- 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.
* 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>
