jedarden/pdftract

Fork 0

Commit graph

Author	SHA1	Message	Date
jedarden	7ea539f8aa	feat(pdftract-39g4j): implement --receipts CLI flag + ExtractionOptions.receipts threading - Add value_parser = ["off", "lite", "svg"] to --receipts CLI flag for clap validation - Add receipts field to ExtractTextArgs and ExtractMarkdownArgs in MCP tools args - Add ExtractionOptions and ReceiptsMode to pdftract-core (options.rs module) - Expose options module in pdftract-core/lib.rs The CLI now validates receipts mode at parse time with helpful error messages. MCP tools accept receipts argument matching the schema defined in sibling 6.7.5. ExtractionOptions struct provides the threading mechanism for the extraction pipeline. Acceptance criteria: - PASS: CLI validates --receipts values (off/lite/svg only) - PASS: CLI shows proper help text with possible values - PASS: ExtractionOptions serializes for HTTP/MCP transport - PASS: MCP tools args have receipts field - WARN: Full extraction implementation pending (deferred to extraction beads) Closes pdftract-39g4j Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>	2026-05-23 04:07:23 -04:00
jedarden	7833d8c514	feat(pdftract-1rami): implement MCP tool catalog with 10 tools Implement the MCP tool catalog for pdftract with all 10 tools wired to the extraction surface via the MCP protocol. The tool registry provides typed argument schemas (JSON Schema via schemars), structured error mapping (Rust errors → JSON-RPC error codes), and per-invocation observability logging. - Tool registry with Tool trait and 10 tool implementations - JSON Schema input schemas for all tools (draft-07 compliant) - Error code mapping: -32000 NOT_YET_IMPLEMENTED, -32001 PDF_ENCRYPTED, -32002 IO_ERROR, -32003 PATH_INVALID - Observability logging: structured stderr log line per tools/call - Integration tests: 10/11 pass (1 ignored for encrypted fixture) - Registry unit tests: 23/23 pass Tools implemented: - extract, extract_text, extract_markdown (stubs pending Phase 6) - search (stub pending Phase 6) - get_metadata, hash (fully implemented, fast paths) - get_table, get_form_fields, get_attachments, classify (stubs return NOT_YET_IMPLEMENTED per spec) Acceptance criteria: 8/8 PASS (2 WARN for Phase 6 stubs) Refs: pdftract-1rami Co-Authored-By: Claude Code <noreply@anthropic.com>	2026-05-23 02:12:41 -04:00

Author

SHA1

Message

Date

jedarden

7ea539f8aa

feat(pdftract-39g4j): implement --receipts CLI flag + ExtractionOptions.receipts threading

- Add value_parser = ["off", "lite", "svg"] to --receipts CLI flag for clap validation
- Add receipts field to ExtractTextArgs and ExtractMarkdownArgs in MCP tools args
- Add ExtractionOptions and ReceiptsMode to pdftract-core (options.rs module)
- Expose options module in pdftract-core/lib.rs

The CLI now validates receipts mode at parse time with helpful error messages.
MCP tools accept receipts argument matching the schema defined in sibling 6.7.5.
ExtractionOptions struct provides the threading mechanism for the extraction pipeline.

Acceptance criteria:
- PASS: CLI validates --receipts values (off/lite/svg only)
- PASS: CLI shows proper help text with possible values
- PASS: ExtractionOptions serializes for HTTP/MCP transport
- PASS: MCP tools args have receipts field
- WARN: Full extraction implementation pending (deferred to extraction beads)

Closes pdftract-39g4j

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-23 04:07:23 -04:00

jedarden

7833d8c514

feat(pdftract-1rami): implement MCP tool catalog with 10 tools

Implement the MCP tool catalog for pdftract with all 10 tools wired to
the extraction surface via the MCP protocol. The tool registry provides
typed argument schemas (JSON Schema via schemars), structured error
mapping (Rust errors → JSON-RPC error codes), and per-invocation
observability logging.

- Tool registry with Tool trait and 10 tool implementations
- JSON Schema input schemas for all tools (draft-07 compliant)
- Error code mapping: -32000 NOT_YET_IMPLEMENTED, -32001 PDF_ENCRYPTED,
  -32002 IO_ERROR, -32003 PATH_INVALID
- Observability logging: structured stderr log line per tools/call
- Integration tests: 10/11 pass (1 ignored for encrypted fixture)
- Registry unit tests: 23/23 pass

Tools implemented:
- extract, extract_text, extract_markdown (stubs pending Phase 6)
- search (stub pending Phase 6)
- get_metadata, hash (fully implemented, fast paths)
- get_table, get_form_fields, get_attachments, classify (stubs return
  NOT_YET_IMPLEMENTED per spec)

Acceptance criteria: 8/8 PASS (2 WARN for Phase 6 stubs)

Refs: pdftract-1rami
Co-Authored-By: Claude Code <noreply@anthropic.com>

2026-05-23 02:12:41 -04:00

2 commits