CodeInterpreterInterception: no sandbox available to run cod	validation	error	code-interpreter, sandbox, state-management
Cannot route sensitive data without a session_id. Ensure the	validation	error	guardrail, pii, routing, session, litellm-proxy
Sensitive data detected by {self.guardrail_name} (routing sk	exception	error	guardrail, pii, routing, session, blocking
Sensitive data detected by {self.guardrail_name}	exception	error	guardrail, pii, blocking, compliance
Event hook {hook} is not in the supported event hooks {suppo	validation	error	guardrail, config, event-hooks, validation
Event hook {event_hook} is not in the supported event hooks	validation	error	guardrail, config, event-hooks, validation
Guardrail {self.guardrail_name or type(self).__name__} imple	exception	error	packaging, import-error, guardrail, dependencies
Setting tag-based guardrails is only available in litellm-en	exception	error	guardrail, licensing, enterprise, config
DD_API_KEY is not set, set 'DD_API_KEY=<>	exception	error	datadog, logging, env-vars, config
DD_SITE is not set in .env, set 'DD_SITE=<>	exception	error	datadog, logging, env-vars, config
Response from datadog API status_code: {response.status_code	exception	warning	datadog, logging, http, batching
DD_API_KEY is not set, set 'DD_API_KEY=<>'	exception	error	datadog, llm-observability, env-vars, config
DD_SITE is not set, set 'DD_SITE=<>', example sit = `us5.dat	exception	error	datadog, llm-observability, env-vars, config
DD_SITE is not set, set 'DD_SITE=<>', example site = `us5.da	exception	error	datadog, llm-observability, env-vars, empty-value
DataDogLLMObs: Unexpected response - status_code: {response.	exception	warning	datadog, llm-observability, http, batching
DeepEval logging error: {e.response.text}	exception	warning	deepeval, logging, http, authentication
Please set 'CONFIDENT_API_KEY=<>' in your environment variab	validation	error	deepeval, env-vars, callback, config
Invalid environment: {environment}. Please use one of the fo	validation	error	deepeval, env-vars, validation, config
Cannot set prompt_directory when working with prompt_initial	validation	error
Either prompt_directory or prompt_data must be set before us	validation	error
prompt_id is required for dotprompt manager	validation	error
Prompt '{prompt_id}'{version_str} not found in prompt direct	exception	error
Error compiling prompt '{prompt_id}': {e}	exception	error
prompt_id is required when prompt_file is provided	exception	error
Prompt directory does not exist: {self.prompt_directory}	exception	error
Invalid YAML frontmatter: {e}	exception	error
Prompt '{prompt_id}'{version_str} not found. Available promp	exception	error
Error rendering template '{prompt_id}': {e}	exception	error
Invalid type for field '{field_name}': expected {getattr(exp	exception	error
LiteLLM Error, trying to use DynamoDB but not table name pas	exception	error
Not connected to DB!	exception	error
Database not connected. Connect a database to your proxy - h	exception	error
limit must be an integer	exception	error
limit must be non-negative	exception	error
Error retrieving usage data: {exc}	exception	error
Error getting table info: {exc}	exception	error
Provider '{provider}' not supported for Focus export	exception	error
FOCUS_S3_BUCKET_NAME must be provided for S3 exports	exception	error	focus, s3, configuration, env-var, validation
VANTAGE_API_KEY must be provided for Vantage exports	exception	error	focus, vantage, configuration, env-var, validation
VANTAGE_INTEGRATION_TOKEN must be provided for Vantage expor	exception	error	focus, vantage, configuration, env-var, validation
FOCUS_GCS_BUCKET_NAME must be provided for GCS exports	exception	error	focus, gcs, configuration, env-var, validation
Provider '{provider}' not supported for Focus export configu	exception	error	focus, factory, validation, programming-error
bucket_name must be provided for GCS destination	exception	error	focus, gcs, configuration, validation
GCS upload failed: status={response.status_code} body={respo	exception	error	focus, gcs, network, upload, permissions
MAVVRIK_API_ENDPOINT must be an HTTPS URL	exception	error	focus, mavvrik, validation, security, configuration
MAVVRIK_API_ENDPOINT host must be a Mavvrik domain (e.g. htt	exception	error	focus, mavvrik, validation, security, ssrf
Mavvrik FOCUS destination: {label} must be HTTPS, got scheme	exception	error	focus, mavvrik, gcs, security, validation, network
Mavvrik FOCUS destination: {label} must be a GCS endpoint (s	exception	error	focus, mavvrik, gcs, security, ssrf, validation
MAVVRIK_API_KEY must be provided for Mavvrik FOCUS destinati	exception	error	focus, mavvrik, configuration, env-var, validation
MAVVRIK_API_ENDPOINT must be provided for Mavvrik FOCUS dest	exception	error	focus, mavvrik, configuration, env-var, validation
MAVVRIK_CONNECTION_ID must be provided for Mavvrik FOCUS des	exception	error	focus, mavvrik, configuration, env-var, validation
Mavvrik FOCUS destination: connector is disconnected (410).	exception	error	focus, mavvrik, connector, remote-state, http-410
Mavvrik FOCUS destination: register failed ({resp.status_cod	exception	error	focus, mavvrik, network, http, auth
Mavvrik FOCUS destination: failed to get signed URL ({resp.s	exception	error	focus, mavvrik, network, http, retryable
Mavvrik FOCUS destination: response missing 'url' field: {re	exception	error	focus, mavvrik, api-contract, json, network
Mavvrik FOCUS destination: GCS session init failed ({init_re	exception	error	focus, mavvrik, gcs, network, signed-url, retryable
Mavvrik FOCUS destination: GCS session init missing Location	exception	error	focus, mavvrik, gcs, http-headers, proxy, network
Mavvrik FOCUS destination: GCS chunk upload failed (chunk of	exception	error	network, gcs, resumable-upload, mavvrik, focus-export
Mavvrik FOCUS destination: failed to update metricsMarker ({	exception	error	mavvrik, focus-export, http-error, metrics-marker
bucket_name must be provided for S3 destination	validation	error	config, s3, focus-export, validation
api_key must be provided for Vantage destination (set VANTAG	validation	error	config, vantage, env-vars, focus-export, auth
integration_token must be provided for Vantage destination (	validation	error	config, vantage, env-vars, focus-export, auth
Export format '{self.export_format}' not supported. Use 'par	exception	error	config, focus-export, validation, export-format
start_time_utc and end_time_utc must be provided together	validation	error	validation, focus-export, api-misuse, time-window
Unsupported frequency: {self.frequency}	validation	error	config, focus-export, scheduler, validation
GCS Bucket logging is a premium feature. Please upgrade to u	validation	error	licensing, premium, gcs, config, litellm-proxy
start_time_utc is required for getting a payload from GCS Bu	validation	error	gcs, validation, api-misuse, logging-callback
GCS Bucket does not support health check	exception	warning	gcs, health-check, not-implemented, logging-callback
GCS_BUCKET_NAME is not set in the environment, but GCS Bucke	validation	error	gcs, env-vars, config, dynamic-params, logging-callback
Both project_id and topic_id must be provided	validation	error	pubsub, env-vars, config, logging-callback, premium
endpoint not set for GenericAPILogger, GENERIC_LOGGER_ENDPOI	validation	error	generic-api, env-vars, config, logging-callback
Invalid log_format: {log_format}. Must be one of: 'json_arra	validation	error	config, validation, logging, constructor
api_base is required in generic_prompt_config	validation	error	config, prompt-management, validation
prompt_id or prompt_spec is required	validation	error	prompt-management, validation, missing-argument
Failed to fetch prompt '{prompt_id}' from API: {e}	exception	error	network, http, prompt-management
Failed to parse prompt response for '{prompt_id}': {e}	exception	error	http, json, prompt-management, misconfiguration
Error compiling prompt '{prompt_id}': {e}	validation	error	prompt-management, wrapper-exception, runtime
Error compiling prompt '{prompt_id}': {e}, prompt_spec: {pro	validation	error	prompt-management, wrapper-exception, async, runtime
gitlab_config is required for gitlab prompt integration	validation	error	gitlab, prompt-management, config, validation
project and access_token are required	validation	error	gitlab, config, validation, missing-argument
ref must be a non-empty string	validation	error	gitlab, validation, api-misuse
Access denied to file '{file_path}'. Check your GitLab permi	exception	error	gitlab, http-403, permissions, network
Authentication failed. Check your GitLab token and auth_meth	exception	error	gitlab, http-401, authentication, credentials
Failed to fetch file '{file_path}': {e}	exception	error	gitlab, network, http-5xx, runtime
Failed to fetch file '{file_path}' via JSON endpoint: {e}	exception	error	gitlab, http, network, api-client, prompt-management
Failed to list files in '{directory_path}': {e}	exception	error	gitlab, http, network, api-client
Failed to get repository info: {e}	exception	error	gitlab, http, api-client, diagnostics
Failed to get branches: {e}	exception	error	gitlab, http, api-client, branches
Failed to get file metadata for '{file_path}': {e}	exception	error	gitlab, http, metadata, api-client
Failed to load prompt '{encode_prompt_id(prompt_id)}' from G	exception	error	gitlab, prompt-management, litellm, wrapper-exception
Template '{template_id}' not found	validation	error	gitlab, prompt-management, litellm, state
Prompt template '{prompt_id}' not found	validation	error	gitlab, prompt-management, litellm, not-found
prompt_id is required for GitLab prompt manager	validation	error	litellm, prompt-management, gitlab, validation
Error compiling prompt '{prompt_id}': {e}	validation	error	litellm, prompt-management, gitlab, wrapper-exception, jinja
Greenscale Logger Error - No logging URL found	exception	error	litellm, greenscale, logging-callback, configuration
Error getting prompt from Humanloop: {e.response.text}	exception	error	humanloop, prompt-management, litellm, http, api-client
Invalid template message type: {type(template_message)}	validation	error	humanloop, prompt-management, litellm, schema, validation
prompt_id is required for Humanloop integration	validation	error	humanloop, prompt-management, litellm, validation
Missing keys={missing_keys} in environment.	exception	error	lago, litellm, environment, configuration, billing
invalid LAGO_API_CHARGE_BY set	exception	error	lago, litellm, configuration, environment, validation
External Customer ID is not set. Charge_by={charge_by}. User	exception	error	lago, litellm, billing, configuration, identity
[91mLangfuse not installed, try running 'pip install langfu	exception	error	python, langfuse, dependency, observability, callback
Max langfuse clients reached: {litellm.initialized_langfuse_	exception	error	python, langfuse, resource-limit, callback, multi-tenant
LANGFUSE_PUBLIC_KEY and LANGFUSE_SECRET_KEY must be set for	validation	error	python, langfuse, opentelemetry, environment, configuration
[91mLangfuse not installed, try running 'pip install langfu	exception	error	python, langfuse, dependency, prompt-management
prompt_id is required for Langfuse prompt management	validation	error	python, langfuse, prompt-management, validation
Error logging request payload. Payload=none.	exception	warning	python, langsmith, callback, logging, internal-api
LEVOAI_API_KEY environment variable is required for Levo int	validation	error	python, levo, environment, configuration, observability
LEVOAI_ORG_ID environment variable is required for Levo inte	validation	error	python, levo, environment, configuration
LEVOAI_WORKSPACE_ID environment variable is required for Lev	validation	error	python, levo, environment, configuration
LEVOAI_COLLECTOR_URL environment variable is required for Le	validation	error	python, levo, environment, configuration, onboarding
standard_logging_object not found in kwargs	validation	warning	python, literal-ai, callback, logging, internal-api
MAVVRIK_FOCUS_FREQUENCY='{frequency}' is not supported. Only	validation	error	python, mavvrik, focus, configuration, cost-export
HTTP {self.status_code}	http	info	python, mock, testing, http, httpx
Missing keys={missing_keys} in environment.	exception	error	python, openmeter, environment, configuration, usage-tracking
OpenMeter: user is required	exception	error	python, openmeter, user-attribution, callback, proxy
OpenMeter logging error: {e.response.text}	exception	warning	python, openmeter, http, authentication, network
otel.attributes must be a mapping with optional 'include_lis	validation	error	python, opentelemetry, configuration, yaml, validation
otel.attributes: include_list and exclude_list are mutually	validation	error	python, opentelemetry, configuration, yaml, validation
otel.attributes: {TOKEN_TYPE_ATTRIBUTE} is a structural toke	validation	error	python, opentelemetry, metrics, configuration, validation
otel.attributes: unknown attribute name(s) {unknown}. Valid	validation	error
standard_logging_object not found in kwargs	validation	error
OpenTelemetry OTLP HTTP exporter is not available. Install `	exception	error
OpenTelemetry OTLP gRPC exporter is not available. Install `	exception	error
OpenTelemetry OTLP gRPC log exporter is not available. Insta	exception	error
OpenTelemetry OTLP gRPC metric exporter is not available. In	exception	error
Response from opik API status_code: {response.status_code},	exception	error
unknown mapper name {name!r}; known: {known}	validation	error
OpenTelemetry OTLP gRPC metric exporter is not available. In	exception	error
OpenTelemetry OTLP gRPC log exporter is not available. Insta	exception	error
