Relaticle

Fixes

Chat: Harden the AI approval flow against lost state and rate limits (#321)

• Lost approval state (Bug A): the assistant could get stuck re-asking to approve an already-approved action when the post-approval continuation failed or was skipped. Approval state is now injected into the model each turn from the authoritative pending_actions table (a <resolved_actions> context block), so it no longer depends on the continuation journaling to the transcript.
• Rate-limit resilience (Bug B): provider 429s surfaced as a generic error with no retry. Chat jobs now retry transient rate-limit / overloaded responses with capped backoff and surface an honest message. This covers both the typed RateLimitedException and the raw streaming RequestException (429/529/503) — the latter verified end-to-end under the async (Horizon) queue.
• Explicit pause: when the approval auto-continue chain hits its cap it now broadcasts a ChatPaused notice (“say continue to resume”) instead of stalling silently.

Full Changelog: https://github.com/relaticle/relaticle/compare/v3.3.3…v3.3.4