doc-holmes
Layout-preserving precise translation for large PDFs. Keeps formulas, figures, tables, TOC and annotations intact; outputs a bilingual side-by-side PDF plus a pure-translation PDF. Tier-A documents also support a zero-dependency direct mode (extract, translate, apply - no engine, no API key) and one
as observed 2026-10-06T10:50:34.888Z- Identifier
doc-holmes- Source
- ClawHub
- Version observed
- 3.0.0
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-09-20T22:20:20.811Z
- Observations recorded
- 14
- Installs (reported upstream)
- 3
- Weekly downloads (upstream)
- 871
- Declared license
- MIT-0
Observation history
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"v2.10.0 - Terminology consistency & quality transparency. 1) Injected glossaries (built-in medical table, user CSV, adaptive seeding) now disable the engine's automatic term extra | "v3.0.0 major release. 1) Zero-dependency direct mode - no engine, no endpoint, no API key: extract line-level text from tier-A documents (fully offline), you/your model translate |
latestVersion |
"2.10.0" | "3.0.0" |
summary |
"Layout-preserving precise translation for large PDFs (papers, guidelines, reports). Keeps formulas, figures, tables, TOC and annotations intact; outputs a bilingual side-by-side P | "Layout-preserving precise translation for large PDFs. Keeps formulas, figures, tables, TOC and annotations intact; outputs a bilingual side-by-side PDF plus a pure-translation PDF |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v2.8.0 - Editable DOCX output and batch policy transparency. New: --output-format docx converts the translated PDF into an editable Word document via LibreOffice (for revisions, a | "v2.10.0 - Terminology consistency & quality transparency. 1) Injected glossaries (built-in medical table, user CSV, adaptive seeding) now disable the engine's automatic term extra |
latestVersion |
"2.8.0" | "2.10.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v2.7.0 - Document pipeline completion. New: merge subcommand (combines multiple PDFs), split subcommand (breaks by page-range expression), estimate subcommand (dry-run: pages/char | "v2.8.0 - Editable DOCX output and batch policy transparency. New: --output-format docx converts the translated PDF into an editable Word document via LibreOffice (for revisions, a |
latestVersion |
"2.7.0" | "2.8.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v2.6.0 - Translation efficiency and intelligence. 1) Segment-level translation cache: batch mode automatically checks a SQLite-backed cache (SHA256 keyed by source text + language | "v2.7.0 - Document pipeline completion. New: merge subcommand (combines multiple PDFs), split subcommand (breaks by page-range expression), estimate subcommand (dry-run: pages/char |
latestVersion |
"2.6.0" | "2.7.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v2.5.0 - Editable DOCX output and batch policy transparency. New: --output-format docx converts the translated PDF into an editable Word document via LibreOffice (for revisions, a | "v2.6.0 - Translation efficiency and intelligence. 1) Segment-level translation cache: batch mode automatically checks a SQLite-backed cache (SHA256 keyed by source text + language |
latestVersion |
"2.5.0" | "2.6.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v2.4.0 - Document pipeline completion: merge, split, and estimate subcommands. merge combines multiple PDFs into one (closes the --pages partitioned-translation loop). split break | "v2.5.0 - Editable DOCX output and batch policy transparency. New: --output-format docx converts the translated PDF into an editable Word document via LibreOffice (for revisions, a |
latestVersion |
"2.4.0" | "2.5.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v2.2.0 - Tier-C repair layer 2.0: drop-level noise lines (watermarks, ICP filings) are now removed from the rebuilt OCR text layer before translation, with per-line glue-splitting | "v2.4.0 - Document pipeline completion: merge, split, and estimate subcommands. merge combines multiple PDFs into one (closes the --pages partitioned-translation loop). split break |
latestVersion |
"2.2.0" | "2.4.0" |
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"Medical-terminology consistency and visual batch reporting. 1) A bundled 45-term medical EN-to-ZH glossary is injected into the engine's glossary pipeline by default (RCT, systema | "v2.2.0 - Tier-C repair layer 2.0: drop-level noise lines (watermarks, ICP filings) are now removed from the rebuilt OCR text layer before translation, with per-line glue-splitting |
latestVersion |
"2.1.0" | "2.2.0" |
summary |
"Layout-preserving precise translation for large PDFs (papers, guidelines, reports). Keeps formulas, figures, tables, TOC and annotations intact; outputs a bilingual side-by-side P | "Layout-preserving precise translation for large PDFs (papers, guidelines, reports). Keeps formulas, figures, tables, TOC and annotations intact; outputs a bilingual side-by-side P |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"Major release: oversized-PDF reliability. 1) Large-document auto strategy: PDFs of 40+ pages are automatically partitioned (25 pages/part, engine-native splitting with automatic m | "Medical-terminology consistency and visual batch reporting. 1) A bundled 45-term medical EN-to-ZH glossary is injected into the engine's glossary pipeline by default (RCT, systema |
latestVersion |
"2.0.0" | "2.1.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"Compatibility and transparency release: 1) fixed a single-line YAML pitfall in the SKILL.md description field (a colon followed by a space can make strict Agent-skill parsers reje | "Major release: oversized-PDF reliability. 1) Large-document auto strategy: PDFs of 40+ pages are automatically partitioned (25 pages/part, engine-native splitting with automatic m |
latestVersion |
"1.3.0" | "2.0.0" |
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"Timeout robustness for large documents (driven by real-world STTT review case): 1) fixed DOC_HOLMES_OPENAI_TIMEOUT never reaching the engine (HTTP timeout was stuck at 60s); 2) de | "Compatibility and transparency release: 1) fixed a single-line YAML pitfall in the SKILL.md description field (a colon followed by a space can make strict Agent-skill parsers reje |
latestVersion |
"1.2.0" | "1.3.0" |
summary |
"Translates large PDFs while preserving layout, formulas, figures, tables, TOC, and annotations; outputs bilingual side-by-side and pure-translation PDFs." | "Layout-preserving precise translation for large PDFs (papers, guidelines, reports). Keeps formulas, figures, tables, TOC and annotations intact; outputs a bilingual side-by-side P |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"Tier-B upgrade, step one: span-level duplicate-layer detection (same-text near-overlap counting with samples into the audit trail; redaction surgery was tested and deliberately NO | "Timeout robustness for large documents (driven by real-world STTT review case): 1) fixed DOC_HOLMES_OPENAI_TIMEOUT never reaching the engine (HTTP timeout was stuck at 60s); 2) de |
latestVersion |
"1.1.0" | "1.2.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"Endpoint-safety hotfix: no endpoint or credentials are bundled anymore - users configure their own OpenAI-compatible endpoint and API key (official Zhipu open platform free tier r | "Tier-B upgrade, step one: span-level duplicate-layer detection (same-text near-overlap counting with samples into the audit trail; redaction surgery was tested and deliberately NO |
latestVersion |
"1.0.1" | "1.1.0" |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.