Failed to fetch AgentOps token: {response.text}	exception	error
POSTHOG_API_KEY is not set, set 'POSTHOG_API_KEY=<>'	exception	error
PostHog credentials not found in kwargs	exception	error
Response from PostHog API status_code: {response.status_code	exception	error
standard_logging_object not found in kwargs	validation	error
Configuration validation failed: {all_error_messages}	validation	error
Prometheus exclude configuration validation failed: {errors}	validation	error
Invalid labels for metric '{metric_name}': {invalid_labels}	validation	error
Invalid metric name: {metric_name}	validation	error
standard_logging_object is required, got={standard_logging_p	validation	error	prometheus, metrics, callbacks, standard-logging-object, kwargs
PROMETHEUS_URL not set please set 'PROMETHEUS_URL=<>' in .en	validation	error	prometheus, configuration, environment, metrics
Missing prometheus_client. Run `pip install prometheus-clien	exception	error	prometheus, dependency, installation, callbacks
Promptlayer did not successfully log the response!	exception	warning	promptlayer, logging, api-key, callbacks
Error compiling prompt: {e}. Prompt id={prompt_id}	validation	error	prompt-management, promptlayer, templates, configuration
prompt_id is required for Prompt Management Base class	validation	error	prompt-management, model-alias, configuration
Rubrik webhook URL not configured. Set RUBRIK_WEBHOOK_URL or	exception	error	rubrik, security, webhook, configuration, environment
Cannot normalize tool_call of type {type(tc).__name__}: {tc!	exception	error	rubrik, tool-calls, normalization, provider-compat
{service_name} returned non-dict JSON ({type(result).__name_	exception	error	rubrik, json, response-shape, moderation
Missing boto3 to call bedrock. Run 'pip install boto3'.	exception	error	s3, dependency, botocore, installation, logging
Missing boto3 to call S3. Run 'pip install boto3'.	exception	error	s3, dependency, botocore, download
baseline_model is set for exactly the reverse jobs	validation	error	shadow-eval, pydantic, validation, configuration
sqs_app_encryption_key_b64 is required when encryption is en	exception	error	sqs, encryption, configuration, secrets
LiteLLM Error, trying to use Supabase but url or key not pas	exception	error	supabase, configuration, environment, logging
WANDB_API_KEY must be set for Weave OpenTelemetry integratio	exception	error	weave, wandb, opentelemetry, configuration, environment
WANDB_PROJECT_ID must be set for Weave OpenTelemetry integra	exception	error	weave, wandb, project-config, environment
WebSearchInterception: missing follow-up messages	exception	error	anthropic, web-search, interception, tool-calls, validation
\033[91m wandb not installed, try running 'pip install wandb	exception	error
Interactions API not supported for: {custom_llm_provider}	exception	error
Master key must be 32 bytes for AES-256-GCM	exception	error
process_audio_file does not accept bare str inputs. Pass byt	exception	error
process_audio_file does not accept bare str tuple contents.	exception	error
Unsupported content type in tuple: {type(content)}	exception	error
Tuple must have at least 2 elements: (filename, content)	exception	error
Unsupported audio_file type: {type(audio_file)}	exception	error
Could not extract file content from audio_file	exception	error
calculate_request_duration does not accept bare str inputs.	exception	error
Agentic loop detected repeated tool-call fingerprint; aborti	exception	error
Exceeded max_agentic_loops={max_loops} for model={model}	exception	error
Agentic loop plan missing patched messages	exception	error
Cloud storage object name is required	exception	error
Cloud storage object name must be relative	exception	error
Cloud storage object name contains control characters	exception	error
Cloud storage object name contains an invalid path segment	exception	error
Cloud storage bucket name is required	exception	error	cloud-storage, config, gcs, validation
Cloud storage bucket name must not include a URI scheme or q	validation	error	cloud-storage, config, uri, gcs, validation
Cloud storage bucket name contains control characters	validation	error	cloud-storage, config, control-characters, encoding, gcs
Cloud storage bucket name contains an invalid separator	validation	error	cloud-storage, config, windows, path-separator, gcs
file_id must be a {scheme} URI	validation	error	file-upload, cloud-storage, file-id, validation, security
file_id must include a cloud storage object name	validation	error	file-upload, cloud-storage, file-id, validation
file_id bucket does not match the configured storage bucket	validation	error	file-upload, cloud-storage, bucket-mismatch, config, security
file_id object does not match the configured storage prefix	validation	warning	file-upload, cloud-storage, prefix, legacy-migration, config
file_id must reference a LiteLLM-managed storage object	validation	error	file-upload, cloud-storage, security, prefix, access-control
Invalid duration format	validation	error	duration-parser, budget, validation, config
Unsupported duration unit, passed duration: {duration}	validation	error	duration-parser, budget, units, validation
Monthly resets currently only support 1 month intervals	validation	error	duration-parser, budget, monthly-reset, validation
ContextWindowExceededError: {exception_provider} - {message}	exception	error	context-window, tokens, exception-mapping, provider-error
{exception_provider} - {message}	exception	error	model-not-found, exception-mapping, config, provider-error
ContentPolicyViolationError: {exception_provider} - {message	exception	error	content-policy, moderation, exception-mapping, provider-error
{exception_provider} - {message} This error occurs when lo	exception	error	responses-api, encrypted-content, load-balancing, router, affinity
AuthenticationError: {exception_provider} - {message}	exception	error
NotFoundError: {exception_provider} - {message}	exception	error
Timeout Error: {exception_provider} - {message}	exception	error
InternalServerError: {exception_provider} - {message}	exception	error
BadGatewayError: {exception_provider} - {message}	exception	error
ServiceUnavailableError: {exception_provider} - {message}	exception	error
APIError: {exception_provider} - {message}	exception	error
APIConnectionError: {exception_provider} - {message}	exception	error
AnthropicError - {error_str}	exception	error
AnthropicException - {error_str}	exception	error
AnthropicException BadGatewayError - {error_str}	exception	error
AnthropicException Timeout - {error_str}	exception	error
ReplicateException - {error_str}	exception	error
ReplicateException - {original_exception.message}	exception	error
ReplicateException - {original_exception}	exception	error
{custom_llm_provider.capitalize()}Exception: Authentication	exception	error
{custom_llm_provider.capitalize()}Exception: Context Window	exception	error	context-window, tokens, litellm, input-validation
{custom_llm_provider.capitalize()}Exception: Rate Limit Errr	exception	error	rate-limit, quota, litellm, billing
{custom_llm_provider.capitalize()}Exception - Use 'watsonx_t	exception	error	function-calling, watsonx, bad-request, litellm
BedrockException: Context Window Error - {error_str}	exception	error	bedrock, context-window, tokens, aws, litellm
BedrockException - {error_str} . Enable 'litellm.modify_para	exception	error	bedrock, tools, message-format, converse-api, litellm
BedrockException - {error_str}	exception	error	bedrock, malformed-request, schema, bad-request, litellm
BedrockException - {error_str} . Pass in default user messag	exception	error	bedrock, message-order, converse-api, litellm
BedrockException Invalid Authentication - {error_str}	exception	critical	bedrock, aws, credentials, authentication, litellm
BedrockException PermissionDeniedError - {error_str}	exception	critical	bedrock, aws, iam, permissions, litellm
BedrockException: Rate Limit Error - {error_str}	exception	error	bedrock, throttling, rate-limit, aws, retry, litellm
BedrockException: Timeout Error - {error_str}	exception	error	bedrock, timeout, network, aws, litellm
litellm.BadRequestError: SagemakerException - {error_str}	exception	critical	sagemaker, aws, credentials, bad-request, authentication
SagemakerException - the value of 'n' must be > 0 and <= 2 f	exception	error	sagemaker, aws, bad-request, sampling, validation
SagemakerException - {error_str}	exception	error	sagemaker, aws, context-window, tokens, bad-request
SagemakerException - {original_exception.message}	exception	error	sagemaker, aws, http-500, service-unavailable, retryable
litellm.BadRequestError: {custom_llm_provider}Exception - {e	exception	error	litellm, vertex-ai, gcp, configuration, api-not-enabled
{custom_llm_provider.capitalize()}Exception - {error_str}	exception	error	litellm, vertex-ai, payload-size, context-window, multimodal
ContextWindowExceededError: {custom_llm_provider.capitalize(	exception	error	litellm, vertex-ai, context-window, tokens, prompt-length
{custom_llm_provider.capitalize()}Exception BadRequestError	exception	error	litellm, vertex-ai, permissions, iam, http-403
{custom_llm_provider.capitalize()}Exception ContentPolicyVio	exception	error	litellm, vertex-ai, content-filter, safety, policy
litellm.RateLimitError: {custom_llm_provider.capitalize()}Ex	exception	error	litellm, vertex-ai, rate-limit, http-429, quota
Cloudflare Exception - {original_exception.message}	exception	critical	litellm, cloudflare, authentication, api-token, workers-ai
CohereException - {original_exception.message}	exception	critical	litellm, cohere, authentication, api-key
CohereException - {error_str}	exception	error
{error_str}	exception	error
HuggingfaceException - {original_exception.message}	exception	error
AI21Exception - {original_exception.message}	exception	error
NLPCloudException - {error_str}	exception	error	nlp-cloud, context-window, token-limit, litellm
TogetherAIException - {error_response['error']}	exception	error	together-ai, context-window, max-tokens, token-limit, litellm
TogetherAIException - {error_str}	exception	warning	together-ai, timeout, retryable, litellm
TogetherAIException - {original_exception.message}	exception	error	together-ai, timeout, retry, litellm
AlephAlphaException - {original_exception.message}	exception	error	aleph-alpha, context-window, validation, litellm
OllamaException: Invalid Model/Model not loaded - {original_	exception	error	ollama, model-not-found, local-models, litellm
OllamaException: {original_exception}	exception	critical	ollama, connection, service-unavailable, litellm
VLLMException - {original_exception.message}	exception	critical	vllm, connection, self-hosted, litellm
AzureException ContextWindowExceededError - {message}	exception	error	azure, context-window, validation, litellm
AzureException NotFoundError - {message}	exception	critical	azure, deployment-not-found, configuration, litellm
`invalid_encrypted_content` AzureException - {message} This error occurs when load balancing Responses API	exception	error	azure, responses-api, load-balancing, litellm
AzureException BadRequestError - {message}	exception	error
{exception_provider} AuthenticationError - {message}	exception	error
{exception_provider} APIConnectionError - {message}	exception	error
AzureException - {message}	exception	error
AzureException AuthenticationError - {message}	exception	error
AzureException Timeout - {message}	exception	error
AzureException RateLimitError - {message}	exception	error
AzureException BadGatewayError - {message}	exception	error
AzureException ServiceUnavailableError - {message}	exception	error
AzureException APIError - {message}	exception	error
{exception_provider} APIConnectionError - {message} {_redact	exception	error
{exception_provider} - {error_str}	exception	error
AuthenticationError: {exception_provider} - {error_str}	exception	error
NotFoundError: {exception_provider} - {error_str}	exception	error
Timeout Error: {exception_provider} - {error_str}	exception	error
BadRequestError: {exception_provider} - {error_str}	exception	error
RateLimitError: {exception_provider} - {error_str}	exception	error
ServiceUnavailableError: {exception_provider} - {error_str}	exception	error	http-503, transient, provider-outage, retryable
APIError: {exception_provider} - {error_str}	exception	error	api-error, catch-all, http-status, provider
APIConnectionError: {exception_provider} - {error_str}	exception	error	network, connection, dns, api-base
APITimeoutError - Request timed out. Error_str: {error_str}	exception	error	timeout, client-timeout, streaming, retryable
{exception_provider} BadRequestError : This can happen due t	exception	error	azure, bad-request, api-version, sdk-compat
{original_exception}\n{_redact_string(traceback.format_exc()	exception	error	unmapped-exception, traceback, sdk-version, bug-report
{most_recent_exception_str}. All fallback attempts failed. E	exception	error	fallbacks, exhausted, router, resilience
RSS feed missing <channel> element	validation	warning	rss, parsing, internal-utility, feed-format
model parameter is required but was None. Please provide a v	validation	error	validation, model-none, config, bad-request
api base needs to be a string. api_base={api_base}	validation	error	validation, api-base, type-error, config
dynamic_api_key needs to be a string. Got type={type(dynamic	validation	error	validation, api-key, type-error, secrets
dynamic_api_key needs to be a string. dynamic_api_key={dynam	validation	error	validation, api-key, openai-compatible, secrets
Provider {custom_llm_provider} not found	validation	error	json-providers, registry, custom-provider, config
