Expose builtin document parsing through the host handle (EXT-5) #222

Merged
weichen merged 7 commits from feature/ext-5-host-parse into main 2026-10-06 15:14:31 +00:00
Owner

EXT-5: expose builtin document parsing through the host handle and add builtin xlsx/pptx parsers.

  • modules/documents -> 5825cd3 (PR #39): restore EXT-1 proposal (cherry-pick a47754b, lost from main by pin move 8af945a) + EXT-5 request + compat-policy sect.3 snapshot-methods sentence.
  • modules/backend -> 727f370 (PR #67): Host.ParseDocument (owner-scoped pure compute; errors only on ctx cancel or >100MiB); builtin:xlsx/builtin:pptx parsers (caps 200k cells / 64MiB per zip part); legacy doc/xls/ppt hint; registry gains xlsx/pptx + text; surface snapshot records interface methods; docx part reads share the 64MiB cap.
  • Dev: architecture baseline gains "backend/app backend/ingest"; examples/downstream-rdm fakeHost implements ParseDocument (examples test run locally — not covered by make test).

Evidence: task card .task/feature-ext-5-host-parse.md (SELF rows; precheck/task-sync/make test/examples/documents diff-check). GATE = CI make test + make build on this PR head.

EXT-5: expose builtin document parsing through the host handle and add builtin xlsx/pptx parsers. - modules/documents -> 5825cd3 (PR #39): restore EXT-1 proposal (cherry-pick a47754b, lost from main by pin move 8af945a) + EXT-5 request + compat-policy sect.3 snapshot-methods sentence. - modules/backend -> 727f370 (PR #67): Host.ParseDocument (owner-scoped pure compute; errors only on ctx cancel or >100MiB); builtin:xlsx/builtin:pptx parsers (caps 200k cells / 64MiB per zip part); legacy doc/xls/ppt hint; registry gains xlsx/pptx + text; surface snapshot records interface methods; docx part reads share the 64MiB cap. - Dev: architecture baseline gains "backend/app backend/ingest"; examples/downstream-rdm fakeHost implements ParseDocument (examples test run locally — not covered by make test). Evidence: task card .task/feature-ext-5-host-parse.md (SELF rows; precheck/task-sync/make test/examples/documents diff-check). GATE = CI make test + make build on this PR head.
weichen added 7 commits 2026-10-06 15:06:09 +00:00
Why: establish the authorized task workspace and its initial baseline.

Evidence: preserved precheck receipt in .task/feature-ext-5-host-parse.md; R0=840f8f96d184b8ecd6c3e84951ee408aa654a25b.

Impact: task metadata only; the feature workspace starts at 840f8f96d1.

Refs: .task/feature-ext-5-host-parse.md
Why: EXT-5 needs an extension-point request card (compat-policy sect.6) plus implementation scope before code changes.

Evidence: precheck receipt SELF in card; R0=840f8f96d184b8ecd6c3e84951ee408aa654a25b.

Impact: task metadata only.

Refs: .task/feature-ext-5-host-parse.md
Why: completion claims require tool-written evidence (AGENTS.md).

Evidence: SELF receipt appended by make evidence; full suite green incl. ui 103 tests and agent-command.

Impact: task metadata only.

Refs: .task/feature-ext-5-host-parse.md
Why: documents has no CI; the diff-check is its verification gate.

Evidence: SELF receipt; diff --check clean, two documents commits and one backend commit listed.

Impact: task metadata only.

Refs: .task/feature-ext-5-host-parse.md
Why: make test does not compile examples/; the EXT-5 Host method requires the example fake to keep compiling.

Evidence: SELF receipt; example.com/agent-system-plugin-rdm ok.

Impact: task metadata only.

Refs: .task/feature-ext-5-host-parse.md
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=840f8f96d184b8ecd6c3e84951ee408aa654a25b; candidate=59855d5ee02024ee28df795798b5dc8c775e7c92.

Impact: task metadata only.

Refs: .task/feature-ext-5-host-parse.md
Record the final-tree make test evidence
ci / test (pull_request) Successful in 2m26s
f5c83534fe
Why: task-sync flagged receipts predating the committed gitlinks; rerun at committed HEAD.

Evidence: SELF receipt exit=0 at 45594cc560.

Impact: task metadata only.

Refs: .task/feature-ext-5-host-parse.md
weichen merged commit c06da57359 into main 2026-10-06 15:14:31 +00:00
Sign in to join this conversation.
No Reviewers
No labels
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: weichen/Agent-System-Dev#222