Addresses three open CodeRabbit findings on PR #1983.
- Provider::Anthropic Langfuse rescue branches no longer include
`e.full_message` in `Rails.logger.warn`. `full_message` bundles the
backtrace + cause chain and on some SDK error types includes the
serialized request/response payload (prompt, model output). Logs
now report `#{e.class}: #{e.message}` only. Three sites:
create_langfuse_trace, log_langfuse_generation, upsert_langfuse_trace.
Note: Provider::Openai has the same pattern (copy-pasted source) —
harmonization deferred to a follow-up cleanup PR; this commit fixes
only the Anthropic provider to keep PR scope tight.
- MessageFormatter#parse_arguments now coerces any non-Hash parsed
result to `{}`. Anthropic's Messages API requires `tool_use.input`
to be a JSON object (map); a stored ToolCall::Function record whose
arguments parse to a scalar, bool, or array (corrupt row, legacy
data, cross-provider bleed) would otherwise produce a payload the
API rejects. Normal flow stores Hash arguments end-to-end so the
fix is defensive — adds 2 tests covering scalar/array JSON strings
and non-String non-Hash inputs.
- Assistant::Responder dedups the chat-history fetch. The previous
layout fired two near-identical `chat.messages.where(...).includes(
:tool_calls).ordered` queries per LLM turn (one for the OpenAI-shape
payload, one for the raw-records kwarg). A new memoized
`complete_chat_messages` fetches once; `chat_message_records` filters
out the current message via `Array#reject`, `openai_messages_payload`
iterates the cached array unchanged. One SQL query per turn instead
of two. Memoization scope = single Responder instance (per LLM call),
so cache invalidation is not a concern.
All 4370 tests pass (1 pre-existing libvips env error unrelated).
Rubocop + brakeman clean.
- Provider::Anthropic#supports_pdf_processing? bypasses prefix gate for
custom endpoints, mirroring supports_model?
- Provider::Anthropic#initialize raises Error when custom_endpoint? AND
model.blank?, parity with Provider::Openai
- stream_chat_response captures partial usage on mid-stream errors and
records it via the new on_partial callback so chat_response can skip
the duplicate error row in the outer rescue
- safe_accumulated_message swallows the secondary failure when the SDK
cannot reconstruct a snapshot
- langfuse_client memoizes properly (||= instead of =) so repeated calls
don't churn Langfuse instances
- MessageFormatter sorts tool_calls by created_at then id so the
message array is deterministic across replays; skips tool_calls
missing both provider_call_id and provider_id rather than sending
`id: nil` and getting rejected by Anthropic
- Setting.anthropic_access_token default falls back through
ENV["ANTHROPIC_API_KEY"].presence (was missing .presence, so an
empty-string env value bled through)
- User#openai_configured? / #anthropic_configured? delegate to the
Provider::* class methods — single source of truth
- Assistant::Responder renames the OpenAI-shape history builder
conversation_history → openai_messages_payload so the kwarg name
matches the local method name (messages: openai_messages_payload,
conversation_history: chat_message_records)
- Assistant::Builtin stale-history comment updated to reference both
builders
Adds a streaming chat_response test using ad-hoc subclasses of the
SDK event types so the case/when dispatch matches via is_a? without
stubbing class-level === behavior.
Introduces Provider::Anthropic alongside Provider::Openai, implementing
the LlmConcept chat_response contract over the official anthropic Ruby
SDK. Batch ops, PDF, and RAG land in follow-up PRs.
- Provider::Anthropic uses Messages API for sync and streaming responses
- ChatConfig builds requests with ephemeral prompt-cache markers on the
system prompt and the last tool definition
- MessageFormatter reconstructs multi-turn history (text + tool_use +
tool_result blocks) from raw Message records, including the paired
user-role tool_result turn Anthropic requires after every tool_use
- ChatParser maps Anthropic Message into the shared ChatResponse Data
- Registry, Setting, User, Chat default model wired for ANTHROPIC_*
envs and Setting.anthropic_*; LLM_PROVIDER selects between providers
- Responder forwards raw conversation_history (Array<Message>) so
providers without hosted conversation state can rebuild context
- OpenAI provider accepts and ignores the new kwarg (no behavior change)
Tests cover provider init, model gating, MessageFormatter for all turn
shapes, ChatConfig request building (max_tokens, system cache, tool
conversion), ChatParser for text / tool_use / mixed blocks, Registry
discovery, and mocked chat_response success / error / function_request
paths. Live VCR cassettes recorded in a follow-up with a real key.
Stacked PRs: 2/5 batch ops + cost ledger, 3/5 PDF, 4/5 pgvector RAG,
5/5 settings UI + disclosure.
* Password reset back button also after confirmation
Signed-off-by: Juan José Mata <juanjo.mata@gmail.com>
* Implement a filter for category (#215)
- Also implement an is empty/is null condition.
* Implement an LLM cost estimation page
Track costs across all the cost categories: auto categorization, auto merchant detection and chat.
Show warning with estimated cost when running a rule that contains AI.
* Update pricing
* Add google pricing
and fix inferred model everywhere.
* Update app/models/llm_usage.rb
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Signed-off-by: soky srm <sokysrm@gmail.com>
* FIX address review
* Linter
* Address review
- Lowered log level
- extracted the duplicated record_usage method into a shared concern
* Update app/controllers/settings/llm_usages_controller.rb
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Signed-off-by: soky srm <sokysrm@gmail.com>
* Moved attr_reader out of private
---------
Signed-off-by: Juan José Mata <juanjo.mata@gmail.com>
Signed-off-by: soky srm <sokysrm@gmail.com>
Co-authored-by: Juan José Mata <juanjo.mata@gmail.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
* Implement support for generic OpenAI api
- Implements support to route requests to any openAI capable provider ( Deepsek, Qwen, VLLM, LM Studio, Ollama ).
- Keeps support for pure OpenAI and uses the new better responses api
- Uses the /chat/completions api for the generic providers
- If uri_base is not set, uses default implementation.
* Fix json handling and indentation
* Fix linter error indent
* Fix tests to set env vars
* Fix updating settings
* Change to prefix checking for OAI models
* FIX check model if custom uri is set
* Change chat to sync calls
Some local models don't support streaming. Revert to sync calls for generic OAI api
* Fix tests
* Fix tests
* Fix for gpt5 message extraction
- Finds the message output by filtering for "type" == "message" instead of assuming it's at index 0
- Safely extracts the text using safe navigation operators (&.)
- Raises a clear error if no message content is found
- Parses the JSON as before
* Add more langfuse logging
- Add Langfuse to auto categorizer and merchant detector
- Fix monitoring on streaming chat responses
- Add Langfuse traces also for model errors now
* Update app/models/provider/openai.rb
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Signed-off-by: soky srm <sokysrm@gmail.com>
* handle nil function results explicitly
* Exposing some config vars.
* Linter and nitpick comments
* Drop back to `gpt-4.1` as default for now
* Linter
* Fix for strict tool schema in Gemini
- This fixes tool calling in Gemini OpenAI api
- Fix for getTransactions function, page size is not used.
---------
Signed-off-by: soky srm <sokysrm@gmail.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: Juan José Mata <juanjo.mata@gmail.com>