Unsupported provider config: {transcription_provider_config}	validation	error	litellm, transcription, openai, provider-config, version-mismatch
Unable to health check wildcard model for provider {custom_l	exception	warning	litellm, health-check, wildcard-model, proxy, config
Callback param '{param}' (from {source}) contains an 'os.env	validation	error	litellm, security, callbacks, os-environ, proxy, upgrade
litellm.JSONSchemaValidationError: model={model}, returned a	exception	error	litellm, json-schema, response-format, validation, structured-output
[Non-Blocking] LiteLLM.Success_Call Error: {e}	exception	error	litellm, logging, cost-calculation, success-handler, pricing
No valid endpoint found for Arize, please set 'ARIZE_ENDPOIN	validation	error	litellm, arize, observability, callbacks, environment-variables
LOGFIRE_TOKEN not found in environment variables	validation	error	litellm, logfire, observability, callbacks, environment-variables
Internal Error: Cache cannot be empty - internal_usage_cache	validation	error	litellm, rate-limiting, redis, proxy, configuration
LANGTRACE_API_KEY not found in environment variables	validation	error	litellm, langtrace, observability, callbacks, environment-variables
BitBucket configuration not found. Please set litellm.global	validation	error	litellm, bitbucket, prompt-management, callbacks, configuration
Gitlab configuration not found. Please set litellm.global_gi	validation	error	litellm, gitlab, prompt-management, callbacks, configuration
ARIZE_API_KEY not found in environment variables	validation	error	litellm, arize, observability, callbacks, environment-variables
start_time is required, got={start_time} of type {type(start	validation	error	litellm, logging, type-validation, timestamps, callbacks
end_time is required, got={end_time} of type {type(end_time)	validation	error	litellm, logging, type-validation, timestamps, callbacks
usage is required, got={usage} of type {type(usage)}	validation	error	litellm, logging, usage, type-validation, callbacks
Model {model_info['key']} does not have 'input_cost_per_char	validation	error	litellm, cost-calculation, pricing, model-info, configuration
completion_response must be of type ImageResponse for bedroc	validation	error	bedrock, image-generation, cost-calculation, type-error
judge response is not a JSON object	validation	error	llm-as-a-judge, json-parsing, guardrails, prompt-engineering
Error in response object format	exception	error	streaming, caching, response-conversion
LiteLLM: provider returned a response with no 'choices'. Raw	http	error	streaming, provider-response, choices-missing, api-error
Invalid response object {traceback.format_exc()} received_a	exception	error	response-conversion, catch-all, schema-mismatch, debugging
No active custom logger found for callback name: {callback_n	validation	error	callbacks, observability, configuration, registry
Mock error	exception	error	mocking, testing, embeddings, intentional-error
extract_file_data does not accept bare str inputs. Pass byte	validation	error	files, security, input-validation, migration
Unsupported file content type: {type(file_content)}	validation	error	files, type-error, input-validation
unpack_defs: inlined schema exceeded the {max_inlined_bytes:	validation	error	json-schema, tools, resource-limits, schema-bomb
Unable to determine content type from URL: {url}. Response c	validation	error	vision, images, content-type, url-fetch
file_id and file_data are both None	validation	error	files, message-format, input-validation, anthropic
Failed to parse tool call arguments. Error: {original_error}	validation	error	json, tool-calling, llm-response, parsing
`prompt` must be a non-empty string or a non-empty list of s	validation	error	validation, prompt, chat-api, input
Image url not in expected format. Example Expected input - "	exception	error	vision, image, base64, input
Error rendering template - {e}	exception	error	huggingface, jinja2, chat-template, rendering
No chat template found	exception	error	huggingface, chat-template, async, network
Image url not in expected format. Example Expected input - "	exception	error	vision, image, media-type, validation
Invalid first message. Should always start with 'role'='user	exception	error	anthropic, messages, role-order, validation
function_call missing. Received tool call with 'type': 'func	exception	error	gemini, vertex, tool-calling, history
function_call missing. Received tool call with 'type': 'func	exception	error	gemini, vertex, function-call, legacy
Unable to convert openai tool calls={message} to gemini tool	exception	error	gemini, vertex, tool-calling, conversion
Missing corresponding tool call for tool response message. R	exception	error	gemini, tool-calling, tool-result, history
Unable to parse anthropic tool result for message: {message}	exception	error	anthropic, tool-result, messages, validation
Unable to parse anthropic file message: {message}	exception	error	anthropic, files, content-block, validation
Either file_data or file_id must be present in the file mess	exception	error	anthropic, files, pdf, validation
image conversion failed please run `pip install Pillow`	exception	error	dependencies, pillow, gemini, vision
URL does not point to a valid image (content-type: {content_	validation	error	vision, http, content-type, url
gemini image conversion failed please run `pip install Pillo	exception	error	dependencies, pillow, gemini, vision, base64
Unsupported image format: {image_format}. Supported formats:	validation	error	bedrock, vision, image-format, validation
No supported extensions for MIME type: {mime_type}. Supporte	validation	error	bedrock, documents, mime-type, validation
Unsupported image type. Expected either image url or base64	validation	error	bedrock, image, multimodal, input-validation
Unable to convert openai tool calls={tool_calls} to bedrock	exception	error	bedrock, tool-calls, function-calling, message-format
Unsupported content type: {type(content_block)}	validation	error	bedrock, message-format, content-blocks, input-validation
Bedrock Converse only supports base64-encoded document sourc	validation	error	bedrock, document, pdf, multimodal
Error: Unsupported image format. Format={_img_type}. Support	exception	error	image, url, mime-type, multimodal
data_json.get("error")	exception	error	predibase, streaming, upstream-error, provider
chunk	validation	error	predibase, streaming, error-handling, provider
Unable to parse response. Original response: {chunk}	validation	error	ai21, streaming, schema, legacy
An unknown error occurred with the stream	exception	error	nlp-cloud, streaming, provider, diagnostics
The response was blocked by VertexAI. {chunk}	exception	error	vertex-ai, gemini, safety-filter, streaming
chunk is not a string: {chunk}	validation	error	codestral, mistral, streaming, type-mismatch
{self.custom_llm_provider} raised a streaming error - finish	exception	error	streaming, provider-error, retry, transient
litellm.MidStreamFallbackError: {message}	exception	critical	streaming, fallback, router, transient, network
text and messages cannot both be set	validation	error	token-counter, validation, api-misuse
tools or tool_choice cannot be set if using text	validation	error	token-counter, validation, tools, api-misuse
Either text or messages must be provided	validation	error	token-counter, validation, null-handling
Unsupported type {type(value)} for key tool_calls in message	validation	error	token-counter, tool-calls, validation, schema
Unsupported tool call {tool_call} must contain a function ke	validation	error	token-counter, tool-calls, validation, schema
Unsupported type {type(value)} for key function_call in mess	validation	error	token-counter, function-call, validation, legacy
Unexpected key {key!r}; expected 'tool_calls' or 'function_c	validation	error	token-counter, internal, invariant
Unsupported tokenizer type	validation	error	token-counter, tokenizer, configuration
Invalid detail value: {detail}. Expected 'low', 'high', or '	validation	error	token-counter, image, validation, api-misuse
Missing required key 'url' in image_url dict.	validation	error	token-counter, image, validation, missing-field
Empty image_url string is not valid.	validation	error	token-counter, image, validation, empty-input
Invalid image_url type: {type(image_url).__name__}. Expected	validation	error	token-counter, image, validation, type-error
Anthropic content missing required field: 'type'	validation	error	token-counter, anthropic, validation, missing-field
Unknown Anthropic content type: '{content_type}'	validation	error	token-counter, anthropic, validation, schema
Missing required fields in {content_type} block: {', '.join(	validation	error	token-counter, anthropic, validation, missing-field
Error counting field '{field_name}': {e}	exception	warning	token-counter, anthropic, wrapped-error, fallback
Invalid content item type: {content_type}. Expected str or d	exception	warning	token-counter, content-blocks, validation, forward-compat
Error getting number of tokens from content list: {e}, defau	exception	warning	token-counter, wrapped-error, fallback, validation
{field_name} is required	validation	error	url, validation, valueerror, path-segment
{field_name} cannot be a dot path segment	validation	error	url, path-traversal, security, ssrf, validation
getaddrinfo returned non-string host: {host!r}	exception	error	ssrf, dns, socket, type-narrowing, internal-guard
URL scheme '{parsed.scheme}' is not allowed	exception	error	ssrf, url, scheme, security, validation
URL has no hostname	exception	error	ssrf, url, config, hostname, validation
DNS resolution failed for '{hostname}': {e}	exception	error	ssrf, dns, network, gaierror
No addresses found for '{hostname}'	exception	error	ssrf, dns, resolver, internal-guard
URL targets a blocked address ({resolved_ip}). If this is a	exception	critical	ssrf, security, network, private-ip, dns-rebinding, cloud-metadata
URL scheme is not allowed	exception	error	ssrf, redirect, scheme, security
Origin mismatch on scheme	exception	error	ssrf, redirect, origin, scheme, security
Origin mismatch on host	exception	error	ssrf, redirect, origin, hostname, security
Origin mismatch on port	exception	error	ssrf, redirect, origin, port, security
Redirect response has no Location header	exception	error	ssrf, redirect, http, location-header, malformed-response
Too many redirects	exception	error	ssrf, redirect, redirect-loop, http
No guardrail translation mapping found for call_type: {call_	exception	error	guardrails, mcp, call-type, registry, valueerror
api_base is required for A2A provider	validation	error	a2a, config, api-base, provider, valueerror
At least one message is required for A2A completion	validation	error
Failed to parse A2A response: {e}	http	error
A2A error: {error.get('message', 'Unknown error')}	http	error
image_response must be of type ImageResponse got type={type(	exception	error
Parameter {k} is not supported for model {model}. Supported	validation	error
AIML_API_KEY or AIMLAPI_KEY is not set	validation	error
Missing Anthropic API Key	validation	error
Missing Anthropic API Key - A call is being made to anthropi	validation	error
Batch creation not yet implemented for Anthropic	exception	error
Failed to parse Anthropic batch response: {e}	exception	error
{response_body}	http	error
{e}	http	error
{error_text}	http	error
Provider config not found for model: {model} and provider: {	exception	error
{message}	http	error
Failed to decode JSON from chunk: {chunk}	exception	error	anthropic, streaming, sse, json, proxy
Error receiving chunk from stream: {e}	exception	error	anthropic, streaming, sync, runtimeerror, wrapper
Error parsing chunk: {e}, Received chunk: {chunk}	exception	error	anthropic, streaming, chunk-parsing, sse
Missing required parameter: parameters	validation	error	anthropic, tools, computer-use, validation
Missing required parameter: display_width_px or display_heig	validation	error	anthropic, tools, computer-use, validation
Missing required parameter: name	validation	error	anthropic, tools, hosted-tools, validation
Tool search tool must have a valid name	validation	error	anthropic, tools, tool-search, validation
Advisor tool must have a valid model	validation	error	anthropic, tools, advisor, validation
Unsupported tool type: {tool['type']}	validation	error	anthropic, tools, unsupported-type, validation
defer_loading must be a boolean	validation	error	anthropic, tools, defer-loading, type-validation, config
allowed_callers must be a list of strings	validation	error	anthropic, tools, allowed-callers, type-validation
{completion_response["error"]}	http	error	anthropic, api-error, rate-limit, auth
Unable to get json response - {e}, Original Response: {raw_r	http	error	anthropic, non-json, proxy, gateway, http
ANTHROPIC_API_BASE/ANTHROPIC_BASE_URL or ANTHROPIC_API_KEY/A	validation	error	anthropic, environment, api-key, models, config
Failed to fetch models from Anthropic. Status code: {respons	exception	error
Missing Anthropic API Key - A call is being made to anthropi	validation	error
{raw_response.text}	http	error
{completion_response["error"]}	http	error
Failed to decode JSON from chunk: {chunk}	exception	error
{error_text}	http	error
{e.response.text}	http	error
CountTokens processing error: {e}	http	error
model parameter is required	validation	error
messages parameter is required	validation	error
messages must be a list	validation	error
Message {i} must be a dictionary	validation	error
Message {i} must have a 'role' field	validation	error
Message {i} must have a 'content' field	validation	error
context_management polyfill failed: {e}	http	error
Failed to translate request to OpenAI format	exception	error
Failed to transform streaming response	exception	error
