What
- The background turn-state classifier gained a
projectsRecapmode: when invoked withprojectsRecap: true, it skips the normal preclassify/heuristic path, uses a distinct (server-overridable) system prompt, and asks the model to produce a recap "card" with a state ofneeds_reply,needs_approval,done,failed, orworking, plus a "happened" summary. It retries once if the response JSON is invalid. - The mid-turn/end-of-turn background-agent status classifier now passes a
projectsRecapflag into the classification call that produces a task's working/idle/blocked detail text. - A project's task/thread status can now use this richer "recap" object (headline, needs, needsYou, happened, reply) instead of the old flat detail/needs/output.result fields.
- Results and failures are logged via a
projects_thread_recaptelemetry event, with reasons likeheuristic_engine,line_truncated,parse_failed, andside_query_failed. - The whole feature is behind the
tengu_projects_thread_recapflag and currently off.
Why This lays the groundwork for showing a more useful, model-written summary of what happened in a Projects background task, rather than a flat status line, though it isn't enabled yet.
Feature flag
tengu_projects_thread_recap_prompt Not enough to sayNothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.
This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.265: not a boolean we can read
Read once, for one account on one subscription tier, against v2.1.265. It isn't a statement about your account. What a flag value here can and cannot tell you
One source agreesOne thing we can check says the same as this entry.
The name it cites is new in this build
New in this build: tengu_projects_thread_recap_prompt