4 Commits

Author	SHA1	Message	Date
Guillem Arias Fauste	8251b7e4d6	feat(ai): add Anthropic provider with chat parity (1/5) (#1983) ... * feat(ai): add Anthropic provider with chat parity (1/5) 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. * fix(ai): address PR review on Anthropic provider foundation Surface fixes raised by Codex + CodeRabbit on PR 1/5: - Provider::Anthropic#chat_response now accepts (and ignores) a `messages:` kwarg. Assistant::Responder passes both `messages:` (OpenAI-shape) and `conversation_history:` (raw Message records) for cross-provider parity, so the previous signature raised ArgumentError on the first chat turn through the Anthropic provider. - Provider::Anthropic#supports_model? bypasses the `claude` prefix gate when a custom base_url is configured, mirroring the OpenAI provider. Bedrock-shaped IDs like `anthropic.claude-sonnet-4-5-20250929-v1:0` and `claude-opus-4@20250514` are otherwise rejected by Assistant::Provided#get_model_provider and the chat dies. - Setting.anthropic_access_token is now in EncryptedSettingFields::ENCRYPTED_FIELDS so the Anthropic API key is encrypted at rest like every other provider secret. Previously plaintext while siblings (openai_access_token, twelve_data_api_key, external_assistant_token) were ciphertext. - Chat.default_model falls back to whichever provider is actually configured. Previously, with LLM_PROVIDER=anthropic but no Anthropic credentials, the default model resolved to a Claude ID that no registered provider supported, so chats failed even when OpenAI was fully configured. Adds Provider::{Anthropic,Openai}#configured? class methods for the readable callsite. - Provider::Anthropic.effective_model uses `ENV["ANTHROPIC_MODEL"].presence || Setting.anthropic_model` so the Setting lookup is only performed when the env var is absent — the previous `ENV.fetch(KEY, default)` evaluated the default arg eagerly on every call. - Provider::Anthropic::ChatConfig#anthropic_input_schema strips both `:strict` and `"strict"` keys so JSON-decoded schemas with string keys cannot leak the OpenAI-only flag through to Anthropic. Test coverage added: supports_model? bypass on custom endpoints, chat_response messages: kwarg compatibility, default_model fallback in the three credential combinations, configured? against ENV + Setting, strict-flag stripping for both key types, and a `Setting.expects(:anthropic_model).never` assertion proving the ENV-precedence test now exercises the lazy path. All 4365 tests pass (1 pre-existing libvips env error unrelated). * test(chat): make default_model tests resilient to ENV model overrides CodeRabbit flagged on PR review: the new default_model tests asserted against Provider::*::DEFAULT_MODEL, but Chat.default_model actually returns Provider::*.effective_model.presence (which reads OPENAI_MODEL / ANTHROPIC_MODEL from the environment). With either env var set, the tests would fail intermittently even though routing was correct. - New default_model tests now assert against the provider's effective_model directly, so they verify the routing decision (which provider's value wins) without coupling to the constant. - Pre-existing "creates with default model" assertions had the same brittleness; switch them to compare against Chat.default_model so the chosen model is whatever the env / Setting cascade resolves to. Verified by running `ANTHROPIC_MODEL=claude-haiku-4-5 OPENAI_MODEL=gpt-4o bin/rails test test/models/chat_test.rb` — 16 runs, 0 failures (previously 2 pre-existing failures + 0 from the new tests). * fix(ai): address local review on Anthropic foundation - 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. * test(ai): add Anthropic tool_use round-trip + multi-tool turn coverage Addresses @jjmata's "worth confirming" note on PR #1983: tool-use turns from prior assistant messages must round-trip correctly when retrieved from the database. - New `ChatParser → ToolCall::Function → MessageFormatter` test walks the full path: Anthropic response with a tool_use block → ChatFunctionRequest → ToolCall::Function.from_function_request → persisted on the AssistantMessage → MessageFormatter rebuild on the next turn. Asserts the original `tool_use.id` is preserved end-to-end as both `tool_use.id` and the paired `tool_result.tool_use_id`, and that the original `input` hash and serialized result content survive. - New multi-tool assistant turn test confirms two tool_use blocks on a single assistant message render as two tool_use blocks followed by two paired tool_result blocks in a single user-role follow-up, matching Anthropic's required alternation. Both tests exercise the existing PR1 code without behavior changes. * test(ai): require "ostruct" explicitly in Anthropic provider tests OpenStruct is moving out of Ruby's default load path (warning in 3.4+, removed in 3.5+). Tests work today because ActiveSupport transitively loads it, but that's incidental. Match the existing convention in test/controllers/settings/hostings_controller_test.rb which explicitly requires ostruct for the same reason. * fix(ai): sanitize Langfuse warn logs, normalize tool_use.input, dedup history fetch 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. * fix(ci): replace sk-ant- prefixed test placeholders Pipelock secret scanner pattern-matches `sk-ant-*` as a real Anthropic API key and fails the PR security-scan check. Test stubs and ClimateControl env values used `sk-ant-test`, `sk-ant-from-setting`, `sk-ant-x`, `sk-ant-y` as obvious placeholders, but the scanner does not care about value entropy. Switched to `fake-anthropic-key-*` / `fake-token-*` strings so the scanner stops flagging them. No production code touched, no behavior change — Provider::Anthropic still accepts any non-blank token.	2026-05-31 16:11:28 +02:00