Failed to transform response to Anthropic format	exception	error
Bad Request: model is required for Anthropic Messages Reques	validation	error	anthropic, validation, request-body, pass-through
Bad Request: messages is required for Anthropic Messages Req	validation	error	anthropic, validation, request-body, pass-through
Incompatible tool choice param submitted - {tool_choice}	validation	error	anthropic, tool-choice, translation, validation
context_management.compact_20260112.trigger.value must be at	validation	error	anthropic, context-management, compaction, validation
custom_llm_provider is required for Anthropic messages, pass	validation	error	anthropic, routing, custom-llm-provider, configuration
advisor tool definition must include a 'model' field specify	validation	error	anthropic, advisor, tools, validation
advisor tool definition sets 'api_base' without 'api_key'. A	validation	error	anthropic, advisor, security, ssrf, credentials
advisor tool definition sets 'api_base'={api_base!r}, which	validation	error	anthropic, advisor, security, tls, url-validation
advisor tool definition sets 'api_base' but the proxy has TL	validation	error	anthropic, advisor, security, ssl, dns-rebinding
Invalid reasoning_effort: {reasoning_effort!r}. Must be one	validation	error	anthropic, reasoning-effort, validation, adaptive-thinking
max_tokens is required for Anthropic /v1/messages API	validation	error	anthropic, max-tokens, validation, messages-api
file_id is required in file_content_request	validation	error	anthropic, files, batch, validation
Missing Anthropic API Key	validation	error	anthropic, auth, api-key, files, environment
Anthropic API key is required. Set ANTHROPIC_API_KEY or ANTH	validation	error	anthropic, auth, api-key, files, environment
File data is required	validation	error	anthropic, files, upload, validation
ANTHROPIC_API_KEY or ANTHROPIC_AUTH_TOKEN is required for Sk	validation	error	anthropic, auth, api-key, skills, environment
num must be between {NUM_MIN} and {NUM_MAX}, got {self.num}	validation	error	apiserpent, search, validation, pagination
pages must be between {PAGES_MIN} and {PAGES_MAX}, got {self	validation	error	apiserpent, search, validation, pagination
APISERPENT_API_KEY is not set. Set `APISERPENT_API_KEY` envi	validation	error	apiserpent, auth, api-key, search, environment
Missing boto3 to call AWS Polly. Run 'pip install boto3'.	exception	error	aws, polly, text-to-speech, dependency, boto3
api_key is required for Azure AI Speech transcription.	validation	error	azure, speech, authentication, configuration, env-vars
api_base is required for Azure AI Speech transcription. Use	validation	error	azure, speech, configuration, endpoint, env-vars
Azure AI Speech transcription failed with RecognitionStatus=	http	error	azure, speech, api-error, audio-quality, recognition
Azure AI Speech transcription requires a Cognitive Services	validation	error	azure, speech, endpoint, misconfiguration, validation
Missing model or messages	exception	error	azure, openai, validation, invalid-arguments
max retries must be an int	exception	error	azure, openai, type-error, configuration
azure_client is not an instance of AzureOpenAI or OpenAI	exception	error	azure, openai, internal-invariant, client, type-guard
Unexpected string response from Azure: {response[:500]}	exception	error	azure, openai, version-mismatch, sdk, internal-invariant
Azure client is not an instance of AsyncAzureOpenAI or Async	exception	error	azure, openai, async, client, internal-invariant
Failed to parse raw Azure embedding response: {json_error}	exception	error	azure, embeddings, json, network, retry, connection-leak
embedding_response is not an instance of EmbeddingResponse	exception	error	azure, embeddings, internal-invariant, version-mismatch
Rejected polling URL: {ssrf_err}	exception	critical	azure, security, ssrf, batch, headers, origin-check
Polling response missing 'status' field	exception	error	azure, batch, polling, security, ssrf, api-error
Operation polling timed out.	exception	error
model is not set	exception	error
invalid completion response	exception	error
OpenAI client is not initialized. Make sure api_key is passe	exception	error
OpenAI client is not an instance of AsyncOpenAI. Make sure y	exception	error
Azure client is not an instance of AsyncAzureOpenAI or Async	exception	error
Azure client is not an instance of AzureOpenAI or OpenAI. Ma	exception	error
Azure OpenAI does not support reasoning_effort='none' for th	http	error
Azure does not support 'tool_choice', for api_version={api_v	http	error
Azure does not support '{value}' as a {param} param, for api	http	error
tenant_id, client_id, and client_secret must be provided	validation	error
AZURE_CLIENT_ID and AZURE_TENANT_ID must be set	http	error	azure, configuration, environment-variables, authentication, oidc
OIDC token could not be retrieved from secret manager.	http	error	azure, authentication, oidc, secrets, managed-identity
{req_token.text}	http	error	azure, authentication, oauth2, network, aadsts
Azure AD Token access_token not returned	http	error	azure, oauth2, protocol, proxy
Azure AD Token expires_in not returned	http	error	azure, oauth2, cache, protocol
Azure AD token must be a string, got {type(token)}	exception	error	azure, authentication, type-error, token-provider
Failed to get Azure AD token: {e}	exception	error	azure, authentication, azure-identity, runtime-error, credentials
api_base is required for Azure AI Studio. Please set the api	exception	error	azure, configuration, environment-variables, ai-studio
Missing model or messages	http	error	azure, validation, request-validation, text-completion
max retries must be an int	http	error	azure, validation, retries, type-error
azure_client is not an instance of AzureOpenAI	http	error	azure, client-initialization, type-guard, sdk
{str(e)}	http	error	azure, upstream-error, error-mapping, http
azure_client is not an instance of AsyncAzureOpenAI	http	error	azure, async, client-initialization, type-guard
AzureOpenAI client is not initialized. Make sure api_key is	exception	error	azure, files, authentication, configuration, client-initialization
AzureOpenAI client is not an instance of AsyncAzureOpenAI. M	exception	error	azure, openai, files, async, client-type, validation
Azure OpenAI client is not initialized. Make sure api_key is	exception	error	azure, openai, fine-tuning, credentials, api-key, configuration
OpenAI client is not an instance of AsyncOpenAI. Make sure y	exception	error	azure, openai, fine-tuning, async, client-type, validation
api_base is required for Azure AI Studio. Please set the api	validation	error	azure, openai, image-edit, api-base, configuration, url-construction
Azure api base not found	exception	error	azure, passthrough, proxy, api-base, configuration, router
api_base is required for Azure OpenAI calls	validation	error	azure, openai, realtime, websocket, api-base, configuration
api_version is required for Azure OpenAI calls	validation	error	azure, openai, realtime, websocket, api-version, configuration
api_base is required for Azure WebSocket	validation	error	azure, openai, responses-api, websocket, api-base, configuration
api_base is required for Azure AVA TTS. Format: https://{reg	validation	error	azure, tts, configuration, api-base, validation
{error_msg}: {response.text}	http	error	azure, agents, http-error, foundry, auth
Run {status}: {error_msg}	http	error	azure, agents, run-status, polling, tool-failure
Run timed out waiting for completion	http	error	azure, agents, timeout, polling, long-running
Streaming request failed: {error_text.decode()}	http	error	azure, agents, streaming, http-error, auth
api_base is required for Azure AI Agents. Set it via AZURE_A	validation	error	azure, agents, configuration, api-base, validation
api_key (Azure AD token) is required for Azure Foundry Agent	validation	error	azure, agents, auth, azure-ad, configuration
CountTokens processing error: {e}	exception	error	azure, anthropic, count-tokens, passthrough, wrapped-exception
Missing Azure API Base - Please set `api_base` or `AZURE_API	validation	error	azure, anthropic, configuration, api-base, validation
api_base is required for Azure AI Studio. Please set the api	validation	error	azure, foundry, configuration, api-base, validation
api_base is None. Please set AZURE_AI_API_BASE or dynamicall	validation	error	azure, embeddings, image, configuration, api-base
api_key is None. Please set AZURE_AI_API_KEY or dynamically	validation	error	azure, embeddings, configuration, api-key, auth
/image/embeddings route returned None Embeddings.	exception	error	azure, embeddings, image, empty-response, data-validation
/v1/embeddings route returned None Embeddings.	exception	error	azure, embeddings, empty-response, data-validation, async
Model {model} is not supported for Azure AI image editing.	validation	error	azure, image-edit, model-dispatch, validation, unsupported-model
Azure AI API key is required for model {model}. Set AZURE_AI	validation	error	azure, image-edit, flux, api-key, auth, configuration
FLUX 2 image edit requires a prompt.	validation	error
FLUX 2 image edit requires an image.	validation	error
Empty image list provided	validation	error
Unsupported image type: {type(image)}	validation	error
Azure AI API base is required. Set AZURE_AI_API_BASE environ	validation	error
Parameter {key} is not supported for model {model}. Supporte	validation	error
Invalid size format: '{size}'. Expected format 'WIDTHxHEIGHT	validation	error
Unsupported size value: '{size}'. Use a known size (e.g., '1	validation	error
Azure AI API key is required for model {model}. Set AZURE_AI	validation	error
Azure AI API base is required. Set AZURE_AI_API_BASE environ	validation	error
raw_response.text	http	error
Azure AI API key is required for model {model}. Set AZURE_AI	validation	error
Azure AI API base is required. Set AZURE_AI_API_BASE environ	validation	error
Azure API version is required. Set AZURE_AI_API_VERSION envi	validation	error
api_base is required for Azure AI FLUX 2 image generation	validation	error
api_base is required for Azure AI MAI image generation	validation	error
api_base is required for Azure AI MAI image editing	validation	error
Parameter {k} is not supported for model {model}. Supported	validation	error
Invalid size format: '{size}'. Expected format 'WIDTHxHEIGHT	validation	error
Unsupported size value: '{size}'. Use a known size (e.g., '1	validation	error
raw_response.text	http	error	azure, image-generation, json-parse, upstream-error
Invalid `pages` string for Azure Document Intelligence: {pag	validation	error	azure, document-intelligence, ocr, validation, pages
`pages` must be integers, not booleans	validation	error	azure, document-intelligence, ocr, type-validation, pages
`pages` integers must be >= 0 (Mistral 0-based indices)	validation	error	azure, document-intelligence, ocr, validation, pages, off-by-one
Invalid `pages` list for Azure Document Intelligence: {pages	validation	error	azure, document-intelligence, ocr, validation, pages
`pages` must be a list[int] (0-based, Mistral-style) or a st	validation	error	azure, document-intelligence, ocr, type-validation, pages
Missing Azure Document Intelligence API Key - Set AZURE_DOCU	validation	error	azure, document-intelligence, ocr, authentication, config, environment
Missing Azure Document Intelligence Endpoint - Set AZURE_DOC	validation	error	azure, document-intelligence, ocr, config, environment, endpoint
Expected document dict, got {type(document)}	validation	error	azure, document-intelligence, ocr, validation, request-format
Invalid document type: {doc_type}. Must be 'document_url' or	validation	error	azure, document-intelligence, ocr, validation, request-format
Document URL is required	validation	error	azure, document-intelligence, ocr, validation, request-format
Azure Document Intelligence operation polling timed out afte	exception	error	azure, document-intelligence, ocr, timeout, polling
Azure Document Intelligence analysis failed: {error_msg}	validation	error	azure, document-intelligence, ocr, upstream-error, polling
Unknown operation status: {status}	validation	error	azure, document-intelligence, ocr, polling, api-drift
Failed to parse Azure DI operation response: {e}	validation	error	azure, document-intelligence, ocr, json-parse, polling, authentication
Azure Document Intelligence returned 202 but no Operation-Lo	validation	error	azure, document-intelligence, ocr, headers, proxy, polling
Azure Document Intelligence: rejected polling URL ({ssrf_err	validation	error	azure, document-intelligence, ocr, security, ssrf, proxy, polling
Azure Document Intelligence analysis failed with status: {op	validation	error	azure, document-intelligence, ocr, upstream-error, response-transform
Missing Azure AI API Key - A call is being made to Azure AI	validation	error	azure, ocr, authentication, config, environment
Missing Azure AI API Base - Set AZURE_AI_API_BASE environmen	validation	error	azure, ocr, configuration, missing-parameter
Expected document dict, got {type(document)}	validation	error	azure, ocr, type-error, validation
Azure AI API Base is required. api_base=None. Set in call or	validation	error	azure, rerank, configuration, missing-parameter
Azure AI API Base must be an absolute URL including scheme (	validation	error	azure, rerank, url, configuration
Azure AI API key is required. Please set 'AZURE_AI_API_KEY'	validation	error	azure, rerank, authentication, missing-parameter
api_key is required	validation	error	azure, vector-stores, azure-search, authentication
Azure AI Search service name is required. Provide it via lit	validation	error	azure, vector-stores, azure-search, configuration
