Skip to content

feat(mcp): MS-OI29500 implementation notes ingest + ooxml_behavior tool #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
caio-pizzol wants to merge 4 commits into
base: main
Choose a base branch
from
Open

feat(mcp): MS-OI29500 implementation notes ingest + ooxml_behavior tool #5

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
b94551d
feat(mcp): MS-OI29500 implementation notes ingest + ooxml_behavior tool
caiopizzol Apr 28, 2026
2c80bb0
fix(behavior-notes): address PR #5 review issues
caiopizzol Apr 28, 2026
348f789
feat(mcp): rename ooxml_behavior + add Word observation verification …
caiopizzol Apr 28, 2026
216a96b
fix(behavior-notes): correct seed claim_label + status filter pre-LIMIT
caiopizzol Apr 28, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,4 +11,7 @@ dev/
PLAN.md

# XSD/spec artifacts: pulled by scripts/fetch-xsd.ts; never committed.
data/xsd-cache/
data/xsd-cache/

# MS-OI29500 ingest cache (Microsoft Learn markdown pages).
data/ms-oi29500-cache/
13 changes: 7 additions & 6 deletions CLAUDE.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,10 +33,11 @@ apps/
packages/
shared/ Database client, embedding client, types
scripts/
ingest-pdf/ ECMA PDF -> spec_content (semantic search corpus)
ingest-xsd/ ECMA XSDs -> schema graph (structural query corpus)
sources-sync.ts data/sources.json -> reference_sources
db-migrate.ts Apply db/migrations/*.sql in order
ingest-ecma-376-pdfs/ ECMA-376 PDFs -> spec_content (semantic search corpus)
ingest-ecma-376-xsds/ ECMA-376 XSDs -> schema graph (structural query corpus)
ingest-ms-oi29500/ MS-OI29500 Learn pages -> behavior_notes (Word/Office implementation behavior)
sources-sync.ts data/sources.json -> reference_sources
db-migrate.ts Apply db/migrations/*.sql in order
db/
schema.sql PostgreSQL + pgvector + XSD schema graph
migrations/ Numbered, idempotent SQL migrations
Expand Down Expand Up @@ -136,7 +137,7 @@ PDF → extract (Python) → chunk (6KB) → embed (Voyage) → upload (PostgreS
bun run pdf:ingest 1 ./pdfs/ECMA-376-Part1.pdf # full pipeline for one part
```

See `scripts/ingest-pdf/README.md`.
See `scripts/ingest-ecma-376-pdfs/README.md`.

**XSD (structural corpus, into `xsd_*` tables)**:

Expand All @@ -149,7 +150,7 @@ bun run xsd:fetch # URL + sha256 from data/so
bun run xsd:ingest
```

See `scripts/ingest-xsd/README.md`.
See `scripts/ingest-ecma-376-xsds/README.md`.

## Database

Expand Down
2 changes: 1 addition & 1 deletion apps/mcp-server/src/index.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -124,7 +124,7 @@ export default {
await writer.write(encoder.encode(":keepalive\n\n"));
}
} catch {
// Client disconnected — stream closed
// Client disconnected - stream closed
}
})(),
);
Expand Down
2 changes: 1 addition & 1 deletion apps/mcp-server/src/mcp.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -140,7 +140,7 @@ function handleInitialize(id: number | string | null): JsonRpcResponse {
version: "0.1.0",
},
instructions:
"OOXML (ECMA-376 / Office Open XML) reference server. Two tool families: prose search over the spec PDFs (ooxml_search, ooxml_section, ooxml_parts) and deterministic schema lookup over the parsed XSDs (ooxml_element, ooxml_type, ooxml_children, ooxml_attributes, ooxml_enum, ooxml_namespace).",
"OOXML (ECMA-376 / Office Open XML) reference server. Three tool families: prose search over the spec PDFs (ooxml_search, ooxml_section, ooxml_parts), deterministic schema lookup over the parsed XSDs (ooxml_element, ooxml_type, ooxml_children, ooxml_attributes, ooxml_enum, ooxml_namespace), and Office implementation behavior notes from MS-OI29500 (ooxml_behavior, plus inline notes on ooxml_element/ooxml_type when the symbol has any).",
},
};
}
Expand Down
Loading