Michal Tajchert	ccd6a53071	fix(chat): eager pending AssistantMessage to fix Turbo subscribe race (#1657) (#1658) ... * fix(chat): persist eager pending assistant message to fix subscribe race When the LLM replies in ~1-2s the assistant message broadcast could fire before the client's Turbo stream subscription was established, leaving the UI stuck on the thinking indicator while the response was already persisted. Create the AssistantMessage as `pending` synchronously in `Chat#ask_assistant_later`, so it is rendered server-side on the chat show page with a "Thinking ..." inline placeholder. The worker then finds and updates the existing row via `append_text!`, which flips the status to `complete` and broadcasts updates against a DOM id that is already in the page — no race possible. On error, the placeholder is destroyed if no content streamed, otherwise demoted to `failed`. Replaces the standalone thinking indicator partial and the `Assistant::Broadcastable` thinking helpers, both now redundant. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(chat): bind each assistant job to its specific pending placeholder Addressing review feedback on #1658: 1. The pending placeholder lookup based on `last pending` was racy — back-to-back user messages would let one job fill another job's placeholder. Pass the placeholder through the job arguments (`AssistantResponseJob.perform_later(user_message, pending)`) so each turn is bound to its own row. 2. In `Assistant::External#respond_to`, the configured/authorized guards raise before the local was bound, leaving rescue cleanup with `nil` and the placeholder visible forever. Bind the parameter first so cleanup can destroy it on the misconfigured path. The kwarg defaults to nil so the API#retry path (`AssistantResponseJob.perform_later(new_message)`) and the model-level test calls continue to work — they fall back to an in-memory new message, restoring the original test count assertions. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(chat): i18n the pending assistant placeholder string Move the hardcoded "Thinking ..." indicator into the locale file per CLAUDE.md i18n guidelines. With i18n.fallbacks enabled, non-en locales fall back to English until translated. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * Add thinking label translations * Fix chat pending assistant expectations * Fix external assistant pending test lookup * Scope chat stream targets per chat * Update message broadcast target tests --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>	2026-05-03 20:33:29 +02:00
Juan José Mata	7b2b1dd367	Rebase PR #784 and fix OpenAI model/chat regressions (#1384) ... * Wire conversation history through OpenAI responses API * Fix RuboCop hash brace spacing in assistant tests * Pipelock ignores * Batch fixes --------- Co-authored-by: sokiee <sokysrm@gmail.com>	2026-04-15 18:45:24 +02:00
MkDev11	111d6839e0	Feat/Abstract Assistant into module with registry (#1020) ... * Abstract Assistant into module with registry (fixes #1016) - Add Assistant module with registry/factory (builtin, external) - Assistant.for_chat(chat) routes by family.assistant_type - Assistant.config_for(chat) delegates to Builtin for backward compat - Assistant.available_types returns registered types - Add Assistant::Base (Broadcastable, respond_to contract) - Move current behavior to Assistant::Builtin (Provided + Configurable) - Add Assistant::External stub for future OpenClaw/WebSocket - Migration: add families.assistant_type (default builtin) - Family: validate assistant_type inclusion - Tests: for_chat routing, available_types, External stub, blank chat guard * Fix RuboCop layout: indentation in Assistant module and tests * Move new test methods above private so Minitest discovers them * Clear thinking indicator in External#respond_to to avoid stuck UI * Rebase onto upstream main: fix schema to avoid spurious diffs - Rebase feature/abstract-assistant-1016 onto we-promise/main - Rename migration to 20260218120001 to avoid duplicate version with backfill_crypto_subtype - Regenerate schema from upstream + assistant_type only (keeps vector_store_id, realized_gain, etc.) - PR schema diff now shows only assistant_type addition and version bump --------- Co-authored-by: mkdev11 <jaysmth689+github@users.noreply.github.com>	2026-02-23 07:38:58 -05:00