embedding_model is required in litellm_params for Azure AI S	validation	error	azure, vector-stores, azure-search, embeddings, configuration
embedding_config is required in litellm_params for Azure AI	validation	error	azure, vector-stores, azure-search, embeddings, configuration
Failed to generate embedding for query: {e}	exception	error	azure, vector-stores, embeddings, wrapper-exception
Failed to convert ModelResponse to ModelResponseStream: {mod	validation	error	streaming, internal, custom-provider, type-error
Error receiving chunk from stream: {e}	exception	error	streaming, sync, runtime-error, network
Error parsing chunk: {e}, Received chunk: {chunk}	exception	error	streaming, sync, json, sse, parsing
Unsupported response_format type - {response_format}	validation	error	response-format, type-error, pydantic, json-schema
api_base is required	validation	error	configuration, url, missing-parameter, base-provider
api_base is required	validation	error	containers, configuration, url, missing-parameter
api_base is required	validation	error	configuration, evals, api-base, url-construction
Invalid Azure Blob Storage URL: {storage_url}	validation	error	azure, blob-storage, url-validation, configuration
Invalid Azure Blob Storage URL format: {storage_url}	validation	error	azure, blob-storage, url-validation, file-download
Filesystem {self.azure_storage_file_system} does not exist	validation	error	azure, blob-storage, container, provisioning
Unsupported storage backend type: {backend_type}. Supported	validation	error	storage, factory, configuration, unsupported-backend
api_base is required	validation	error	image-edit, api-base, configuration, url-construction
ImageVariationConfig implementa 'transform_request_image_var	exception	error	image-generation, image-variation, not-implemented, base-class
ImageVariationConfig implements 'transform_response_image_va	exception	error	image-generation, image-variation, not-implemented, response-parsing
ImageVariationConfig implementa 'transform_request_image_var	exception	error	image-variation, not-implemented, request-pipeline, dispatch
ImageVariationConfig implements 'transform_response_image_va	exception	error	image-variation, not-implemented, response-parsing, dispatch
api_base is required	validation	error	interactions, api-base, configuration, url-construction
{error_message}	http	error	interactions, http-error, error-mapping, upstream
LiteLLM Managed {self.resource_type} with id={unified_resour	exception	error	managed-resources, delete, not-found, idempotency
LLM Router not initialized. Ensure models added to proxy.	exception	critical	managed-resources, router, initialization, proxy
get_complete_url must be implemented by provider	exception	error	ocr, not-implemented, url-construction, provider-config
transform_ocr_request must be implemented by provider	exception	error	ocr, not-implemented, request-pipeline, provider-config
transform_ocr_response must be implemented by provider	exception	error	ocr, not-implemented, response-parsing, provider-config
{error_message}	http	error	realtime, websocket, error-mapping, upstream
{error_message}	http	error	rerank, error-mapping, http-error, upstream
api_base is required	validation	error	responses-api, api-base, configuration, url-construction
{error_message}	http	error	responses-api, http-error, provider-error, litellm
validate_environment must be implemented by provider	exception	error	sandbox, not-implemented, abstract-method, litellm
acreate_sandbox must be implemented by provider	exception	error	sandbox, not-implemented, async, litellm
arun_code must be implemented by provider	exception	error	sandbox, not-implemented, code-execution, litellm
adelete_sandbox must be implemented by provider	exception	error	sandbox, not-implemented, resource-cleanup, litellm
Sandbox output exceeded {SANDBOX_MAX_OUTPUT_BYTES} bytes; ab	validation	error	sandbox, output-limit, memory-safety, value-error, litellm
Refusing to send the server-configured {credential_name} to	validation	error	security, credential-leak, search-api, api-base, value-error, litellm
get_complete_url must be implemented by provider	exception	error	search-api, not-implemented, abstract-method, litellm
transform_search_request must be implemented by provider	exception	error	search-api, not-implemented, request-transform, litellm
transform_search_response must be implemented by provider	exception	error	search-api, not-implemented, response-transform, litellm
api_base is required	validation	error	skills, configuration, api-base, value-error, litellm
api_base is required	validation	error	text-to-speech, configuration, api-base, value-error, litellm
{error_message}	http	error	text-to-speech, http-error, provider-error, litellm
api_base is required	validation	error	vector-store, configuration, api-base, value-error, litellm
{error_message}	http	error	vector-store, http-error, provider-error, litellm
api_base is required	validation	error	vector-store, files, configuration, api-base, value-error, litellm
{error_message}	http	error	vector-store, files, http-error, provider-error, litellm
api_base is required	validation	error	video-generation, configuration, api-base, value-error, litellm
video create character is not supported for this provider	exception	error	video-generation, not-implemented, feature-support, litellm
video get character is not supported for this provider	exception	error
video edit is not supported for this provider	exception	error
video extension is not supported for this provider	exception	error
Unsupported Bedrock audio format for file {processed_audio.f	validation	error
Rust audio transcription bridge is unavailable	exception	error
Invalid AWS region format: {aws_region_name!r}. Region names	validation	error
Invalid web identity token reference.	exception	error
OIDC token could not be retrieved from secret manager.	exception	error
AWS STS rejected the web identity token: {e}.{detail}	exception	error
Missing boto3 to call bedrock. Run 'pip install boto3'.	exception	error
Missing boto3 to call bedrock. Run 'pip install boto3'.	exception	error
Invalid 'bedrock_tags' value. Expected a list of {'key': <st	validation	error
input_file_id is required for Bedrock batch creation	validation	error
AWS IAM role ARN is required for Bedrock batch jobs. Set 'aw	validation	error
Could not determine Bedrock model ID. Please pass `model` in	validation	error
Failed to parse Bedrock batch response: {e}	exception	error
Invalid batch_id format. Expected ARN, got: {batch_id}	validation	error
Invalid ARN format: {batch_id}	validation	error
Invalid region in ARN: {batch_id}	validation	error
Invalid model format. Expected format: 'model=bedrock/agentc	validation	error
Invalid ARN format: {arn}	validation	error
AgentCore: Failed to read/parse JSON response body: {e}	exception	error
Error processing response: {e}	exception	error
Timeout error occurred.	exception	error
Error converting to valid response block={e}. File an issue	exception	error
Invalid model format. Expected format: 'model=agent/AGENT_ID	validation	error
boto3/botocore is required for AWS event stream parsing	exception	error
Error processing response: {e}	exception	error
Timeout error occurred.	http	error
Received streaming error - {e}	exception	error	aws, bedrock, streaming, chunk-parsing, exception-wrapping
Bedrock event-stream shape could not be loaded from botocore	http	critical	aws, bedrock, botocore, dependency, streaming
Failed to decode chunk: {chunk_data}. Error: {e}	validation	error	aws, bedrock, fake-stream, chunk-parsing, valueerror
Unexpected mistral completion response	http	error	aws, bedrock, mistral, response-parsing, converse
Error parsing response: {raw_response.text}, error: {e}	http	error	aws, bedrock, twelvelabs, json-parsing, http
Error setting response content: {e}. Response: {completion_r	http	error	aws, bedrock, twelvelabs, response-mapping, tools
Invalid guardrailConfig={raw_guardrail_config}. Expected for	http	error	aws, bedrock, guardrails, validation, configuration
guardrailConfig={raw_guardrail_config} is missing 'guardrail	http	error	aws, bedrock, guardrails, validation, configuration
Bedrock Invoke HTTPX: Unknown provider={provider}, model={mo	http	error	aws, bedrock, provider-mapping, converse, model-id
Error processing={raw_response.text}, Received error={e}	http	error	aws, bedrock, response-parsing, provider-mapping, model-id
Error parsing received text={outputText}.\nError-{e}	http	warning	aws, bedrock, empty-response, response-mapping, converse
AWS region not set: set AWS_REGION_NAME or AWS_REGION env va	http	error	aws, bedrock, configuration, region, environment
OIDC token could not be retrieved from secret manager.	http	critical	aws, bedrock, oidc, irsa, kubernetes, authentication
Bedrock event-stream shape could not be loaded from botocore	http	critical	aws, bedrock, botocore, dependency, streaming
Invalid S3 URI format: {s3_uri}	validation	error	bedrock, s3, validation, uri
Missing boto3 to call bedrock. Run 'pip install boto3'.	exception	error	bedrock, boto3, dependencies, aws
S3 bucket name is required. Set 's3_bucket_name' parameter o	validation	error	bedrock, s3, configuration, aws
CountTokens processing error: {e}	http	error	bedrock, count-tokens, error-handling, aws
model parameter is required	validation	error	bedrock, count-tokens, validation
messages parameter is required for Converse input	validation	error	bedrock, count-tokens, validation
messages must be a list	validation	error	bedrock, count-tokens, validation, types
Message {i} must be a dictionary	validation	error	bedrock, count-tokens, validation, types
Message {i} must have a 'role' field	validation	error	bedrock, count-tokens, validation
Message {i} must have a 'content' field	validation	error	bedrock, count-tokens, validation
Request must contain content to count tokens	validation	error	bedrock, count-tokens, validation
Invalid data URL format: {data_url[:50]}...	validation	error	bedrock, nova, embedding, data-url, validation
Invalid data URL format (missing comma): {data_url[:50]}...	validation	error	bedrock, nova, embedding, data-url, validation
output_s3_uri is required for async invoke requests	validation	error	bedrock, nova, embedding, s3, async
No embedding data found in response: {response}	validation	error	bedrock, titan, embedding, response-parsing
Missing boto3 to call bedrock. Run 'pip install boto3'.	exception	error	bedrock, boto3, dependencies, aws, embedding
{err.response.text}	http	error	bedrock, embedding, aws, http
Timeout error occurred.	http	error	bedrock, embedding, timeout, network, aws
Unable to map model response to known provider format. model	exception	error	bedrock, embedding, unsupported-model, mapping
Unable to determine bedrock embedding provider for model: {m	exception	error	bedrock, embedding, model-id, validation
Unmapped model. Received={}. Expected={}	exception	error	bedrock, titan, embedding, model-id
Unable to map Bedrock request to provider	exception	error	bedrock, embedding, batch, internal
Failed to get async invoke status: {response.status_code} -	exception	error	bedrock, async-invoke, aws, polling
Input type '{input_type}' requires async_invoke route. Use m	validation	error	bedrock, twelvelabs, embedding, async-invoke, validation
output_s3_uri cannot be empty for async invoke requests	validation	error	bedrock, twelvelabs, async-invoke, s3, validation
file_id is required in file_content_request	validation	error	bedrock, files, s3, validation
Failed to download file from S3: {s3_uri}. Error: {e}	validation	error	bedrock, s3, files, aws, permissions
file_id must be a managed LiteLLM S3 file id	validation	error	bedrock, files, file-id, validation
S3 bucket_name is required. Set 's3_bucket_name' in proxy co	validation	error	bedrock, files, s3, configuration, proxy
file content is required	validation	error	bedrock, files, upload, validation
S3 bucket_name is required. Set 's3_bucket_name' in litellm_	validation	error	bedrock, files, s3, configuration, upload
file is required	validation	error	bedrock, files, upload, validation, multipart
purpose is required	validation	error	bedrock, files, upload, validation
Embedding batch record is missing required `input` field: mo	validation	error
Bedrock batch embedding requires one input per JSONL record.	validation	error
Bedrock Titan v2 batch embedding does not support pre-tokeni	exception	error
Bedrock batch embedding `input` must be a string (or a singl	validation	error
Bedrock batch embedding currently supports only Amazon Titan	exception	error
Batch record for /v1/completions is missing required `prompt	validation	error
Batch record for /v1/responses is missing required `input` f	validation	error
Embedding batch records do not have a chat-completion equiva	validation	error
Unsupported file content type	validation	error
Missing boto3 to call bedrock. Run 'pip install boto3'.	exception	error
Unable to parse S3 URL: {https_url}	validation	error
BedrockFilesConfig does not support file retrieval	exception	error
BedrockFilesConfig does not support file deletion	exception	error
BedrockFilesConfig does not support file listing	exception	error
file_id is required for Bedrock file content retrieval	validation	error
raw_response.text	http	error	bedrock, s3, files, http-error, download
contents of file are None	validation	error	bedrock, files, batch, validation, jsonl
OUTPAINTING requires either a mask image or a mask prompt. P	validation	error	bedrock, nova-canvas, image-edit, outpainting, validation
Unsupported Amazon Nova Canvas taskType: {task_type!r}. Use	validation	error	bedrock, nova-canvas, image-edit, validation, task-type
