6 Commits

Include renames

Author	SHA1	Message	Date
Jesse_ChenandCursor	bf8ad0d1ff	fix(web): keep consultation conclusions across turns and surface cache hits (BUG-555, BUG-556) ... Session history was silently clipped to the first 4000 characters of the last 12 messages, so follow-ups could not see timing or audit tables. Keep an append-only tail plus a checkpoint summary, retry overflow in the same request, and expose cache hit rate in admin usage. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-09-06 15:16:18 +08:00
Jesse_ChenandCursor	ed9497e76a	fix(voice): speak first, then keep Level 2 skeleton and boundary semantics ... Natal answers were opening on parameter tables, and rectification turns were one-sentence legal copy. Centralize user-facing strings, keep representative-minute and question-slot red lines, and stop duplicating the opening collect prompt as a second assistant message. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-09-02 02:27:50 +08:00
Jesse_ChenandCursor	8010245981	feat(product): present consult and rectification in local skill form ... Default ayanamsa to Raman with true_pushya support, attach governed Raman packets, restore Path C questionnaires and eight-method verification copy, and keep unique-minute confirmation blocked. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-08-20 21:42:47 +08:00
Jesse_ChenandCursor	d35828e76d	fix(consult): read the live skill tree instead of a hash-pinned snapshot ... Manual SKILL.md updates were blocked by registry sha256 and a byte-equal versions/ gate. Consult now loads the operator-maintained tree; rectification and personal-report stay hashed. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-08-19 10:25:55 +08:00
Jesse_ChenandCursor	2bf7472645	fix(consult): run the local skill's full technique spectrum on the web path ... Web answers were thinner than a local Agent calling yinduzhanxing-skill: theme-subset vargas, no visible audit table, and a prompt that dropped the invocation contract. Bind the commercial method, compute D1–D60 plus Western layers, and deliver the same Full-Spectrum checklist. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-08-18 23:30:36 +08:00
Jesse_ChenandCursor	d04fc30b63	feat(consult): bind the skill method into the prompt instead of re-activating it every turn ... Activating the skill answered with the entrypoint plus a flat listing of every file in the package, and nothing carried over between requests: the agent is rebuilt per request, no thread memory is configured, and the replayed history is plain question/answer text. So the model re-activated on every turn and paid for that listing every time, twice more whenever a retry opened a fresh model loop. The method is now read from the hash-verified package and bound into the instructions, and the activation tools are withdrawn while skill_read stays. The agents also stopped loading from the working-tree view, whose reference listing no hash covered - only SKILL.md was compared - so what the model sees is finally what the registry pinned. Withdrawing an activation the model could forget also removes the failure it mostly produced: the contract no longer waits on a model action for method, and the no-birth-time path has no contract left to repair. Measured against this package: activation 118,352 bytes, bound method 47,289. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-08-18 21:47:15 +08:00