Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
25 commits
Select commit Hold shift + click to select a range
07b7281
refactor: remove toc_page_offset from various components and enhance …
EricNGOntos Aug 17, 2026
a827c31
feat: enable PDF_PROFILE_TOC by default and enhance TOC handling
EricNGOntos Aug 18, 2026
4d89b98
refactor: streamline document profile workflow and remove ReAct executor
EricNGOntos Aug 18, 2026
4e9b0e6
refactor: rename planner to coarse_profile and update related components
EricNGOntos Aug 18, 2026
29679ad
refactor: enhance document agent components and remove unused code
EricNGOntos Aug 18, 2026
3d60fd5
refactor: consolidate page link handling and remove unused components
EricNGOntos Aug 18, 2026
e60b8b8
refactor: strip Agent naming from PROFILE workflow surfaces
EricNGOntos Aug 18, 2026
58dbb7e
refactor: remove unused H1-related components and streamline document…
EricNGOntos Aug 18, 2026
af6f1fa
fix: guard None TOC level before int conversion in body_boundary
EricNGOntos Aug 18, 2026
984f140
feat: enhance TOC anchoring with PDF outline adoption
EricNGOntos Aug 18, 2026
ff707b6
refactor: streamline TOC extraction pipeline and enhance outline anch…
EricNGOntos Aug 18, 2026
c899e1a
feat: implement first sibling null parent scanning and enhance TOC an…
EricNGOntos Aug 19, 2026
02518b0
refactor: update budget handling and TOC extraction logic
EricNGOntos Aug 19, 2026
d5bc9a7
refactor: remove budget tracking from document agent components
EricNGOntos Aug 19, 2026
c266568
fix: update calibration phase 1 logic to correctly determine scan sta…
EricNGOntos Aug 19, 2026
44fe7e1
refactor: enhance TOC anchoring and extraction concurrency
EricNGOntos Aug 19, 2026
d5558db
merge: resolve main into profile-coarse-workflow
EricNGOntos Aug 19, 2026
ff15ed2
refactor: improve TOC hierarchy selection and extraction logic
EricNGOntos Aug 19, 2026
f655949
refactor: clean up dependencies and remove unused packages
EricNGOntos Aug 19, 2026
7c3fa77
refactor: update terminology and improve logging in document agent se…
EricNGOntos Aug 19, 2026
f1b6c96
refactor: remove confidence attributes from document agent structures
EricNGOntos Aug 19, 2026
fb69c3f
refactor: enhance shard plan validation and TOC extraction error hand…
EricNGOntos Aug 19, 2026
27bad3b
fix: drop undefined calibration __all__ exports for CodeQL
EricNGOntos Aug 19, 2026
f0ae628
fix: seed AppConfig env defaults in body_boundary contract
EricNGOntos Aug 19, 2026
ebab365
fix: rebind live anchoring primitives after contract module eviction
EricNGOntos Aug 19, 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
14 changes: 1 addition & 13 deletions apps/api/.env.example
Original file line number Diff line number Diff line change
Expand Up @@ -110,20 +110,8 @@ MAX_FILE_SIZE=314572800
MAX_PDF_PAGE_LIMIT=200
OVERSIZED_PDF_SHARD_ENABLED=true
OVERSIZED_PDF_SOFT_LIMIT=1500
PDF_PROFILE_TOC_ENABLED=false
PDF_PROFILE_TOC_ENABLED=true
MINERU_SHARD_CONCURRENCY=3
PARSE_AGENT_PLAN_BUDGET=50000
PARSE_AGENT_VISUAL_BUDGET=120000
PARSE_AGENT_TOC_CONFIRM_MIN_BUDGET=8000
PARSE_AGENT_TOC_CONFIRM_CAP=24000
PARSE_AGENT_COARSE_PLANNER_MIN_BUDGET=12000
PARSE_AGENT_COARSE_PLANNER_CAP=36000
PARSE_AGENT_STRUCTURAL_REACT_MIN_BUDGET=24000
PARSE_AGENT_STRUCTURAL_REACT_CAP=64000
PARSE_AGENT_CALIBRATION_MIN_BUDGET=12000
PARSE_AGENT_CALIBRATION_CAP=40000
PARSE_AGENT_PAGE_TAGGING_MIN_BUDGET=0
PARSE_AGENT_PAGE_TAGGING_CAP=0

# Required for specific features: webhooks and callbacks
WEBHOOK_MASTER_KEY=
Expand Down
14 changes: 1 addition & 13 deletions apps/worker/.env.example
Original file line number Diff line number Diff line change
Expand Up @@ -125,22 +125,10 @@ MAX_FILE_SIZE=314572800
MAX_PDF_PAGE_LIMIT=200
OVERSIZED_PDF_SHARD_ENABLED=true
OVERSIZED_PDF_SOFT_LIMIT=1500
PDF_PROFILE_TOC_ENABLED=false
PDF_PROFILE_TOC_ENABLED=true
# macOS/Homebrew local debugging only; worker Docker image installs OpenJDK.
# JAVA_HOME=/opt/homebrew/opt/java
MINERU_SHARD_CONCURRENCY=3
PARSE_AGENT_PLAN_BUDGET=50000
PARSE_AGENT_VISUAL_BUDGET=120000
PARSE_AGENT_TOC_CONFIRM_MIN_BUDGET=8000
PARSE_AGENT_TOC_CONFIRM_CAP=24000
PARSE_AGENT_COARSE_PLANNER_MIN_BUDGET=12000
PARSE_AGENT_COARSE_PLANNER_CAP=36000
PARSE_AGENT_STRUCTURAL_REACT_MIN_BUDGET=24000
PARSE_AGENT_STRUCTURAL_REACT_CAP=64000
PARSE_AGENT_CALIBRATION_MIN_BUDGET=12000
PARSE_AGENT_CALIBRATION_CAP=40000
PARSE_AGENT_PAGE_TAGGING_MIN_BUDGET=0
PARSE_AGENT_PAGE_TAGGING_CAP=0

# Parser row schema. `entities` (JSON typed entities, §4.4) and `asset_title`
# (asset caption/label, §4.5) are additive trailing columns; the parser layer
Expand Down
2 changes: 1 addition & 1 deletion apps/worker/app/services/document_agent/__init__.py
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
"""Page anatomy agent for hierarchy-first PDF profiling."""
"""Document profile workflow for hierarchy-first PDF profiling."""

from app.services.document_agent.manifest import (
PageAnatomyMap,
Expand Down
1 change: 0 additions & 1 deletion apps/worker/app/services/document_agent/agents/__init__.py

This file was deleted.

This file was deleted.

This file was deleted.

Loading
Loading