Amazon Nova Canvas INPAINTING requires either maskPrompt or	validation	error	bedrock, nova-canvas, image-edit, inpainting, validation
Nova Canvas image edit requires an image input	validation	error	bedrock, nova-canvas, image-edit, validation, input-missing
Nova Canvas image edit does not support tuple FileTypes. Pas	validation	error	bedrock, nova-canvas, image-edit, file-types, validation
Amazon Nova Canvas {task_type} requires a text prompt. Pass	validation	error	bedrock, nova-canvas, image-edit, validation, prompt
Unsupported Bedrock image-edit model: {model!r}. Use a stabi	validation	error	bedrock, image-edit, model-routing, validation
Unsupported Bedrock image-edit model: {model!r}. Use a stabi	validation	error	bedrock, image-edit, model-routing, validation
err.response.text	http	error	bedrock, image-edit, http-error, iam, throttling
Timeout error occurred.	http	error	bedrock, image-edit, timeout, network
Error in response object format, got None	validation	error	bedrock, image-edit, response-parsing, defensive
Parameter {k} is not supported for model {model}. Supported	validation	error	bedrock, stability, image-edit, params, validation
Error transforming text to image params: {e}. Got params: {t	validation	error	bedrock, nova-canvas, image-generation, validation, params
Error transforming image generation config: {e}. Got params:	validation	error	bedrock, nova-canvas, image-generation, validation, config
Error transforming color guided generation params: {e}. Got	validation	error	bedrock, nova-canvas, image-generation, color-guided, validation
Error transforming inpainting params: {e}. Got params: {inpa	validation	error	bedrock, nova-canvas, inpainting, image-generation, validation
Task type {task_type} is not supported	exception	error	bedrock, nova-canvas, not-implemented, task-type, image-generation
"; ".join(finish_reasons)	http	error	bedrock, stability, content-filter, image-generation, finish-reason
err.response.text	http	error	bedrock, http-status, image-generation, aws, api-error
Timeout error occurred.	http	error	bedrock, timeout, image-generation, httpx
Error in response object format, got None	validation	error	bedrock, image-generation, response-parsing, json, proxy
No provider config found for model: {model}	validation	error	bedrock, passthrough, provider-config, model-resolution
Invalid invoke provider: {invoke_provider}, for model: {mode	validation	error	bedrock, streaming, invoke, provider-config, model-resolution
Missing aws_sdk_bedrock_runtime. Install with: pip install a	exception	error	bedrock, realtime, import-error, optional-dependency, installation
err.response.text	http	error	bedrock, rerank, http-status, api-error, async
Timeout error occurred.	exception	error	bedrock, rerank, timeout, async
{err.response.text}	exception	error	bedrock, rerank, http-status, api-error
Missing boto3 to call bedrock. Run 'pip install boto3'.	exception	error	bedrock, rerank, import-error, boto3, installation
No results found in the response={response}	exception	error	bedrock, rerank, response-parsing, validation
Bedrock Mantle auth failed: no Bearer token and no usable AW	exception	error
Rejected polling URL: scheme must be https	exception	error
Rejected polling URL: host is not within the bfl.ai domain	exception	error
No image provided	exception	error
Request failed: {e}	exception	error
BFL initial request failed: {initial_response.text}	exception	error
Error parsing initial response: {e}	exception	error
BFL error: {response_data['errors']}	exception	error
No polling_url in BFL response	exception	error
Polling failed: {response.text}	exception	error
Image generation failed: {status}	exception	error
Polling timed out after {max_wait} seconds	exception	error
BFL_API_KEY is not set. Please set it via environment variab	exception	error	bfl, auth, api-key, configuration, image-edit
Unknown BFL image edit model: {model_name}. Supported models	validation	error	bfl, model-name, validation, image-edit
Max recursion depth {max_depth} reached while reading image	validation	error	bfl, image-input, validation, recursion
Unsupported image input: plain string values that are not UR	validation	error	bfl, image-input, validation, file-path, base64
Unsupported image type: {type(image)}. Expected bytes, str (	validation	error	bfl, image-input, type-error, validation, pil, numpy
Error parsing BFL response: {e}	exception	error	bfl, json, response-parsing, proxy, image-edit
No image URL in BFL result	exception	error	bfl, response-parsing, schema, image-edit
Request failed: {e}	exception	error	bfl, network, http, image-generation, sync
BFL initial request failed: {initial_response.text}	exception	error	bfl, http-status, auth, rate-limit, image-generation
Error parsing initial response: {e}	exception	error	bfl, json, response-parsing, proxy, image-generation
BFL error: {response_data['errors']}	exception	error	bfl, api-error, moderation, validation, image-generation
No polling_url in BFL response	exception	error	bfl, schema, polling, response-parsing, image-generation
Polling failed: {response.text}	exception	error	bfl, polling, rate-limit, http-status, image-generation
Image generation failed: {status}	exception	error	bfl, moderation, job-failed, polling, image-generation
Polling timed out after {max_wait} seconds	exception	error	bfl, polling, timeout, sync, image-generation
Parameter {k} is not supported for model {model}. Supported	validation	error	bfl, params, validation, openai-compat
Invalid size format: '{size}'. Expected format 'WIDTHxHEIGHT	validation	error	bfl, size, validation, input-format
BFL_API_KEY is not set. Please set it via environment variab	exception	critical	bfl, auth, api-key, environment
Unknown BFL image generation model: {model_name}. Supported	validation	error	bfl, model-name, validation, routing
Error parsing BFL response: {e}	exception	error	bfl, json, response-parsing, proxy
No image URL in BFL result	exception	error	bfl, response-schema, image-url, image-generation
BRAVE_API_KEY is not set. Set `BRAVE_API_KEY` environment va	validation	critical	brave, auth, api-key, environment, search
param `{key}` is not supported on Bytez	validation	error	bytez, params, validation, openai-compat
kwarg `messages` must be an array of messages that follow th	validation	error	bytez, messages, validation, input
Missing api_key, make sure you pass in your api key	validation	critical	bytez, auth, api-key, environment
{error}	exception	error	bytez, chat, api-error, response-body
{response.text}	exception	error	bytez, streaming, http-status, sync
Prop `type` is not a string	validation	error	bytez, multimodal, messages, validation, content-parts
Prop `{type}` is not supported	validation	error	bytez, multimodal, content-parts, request-validation
Prop `{value_name}` is not a string	validation	error	bytez, multimodal, content-parts, request-validation
`content` can only contain strings or openai content dicts	validation	error	bytez, content-parts, request-validation, serialization
Content must be a string	validation	error	bytez, request-validation, message-format
Failed to request device code: {exc}	exception	error	chatgpt, oauth, device-flow, network, auth
Device code response missing fields: {data}	exception	error	chatgpt, oauth, device-flow, api-contract
Polling failed: {exc}	exception	error	chatgpt, oauth, device-flow, polling, auth
Timed out waiting for device authorization	exception	error	chatgpt, oauth, device-flow, timeout, auth
Token exchange failed: {exc}	exception	error	chatgpt, oauth, token-exchange, pkce, auth
Token exchange response missing fields: {data}	exception	error	chatgpt, oauth, token-exchange, api-contract
Refresh token failed: {exc}	exception	error	chatgpt, oauth, refresh-token, auth, token-expiry
Refresh response missing fields: {data}	exception	error	chatgpt, oauth, refresh-token, api-contract, token-rotation
str(e)	exception	error	chatgpt, auth, oauth, completion
str(e)	exception	error	chatgpt, auth, oauth, responses-api
error_message or raw_response.text	exception	error	chatgpt, responses-api, sse, streaming, parsing
Failed to parse Clarifai response: {e}	exception	error	clarifai, json-parsing, http, auth, proxy
Missing CLOUDFLARE_ACCOUNT_ID - set CLOUDFLARE_ACCOUNT_ID in	validation	error	cloudflare, configuration, environment-variables, api-base
Missing Cloudflare API Key - A call is being made to cloudfl	validation	error	cloudflare, authentication, api-key, configuration
response.text	exception	error	codestral, mistral, streaming, http-error, text-completion
Missing CODESTRAL_API_Key - Please add CODESTRAL_API_Key to	validation	error	codestral, authentication, api-key, configuration
HTTPStatusError - {e.response.text}	exception	error	codestral, async, http-error, httpx
{e}	exception	error	codestral, async, network, timeout
raw_response.text	exception	error	cohere, json-parsing, response-shape, deprecation
raw_response.text	exception	error	cohere, json-parsing, http-error, proxy
api_base is required	validation	error	cohere, configuration, api-base
Failed to decode JSON from chunk: {chunk}	exception	error	cohere, streaming, json-parsing, sse
Error receiving chunk from stream: {e}	exception	error	cohere, streaming, sync, transport
Error parsing chunk: {e}, Received chunk: {chunk}	exception	error	cohere, streaming, sync, json-parsing
Failed to parse v2 chunk: {e}, chunk: {chunk}	exception	error	cohere, streaming, v2, schema-validation
Input must be a list of strings	validation	error
Cohere API key is required. Please set 'COHERE_API_KEY' or '	validation	error
query is required for Cohere rerank	validation	error
documents is required for Cohere rerank	validation	error
raw_response.text	exception	error
query is required for Cohere rerank	validation	error
documents is required for Cohere rerank	validation	error
CometAPI Error: {}	exception	error
KeyError: {e}, Got unexpected response from CometAPI: {chunk	exception	error
raw_response.text	exception	error
image_response must be of type ImageResponse got type={type(	validation	error
Parameter {k} is not supported for model {model}. Supported	validation	error
COMETAPI_KEY or COMETAPI_API_KEY is not set	validation	error
Provider config not found for model: {model} and provider: {	validation	error
model is required for non-openai image variations	validation	error
image variation provider not found: {custom_llm_provider}.	validation	error
Unknown endpoint: {endpoint_name}	validation	error
Unsupported HTTP method: {method}	validation	error
error_msg (upstream response error message)	http	error	http, upstream-error, container-handler, litellm
_body (masked response body)	http	error	http, streaming, masking, litellm
_text (masked response text)	http	error	http, masking, error-handling, litellm
Not implemented yet!	http	error	custom-llm, stub, not-implemented, litellm
DashScope API key is required. Set 'DASHSCOPE_API_KEY' env v	validation	error	auth, api-key, dashscope, embeddings, environment, litellm
Failed to parse DashScope response as JSON: {e}	http	error	dashscope, json, parsing, proxy, embeddings, litellm
message (upstream DashScope response error message)	http	error	dashscope, embeddings, upstream-error, api
DASHSCOPE_API_KEY is not set	validation	error	dashscope, image-generation, authentication, config
DashScope API key is required. Set 'DASHSCOPE_API_KEY' env v	validation	error	dashscope, rerank, authentication, config
query is required for DashScope rerank	validation	error	dashscope, rerank, validation, request
documents is required for DashScope rerank	validation	error	dashscope, rerank, validation, request
raw_response.text (upstream DashScope error body)	http	error	dashscope, rerank, network, upstream-error
response_json.get("message", str(response_json)) (upstream D	http	error	dashscope, rerank, upstream-error, api
No results in DashScope rerank response: {response_json}	http	error	dashscope, rerank, response-schema, upstream-error
Unsupported content type: {type(content)}	exception	error	databricks, chat, validation, request
Unable to get json response - {e}, Original Response: {raw_r	http	error	databricks, chat, response-schema, authentication
KeyError: {e}, Got unexpected response from Databricks: {chu	http	error	databricks, streaming, response-schema
Either set the DATABRICKS_API_BASE and DATABRICKS_API_KEY en	http	error	databricks, config, dependency, authentication
OAuth M2M token request failed: {e}	http	error	databricks, oauth, network, authentication
OAuth M2M token request failed: {response.text}	http	error	databricks, oauth, authentication, credentials
If the Databricks base URL and API key are not set, the data	http	error	databricks, config, dependency, authentication
Missing API Key - A call is being made to LLM Provider but n	exception	error	databricks, authentication, config, custom-endpoint
Missing API Base - A call is being made to LLM Provider but	exception	error	databricks, config, custom-endpoint, base-url
Failed to decode JSON from chunk: {chunk}	validation	error	databricks, streaming, json, network
Error receiving chunk from stream: {e}	exception	error	databricks, streaming, sync, error-handling
DATAFORSEO_LOGIN is not set. Set `DATAFORSEO_LOGIN` environm	validation	error
DATAFORSEO_PASSWORD is not set. Set `DATAFORSEO_PASSWORD` en	validation	error
Error transforming Deepgram response: {e} Response: {raw_res	validation	error
Deepinfra API Base is required. api_base=None. Set in call o	validation	error
Deepinfra API key is required. Please set 'DEEPINFRA_API_KEY	validation	error
{error_message}	http	error
{completion_response["error"]}	exception	error
{json.dumps(completion_response)}	exception	error
Importing google.generativeai failed, please run 'pip instal	exception	error
