Commit Graph
14 Commits
Author SHA1 Message Date
Tianyi Cui e221615112 test(sdk): cover native dynamic tool lifecycle 2026-09-23 22:40:39 +08:00
Yudong Han 5e25475857 fix(office): use bundled LibreOffice Kit 0.1.0 CLI across deployments (#4902)
* chore(office): upgrade libreoffice kit to 0.0.1-2

* fix(office): guide bounded CLI rendering and preview reuse

* chore(office): consume published LibreOffice Kit 0.0.3

* test(office): mock the complete LibreOffice converter interface

* chore(office): upgrade LibreOffice Kit to 0.0.4

* fix(office): expose bundled LibreOffice Kit 0.1.0 CLI across deployments

* fix(office): inspect Excel visuals only for layout tasks

* fix(office): allow compatible LibreOffice Kit 0.1 updates

* fix(office): stop Excel QA on blank previews and run regressions in CI

* fix(office): end workbook visual QA after an empty preview
2026-09-23 08:32:15 +00:00
_KermanandTianyi Cui fb79a944f5 refactor(llm): separate durable producer sources from request inputs
Give durable user context its producer-owned source kind instead of a generic plugin wrapper. The V3-to-V4 conversion preserves the frozen rename and collision rules, all own JSON metadata, event coordinates, and historical request-only kinds. Native catalog and JSONL admission retain source validation so unknown attribution can survive without its producer while malformed owned sources are refused.

Use an explicit user-only RequestUserInput for auxiliary LLM prompts that do not own durable message identity. Auto Review and compaction remove their request-only source registrations while retaining prompt content and freezing; provider serializers and projections keep the same wire data, assistant replay isolation, image ordering, and tool correlation. Session writes, Agent delivery, and recorded title requests continue to require identified durable messages.

Bind the saved compatibility policy only to user sources and qualify tmux location attribution without weakening fixed system, model, or tool semantics. Rebuild the current inventory and unpublished V4 acknowledgement on the actual tool-role parent, preserving its rationale and all accepted historical records. The catalog format version records tooling metadata; Session remains V4. Developer-role policy and activation belong to their own feature.

The latest-master Messages adapter, serialization, request-input typing, EpochHeader reservation, and attribution checks pass 103 tests across five files. The retained V3 Messages input-history snapshot passes through the source profile; Host/Client typechecks and all 41 documentation gates pass. The generated comparison records four changed roots and 447 unchanged type fingerprints. Latest-master ARIA changes are retained, with producer source labels applied independently; new Messages fixtures retain their producer names as declared source kinds and use the fixed system-message helper; recorded Session generations are unchanged by this regrouping.

Co-authored-by: Tianyi Cui <[email protected]>
2026-09-18 19:07:12 +08:00
yudshj 9d2a3bf2b7 feat(document): decouple shared Office conversion from preview 2026-09-17 11:15:21 +08:00
turtle1999 92da029f6d test(creator): replace retired Cordis tool scenarios 2026-09-16 15:39:17 +08:00
creatixchu b5e7fca4a5 feat(compaction): record image offload decisions without message replacement 2026-09-10 16:47:50 +08:00
Tianyi Cui 96fa1dfac8 Merge pinned master 84bde6c7 into V3 readiness repair 2026-09-08 13:16:35 +08:00
Tianyi Cui 1ca0df2e24 test(python): synchronize advanced snapshot workflow membership 2026-09-07 14:26:30 +08:00
Tianyi Cui 9c8884284f test(sdk): record in-history system prompt updates in both clients
Cover the missing SDK projections through shipped dsh profiles. TypeScript reuses the headless read-completion composition and records SDK notifications. Python all includes a focused minimal-profile variant with an ordinary prompt section updated after shell completion, unchanged tools, persisted/subscribed append events, and independently checked editor output.

Observed: focused TS refresh and built replay passed (1 test); Python sdk-minimal-in-history and sdk-minimal passed against apps/cli/lib/bin.js using uv; unchanged-prompt negative control failed as expected then restored scenario passed; corpus 3 tests, doc-sync 33 gates, and lint:contracts-ready passed. Host-only build initially left SDK built startup incomplete; build:lib:client completed the prerequisites. Native packaged/wheel and Windows validation remain pending parent integration.
2026-09-07 11:09:39 +08:00
Tianyi Cui 36cca40281 test: make the product translation fixture generic 2026-08-13 13:58:03 +08:00
Tianyi Cui 9d0ef6f5bb test: make the Agent Note translation fixture generic 2026-08-13 13:48:09 +08:00
Tianyi Cui 16d86cfba7 test: decouple the translation prompt snapshot from live documents
The snapshot embedded five live bilingual document pairs as reviewed
examples, so editing any of them (README, development guide, i18n docs)
churned the snapshot. Replace them with three synthetic fixture pairs
(product, rules, agent-note shapes) under scripts/fixtures; the prompt
examples stay representative without tracking real document content.
2026-08-13 13:07:57 +08:00
Tianyi Cui 3a87104a9a fix(i18n): harden prompt response handling 2026-07-23 23:12:56 +08:00
Tianyi Cui caaf4f8d18 fix(i18n): complete prompt v4 pipeline path 2026-07-23 22:41:53 +08:00