{str(e)}	exception	error
{traceback.format_exc()}	exception	error
No response received. Original response - {response}	exception	error
E2B API key not set. Set E2B_API_KEY or pass api_key=...	validation	error
Cannot run code from a sandbox id alone. e2b secure sandboxe	validation	error
Error transforming ElevenLabs response: {e} Response: {raw_r	validation	error
ElevenLabs API key is required. Set ELEVENLABS_API_KEY envir	validation	error
ElevenLabs voice_id is required. Pass `voice` when calling `	validation	error
ElevenLabs API key is required. Set ELEVENLABS_API_KEY envir	validation	error
EXA_API_KEY is not set. Set `EXA_API_KEY` environment variab	validation	error
image_response must be of type ImageResponse got type={type(	validation	error
Parameter {k} is not supported for model {model}. Supported	validation	error
Parameter {k} is not supported for model {model}. Supported	validation	error
Parameter {k} is not supported for model {model}. Supported	validation	error
Parameter {k} is not supported for model {model}. Supported	validation	error
Parameter {k} is not supported for model {model}. Supported	validation	error
Parameter {k} is not supported for model {model}. Supported	validation	error
Parameter {k} is not supported for model {model}. Supported	validation	error
Parameter {key} is not supported for model {model}. Supporte	validation	error
Parameter {k} is not supported for model {model}. Supported	validation	error
Parameter {k} is not supported for model {model}. Supported	validation	error
FAL_AI_API_KEY is not set	validation	error
Parameter {k} is not supported for model {model}. Supported	validation	error
CRW_API_KEY is not set. Set `CRW_API_KEY` environment variab	validation	error
Missing Featherless AI API Key	exception	error
FIRECRAWL_API_KEY is not set. Set `FIRECRAWL_API_KEY` enviro	exception	error
FIREWORKS_API_KEY is not set	exception	error
Unable to get json response - {e}, Original Response: {raw_r	http	error
FIREWORKS_API_BASE or FIREWORKS_API_KEY is not set. Please s	exception	error
FIREWORKS_ACCOUNT_ID is not set. Please set the environment	exception	error	fireworks-ai, configuration, environment-variables, model-listing
Failed to fetch models from Fireworks AI. Status code: {resp	http	error	fireworks-ai, http, model-listing, api-errors
FIREWORKS_API_KEY is not set	exception	critical	fireworks-ai, authentication, configuration, environment-variables
FIREWORKS_API_KEY is not set. Please set 'FIREWORKS_API_KEY'	exception	critical	fireworks-ai, rerank, authentication, configuration
query is required for Fireworks AI rerank	exception	error	fireworks-ai, rerank, validation, request-validation
documents is required for Fireworks AI rerank	exception	error	fireworks-ai, rerank, validation, request-validation
No results found in the response={raw_response_json}	exception	error	fireworks-ai, rerank, response-parsing, schema-drift
Missing required fields in the result={result}	exception	error	fireworks-ai, rerank, response-parsing, validation
GDC only accepts a GDCH service account credential as a JSON	exception	error	gdc, authentication, credentials, configuration, google-cloud
When overriding api_base for Gemini agents, you must also su	exception	error	gemini, security, api-base, authentication, agents
Google API key is required. Set GOOGLE_API_KEY or GEMINI_API	exception	critical	gemini, authentication, configuration, environment-variables, agents
{raw_response.text}	http	error	gemini, http, api-errors, agents
GEMINI_API_BASE or GEMINI_API_KEY/GOOGLE_API_KEY is not set.	exception	error	gemini, authentication, model-listing, configuration
Failed to fetch models from Gemini. Status code: {response.s	http	error	gemini, http, model-listing, api-errors
Unexpected error during token counting: {e}	exception	error	gemini, token-counting, response-parsing, exception-handling
GEMINI_API_KEY is required for Google AI Studio file operati	exception	critical	gemini, files, authentication, configuration
api_base is required	exception	error	gemini, files, configuration, api-base
api_key is required	exception	critical	gemini, files, authentication, configuration
File data is required	exception	error	gemini, files, validation, request-validation
Error parsing file upload response: {e}	exception	error	gemini, files, response-parsing, upload
Error parsing file retrieve response: {e}	exception	error
Failed to delete file: {raw_response.text}	exception	error
Error parsing file delete response: {e}	exception	error
GoogleAIStudioFilesHandler does not support file listing	exception	error
GoogleAIStudioFilesHandler does not support file content ret	exception	error
GEMINI_API_KEY is not set	exception	error
Gemini image edit requires at least one image.	exception	error
Unsupported image type for Gemini image edit.	exception	error
image_response must be of type ImageResponse got type={type(	validation	error
GEMINI_API_KEY is not set	exception	error
Google API key is required. Set GOOGLE_API_KEY or GEMINI_API	validation	error
Either 'model' or 'agent' must be provided	validation	error
{raw_response.text}	http	error
Google API key is required	validation	error
api_key is required for Gemini API calls	validation	critical	auth, gemini, realtime, websocket, api-key, config
Unexpected part type: {part}	validation	error	gemini, realtime, parsing, event-mapping, compatibility
Unexpected model turn event, no 'parts' key: {model_turn}	validation	error	gemini, realtime, parsing, event-mapping, schema
Unexpected delta type: {delta_type}	validation	error	gemini, realtime, event-mapping, internal, modality
Invalid JSON message: {message_str}	validation	error	gemini, realtime, json-parsing, client-input, validation
Error transforming content delta events: {e}, got message: {	validation	error	gemini, realtime, parsing, streaming, error-wrapping
Error updating current delta chunks: {e}, got transformed_me	validation	error	gemini, realtime, state-management, internal, type-mismatch
Error updating current item chunks: {e}, got transformed_mes	validation	error	gemini, realtime, state-management, internal, type-mismatch
Unknown openai event: {key}, value: {value}	validation	error	gemini, realtime, event-mapping, compatibility, versioning
Unknown openai event: {openai_event}	validation	error	gemini, realtime, event-mapping, internal, versioning
Unknown message type: {message_str}	validation	warning	gemini, realtime, event-mapping, compatibility, unknown-frame
GEMINI_API_BASE is not set	validation	error	gemini, vector-stores, config, api-base, file-search
GEMINI_API_KEY or GOOGLE_API_KEY is required	validation	error	auth, gemini, vector-stores, api-key, file-search
GEMINI_API_KEY or GOOGLE_API_KEY is required for Veo video g	validation	error	auth, gemini, veo, video-generation, api-key, config
Failed to parse operation response: {e}	validation	error	gemini, veo, video-generation, pydantic, schema, parsing
No operation name in Veo response: {response_data}	validation	error
Video generation is not complete yet. Please check status wi	validation	error
No response data in completed operation	validation	error
Video remix is not supported by Google Veo. Please use video	exception	error
Video remix is not supported by Google Veo.	exception	error
Video list is not supported by Google Veo. Use the operation	exception	error
Video list is not supported by Google Veo.	exception	error
Video delete is not supported by Google Veo. Videos are auto	exception	error
Video delete is not supported by Google Veo.	exception	error
video create character is not supported for Gemini	exception	error
video get character is not supported for Gemini	exception	error
video edit is not supported for Gemini	exception	error
video extension is not supported for Gemini	exception	error
GigaChat credentials not provided. Set GIGACHAT_CREDENTIALS	exception	error
GigaChat authentication failed: {e.response.text}	exception	error
GigaChat authentication request failed: {e}	exception	error	gigachat, authentication, network, httpx, timeout, oauth
Invalid token response: {data}	exception	error	gigachat, authentication, oauth, response-parsing, api-contract
Invalid JSON response: {raw_response.text}	exception	error	gigachat, response-parsing, json, proxy, httpx
Failed to get access token after 3 attempts	exception	critical	github-copilot, oauth, device-flow, authentication, retry-exhausted
API key response missing token	exception	error	github-copilot, authentication, token-refresh, json, cache
Failed to save API key: {e}	exception	error	github-copilot, filesystem, permissions, docker, cache, oserror
Failed to refresh API key: {e}	exception	critical	github-copilot, authentication, token-refresh, retry-exhausted, oauth
Failed to refresh API key after maximum retries	exception	critical	github-copilot, authentication, token-refresh, retry-exhausted, rate-limit
str(e)	exception	critical	github-copilot, authentication, oauth, chat, wrapper
GitHub Copilot API key is required. Please authenticate via	exception	critical	github-copilot, embedding, authentication, oauth, empty-token
str(e)	exception	critical	github-copilot, embedding, authentication, oauth, wrapper
str(e)	exception	critical	github-copilot, messages-api, authentication, oauth, wrapper
GitHub Copilot API key is required. Please authenticate via	exception	critical	github-copilot, responses-api, authentication, oauth, empty-token
str(e)	exception	critical	github-copilot, responses-api, authentication, oauth, wrapper
GOOGLE_PSE_API_KEY is not set. Set `GOOGLE_PSE_API_KEY` envi	validation	error	google-pse, search, api-key, configuration, environment
GOOGLE_PSE_ENGINE_ID is not set. Set `GOOGLE_PSE_ENGINE_ID`	validation	error	google-pse, search, configuration, engine-id, environment
GOOGLE_PSE_API_KEY is required	validation	error	google-pse, search, api-key, configuration, host-aware-resolution
GOOGLE_PSE_ENGINE_ID is required	validation	error	google-pse, search, engine-id, configuration, environment
GradientAI API key not found	validation	error	gradient-ai, authentication, configuration, api-key, env-vars
error.get("message")	http	error	groq, streaming, error-forwarding, rate-limit, api-key
No api base was set. Please provide an api_base, or set the	exception	error	heroku, configuration, api-base, env-vars
file_id or file_data is required	validation	error	hosted-vllm, multimodal, validation, video, message-format
api_base is required for hosted_vllm embeddings	validation	error	hosted-vllm, embeddings, api-base, configuration, env-vars
api_base must be provided for Hosted VLLM rerank	validation	error	hosted-vllm, rerank, api-base, configuration
Hosted VLLM does not support max_chunks_per_doc	validation	error	hosted-vllm, rerank, parameters, validation, cohere-compat
query is required for Hosted VLLM rerank	validation	error	hosted-vllm, rerank, validation, required-params
documents is required for Hosted VLLM rerank	validation	error	hosted-vllm, rerank, validation, required-params
Error parsing response: {raw_response.text}, status_code={ra	http	error	hosted-vllm, rerank, response-parsing, gateway, http
No results found in the response={response}	http	error	hosted-vllm, rerank, response-schema, validation
Missing required fields in the result={result}	http	error	hosted-vllm, rerank, response-schema, validation, version-skew
api_base not set for Hosted VLLM responses API. Set via api_	validation	error	hosted-vllm, responses-api, api-base, configuration, env-vars
api_base must be provided for Hosted VLLM rerank	validation	error	hosted-vllm, transcription, audio, api-base, configuration, misleading-message
No provider mapping found for model {model}	http	error	huggingface, inference-providers, model-availability, hub-api
Failed to fetch provider mapping: {e}	http	error	huggingface, network, rate-limit, hub-api, proxy, httpx
Invalid task_type={task_type}. Expected one of={hf_tasks_emb	exception	error	huggingface, embeddings, task-type, validation
sentence-similarity requires 2+ sentences	validation	error	huggingface, embeddings, validation, input-validation
reranker requires 2+ sentences	validation	error	huggingface, rerank, validation, input-validation
sentence transformers requires 2+ sentences	validation	error	huggingface, embeddings, validation, empty-input, misleading-message
{embeddings[error]}	http	error	huggingface, embeddings, upstream-error, api, auth
Invalid hf task - {task}. Valid formats - {hf_tasks}.	validation	error	huggingface, completion, validation, task-parameter
response is not in expected format - {completion_response}	http	error	huggingface, completion, response-format, tgi
Original Response received: {raw_response.text}	http	error	huggingface, completion, response-format, gateway, json
{completion_response[error]}	http	error	huggingface, completion, upstream-error, auth
query is required for HuggingFace rerank	validation	error	huggingface, rerank, validation, missing-parameter
Cohere 'documents' param is required for HuggingFace rerank	validation	error	huggingface, rerank, validation, missing-parameter
{raw_response.text}	http	error	huggingface, rerank, response-format, gateway, json
api_base is required for Infinity embeddings	validation	error	infinity, embeddings, configuration, api-base, self-hosted
{raw_response.text}	http	error	infinity, embeddings, response-format, self-hosted, json
api_base is required for Infinity rerank	validation	error	infinity, rerank, configuration, api-base, self-hosted
{raw_response.text}	http	error	infinity, rerank, response-format, self-hosted, json
No results found in the response={raw_response_json}	http	warning	infinity, rerank, dead-code, logic-bug, response-format
{raw_response.text}	http	error	jina-ai, rerank, upstream-error, auth, quota
No results found in the response={_json_response}	http	error	jina-ai, rerank, response-format, schema-drift
api_key is required. Set via `api_key` parameter or `JINA_AP	validation	error	jina-ai, rerank, configuration, auth, missing-api-key
flow_id cannot be set via request parameters; use model lang	validation	error	langflow, validation, security, config
flow_id is required; use model langflow/{flow_id}	validation	error	langflow, validation, config
api_base is required for LangFlow. Set it via LANGFLOW_API_B	validation	error	langflow, config, environment
tweaks cannot be set via request parameters; they would over	validation	error	langflow, validation, security, config
LangFlow returned a non-JSON response: {e}	http	error	langflow, network, response-parsing
Could not extract a message from the LangFlow response; ensu	http	error	langflow, response-parsing, config
api_base is required for LangGraph. Set it via LANGGRAPH_API	validation	error	langgraph, config, environment
str(response.read())	http	error	langgraph, streaming, http
str(await response.aread())	http	error	langgraph, streaming, async, http
Error processing response: {e}	exception	error	langgraph, response-parsing, compatibility
LEMONADE_API_BASE is not set. Please set the environment var	validation	error	lemonade, config, environment
Failed to fetch models from Lemonade. Set Lemonade API Base	exception	error	lemonade, network, config
Failed to fetch models from Lemonade. Status code: {response	http	error	lemonade, http, config
LINKUP_API_KEY is not set. Set `LINKUP_API_KEY` environment	validation	error	linkup, authentication, environment
api_base not set for LiteLLM Proxy route. Set in env via `LI	validation	error	litellm-proxy, config, environment
api_base not set for LiteLLM Proxy route. Set in env via `LI	validation	error	litellm-proxy, images, config
api_base not set for LiteLLM Proxy route. Set in env via `LI	validation	error	litellm-proxy, images, config
api_base not set for LiteLLM Proxy responses API. Set via ap	validation	error	litellm-proxy, responses-api, config
Prisma client is not initialized. Database connection requir	validation	error	litellm-proxy, database, skills, prisma
Unable to record skill ownership: caller has no identity sco	validation	error	litellm-proxy, authentication, skills, multi-tenancy
Skill not found: {skill_id}	validation	error
Manus API key is required. Set MANUS_API_KEY environment var	validation	error
File data is required	validation	error
Error parsing Manus file response: {e}	exception	error
Manus API key is required. Set MANUS_API_KEY environment var	validation	error
raw_response.text	http	error
MILVUS_API_KEY is not set. Either set it in the litellm_para	validation	error
Milvus API base URL is required. Set MILVUS_API_BASE environ	validation	error
embedding_model is required in litellm_params for Milvus. Yo	validation	error
embedding_config is required in litellm_params for Milvus. Y	validation	error
Failed to generate embedding for query: {e}	exception	error
MiniMax API key is required. Set MINIMAX_API_KEY environment	validation	error
MiniMax TTS error: {error_detail}	http	error
URL output format is not yet supported. Use 'hex' format or	exception	error
No audio data in MiniMax response. Response keys: {list(resp	exception	error
Failed to decode audio data: {e}	exception	error
Failed to parse MiniMax response: {e}	exception	error	minimax, text-to-speech, json-parse, api-key, configuration
Error processing MiniMax response: {e}	exception	error	minimax, text-to-speech, wrapper-exception, audio
raw_response.text	http	error	mistral, audio-transcription, json-parse, api-key
Missing Mistral API Key - A call is being made to Mistral bu	validation	error	mistral, ocr, api-key, configuration, environment
Expected document dict, got {type(document)}	validation	error	mistral, ocr, type-validation, request-format
MODELSCOPE_API_KEY is not set. Please set it via environment	validation	error	modelscope, image-generation, api-key, configuration
NIMBLE_API_KEY is not set. Set `NIMBLE_API_KEY` environment	validation	error	nimble, web-search, api-key, configuration
{raw_response.text}	http	error	nlp-cloud, chat, json-parse, gateway
{completion_response["error"]}	http	error	nlp-cloud, chat, upstream-error, model-name
{json.dumps(completion_response)}	http	error	nlp-cloud, chat, response-shape, parsing
Missing Novita AI API Key - A call is being made to novita b	validation	error	novita, api-key, configuration, chat
top_n must be a positive integer, got: {top_n!r}	validation	error	nvidia-nim, rerank, parameter-validation, top-n
Nvidia NIM API key is required. Please set 'NVIDIA_NIM_API_K	validation	error	nvidia-nim, rerank, api-key, configuration
query is required for Nvidia NIM rerank	validation	error	nvidia-nim, rerank, missing-parameter, query
documents is required for Nvidia NIM rerank	validation	error	nvidia-nim, rerank, missing-parameter, documents
{raw_response.text}	http	error	nvidia-nim, rerank, json-parse, api-base
numpy is required for Riva audio resampling. Install Riva ST	exception	error	nvidia-riva, audio-transcription, numpy, dependency, resampling
Could not decode audio for Riva STT. Install audio extras (`	http	error	nvidia-riva, audio-transcription, audio-format, dependency, soundfile
Audio decode produced no samples.	http	error	nvidia-riva, audio-transcription, empty-file, corrupt-audio
Could not decode audio for Riva STT. Convert your audio to w	http	error	nvidia-riva, audio-transcription, audio-format, ffmpeg, decode-error
NVIDIA Riva requires `api_base` (host:port for the gRPC endp	http	error	configuration, nvidia-riva, speech-to-text, grpc, missing-parameter
NVIDIA Riva client is not installed. Install with `pip insta	exception	error	dependencies, nvidia-riva, import-error, speech-to-text, environment
Response cannot be casted to CohereChatResult: {e}	http	error	oci, cohere, response-parsing, schema-drift, pydantic
Chunk cannot be parsed as CohereStreamChunk: {e}	http	error	oci, cohere, streaming, sse, response-parsing
Each content item must be a dictionary	validation	error	oci, input-validation, openai-compat, messages
Each content item must have a string `type` field	validation	error	oci, input-validation, content-parts, openai-compat
Content type `{item_type}` is not supported by OCI	validation	error	oci, unsupported-feature, multimodal, input-validation
Content item of type `text` must have a string `text` field	validation	error	oci, input-validation, content-parts, type-mismatch
Prop `image_url` must be a string or an object with a `url`	validation	error	oci, input-validation, vision, content-parts
Each tool call must be a dictionary	validation	error	oci, input-validation, tool-calls, openai-compat
OCI only supports function tool calls	validation	error	oci, tool-calls, unsupported-feature, input-validation
Tool call `id` must be a string	validation	error	oci, tool-calls, input-validation, missing-parameter
Tool call `function` must be a dictionary	validation	error	oci, tool-calls, input-validation, structure
Tool call `function.name` must be a string	validation	error	oci, tool-calls, input-validation, missing-parameter
Tool call `function.arguments` must be a JSON string	validation	error	oci, tool-calls, input-validation, json-serialization
Message `tool_calls` must be a list	validation	error	oci, input-validation, tool-calls, structure
Message `content` must be a string or list of content parts	validation	error	oci, input-validation, messages, type-mismatch
Tool result message must have a string `tool_call_id`	validation	error	oci, tool-calls, input-validation, missing-parameter
Tool result message `content` must be a string	validation	error	oci, tool-calls, input-validation, type-mismatch
OCI only supports function tools	validation	error
Tool `function` must be a dictionary	validation	error
Response cannot be casted to OCICompletionResponse: {e}	http	error
OCI response contained no choices	http	error
Chunk cannot be parsed as OCIStreamChunk: {e}	exception	error
OCI returned image content in a streaming response — not sup	exception	error
Unsupported content type in OCI streaming response: {item.ty	exception	error
Invalid tool_choice for OCI: missing or non-string 'type' in	exception	error
Invalid tool_choice for OCI: 'FUNCTION' type requires a non-	exception	error
Invalid tool_choice for OCI: unsupported type {raw_type!r};	exception	error
Invalid tool_choice for OCI: expected str or dict, got {type	exception	error
response_format type 'json_schema' requires a 'json_schema'	exception	error
param `{key}` is not supported on OCI	exception	error
kwarg `messages` must be an array of messages that follow th	exception	error
Missing required parameters: oci_user, oci_fingerprint, oci_	exception	error
oci_compartment_id is required for OCI chat requests. Pass i	exception	error
kwarg `oci_serving_mode` must be either 'ON_DEMAND' or 'DEDI	exception	error
No user message found — Cohere models require at least one u	exception	error
Invalid response format from OCI	exception	error
{response_json["error"]}	exception	error
{e.response.text}	exception	error	oci, streaming, http, authentication, rate-limit
{response.text}	exception	error	oci, streaming, http, status-code
Chunk is not a string: {chunk}	exception	error	oci, streaming, sse, type-validation
Chunk does not start with 'data:': {chunk}	exception	error	oci, streaming, sse, parsing
Chunk cannot be parsed as JSON: {e}	exception	error	oci, streaming, sse, json, parsing
cryptography package is required for OCI authentication. Ple	exception	critical	oci, dependencies, import-error, packaging
The provided private key is not an RSA key, which is require	exception	critical	oci, authentication, rsa, crypto, credentials
Private key file not found: {file_path}	exception	critical	oci, authentication, file-not-found, configuration
Failed to read private key file '{file_path}': {e}	exception	critical	oci, authentication, permissions, deployment
Private key file is empty: {file_path}	exception	critical	oci, authentication, secrets, ci, configuration
Invalid OCI region {region!r}: must match ^[a-z][a-z0-9-]{{0	exception	error	oci, configuration, validation, region
Unsupported HTTP method: {method}	exception	warning	oci, validation, http-method, signing
Failed to sign request with provided oci_signer: {e}. The si	exception	error	oci, signing, sdk, interface-mismatch
Missing required OCI credentials: oci_user, oci_fingerprint,	exception	critical	oci, authentication, credentials, environment, configuration
oci_key must be a string containing the PEM private key cont	exception	error	oci, authentication, type-validation, secrets
Private key is required for OCI authentication. Provide eith	exception	critical	oci, authentication, credentials, validation
Missing required parameters: oci_user, oci_fingerprint, oci_	exception	critical	oci, embeddings, credentials, compartment, configuration
oci_compartment_id is required for OCI embedding requests. P	exception	critical	oci, embeddings, compartment, configuration, validation
OCI embedText does not support token-array inputs. Convert t	exception	error	oci, embedding, input-validation, tokens
OCI embedText accepts at most {OCI_EMBED_BATCH_LIMIT} inputs	exception	error	oci, embedding, batch-limit, input-validation
oci_serving_mode must be 'ON_DEMAND' or 'DEDICATED'.	exception	error	oci, embedding, configuration, serving-mode
raw_response.text	exception	error	oci, embedding, upstream-error, http
Failed to parse OCI embed response as JSON: {e}	exception	error	oci, embedding, json, proxy, response-parsing
OCI embed response does not match expected schema: {e}	exception	error	oci, embedding, schema, response-parsing, provider-mismatch
KeyError: {e}, Got unexpected response from Ollama: {chunk}	exception	error	ollama, streaming, keyerror, response-parsing
ollama image conversion failed please run `pip install Pillo	exception	error	ollama, vision, pillow, dependencies, images
Ollama Error - {chunk}	exception	error	ollama, streaming, text-completion, upstream-error
API Base not set. Set one via completion(..,api_base='your-a	exception	error	oobabooga, api-base, configuration
completion_response["error"]	exception	error	oobabooga, embedding, upstream-error
raw_response.text	exception	error	oobabooga, json, response-parsing, configuration
completion_response["error"]	exception	error	oobabooga, upstream-error, chat
str(e)	exception	error	oobabooga, response-parsing, schema, chat
Unable to get json response - {e}, Original Response: {raw_r	exception	error	openai, json, response-parsing, api-base, proxy
Failed to get models: {response.text}	exception	error	openai, models, authentication, http
error_message	exception	error	openai, streaming, vllm, upstream-error, in-band-error
Missing model or messages	exception	error	openai, text-completion, input-validation
error_text	exception	error	openai, text-completion, error-wrapping, http
Error in response object format	exception	error
error_message	exception	error
OPENAI_API_KEY is required for Evals API	exception	error
OpenAI client is not initialized. Make sure api_key is passe	exception	error
OpenAI client is not an instance of AsyncOpenAI. Make sure y	exception	error
raw_response.text	exception	error
Parameter {k} is not supported for model {model}. Supported	exception	error
Parameter {k} is not supported for model {model}. Supported	exception	error
Parameter {k} is not supported for model {model}. Supported	exception	error
error_text	exception	error
image variation provider not found: {custom_llm_provider}.	exception	error
data field is required, for openai image variations. Got={da	exception	error