mirror of
https://github.com/tiennm99/goclaw.git
synced 2026-06-10 14:10:52 +00:00
Viet Tran
ace07509b7
* feat(infra): add runtime package support for skills Install nodejs, npm, pandoc, github-cli + pre-install Python packages (openpyxl, pandas, python-pptx, markitdown) and Node packages (docx, pptxgenjs). Configure runtime dirs for agent pip/npm installs with PIP_TARGET, NPM_CONFIG_PREFIX, NODE_PATH to enable dynamic package installation in read-only container environment. * feat(infra): add bundled skills with runtime package support - Add 5 bundled skills: docx, pdf, pptx, xlsx, skill-creator from container skills-store - Wire GOCLAW_BUILTIN_SKILLS_DIR env var in gateway and CLI - Support optional runtime packages alongside dynamic skill loading - Update Dockerfile to COPY bundled-skills at /app/bundled-skills/ - Add PIP_CACHE_DIR in docker-entrypoint.sh for clean pip installs - Document bundled skills in 14-skills-runtime.md section 6 * feat(infra): remove ai-multimodal skill directory from bundled skills Remove the ai-multimodal skill package as part of consolidating runtime package support for bundled skills. This directory is no longer needed in the bundled skills structure. * feat(ci): add semantic release and Docker Hub publishing Add go-semantic-release workflow to auto-create semver tags on merge to main. Extend docker-publish to push all variants to both GHCR and Docker Hub (digitop/goclaw). * feat(skills): add system skills infrastructure with is_system column, dep scanning, and seeder - Migration 000017: add is_system boolean column with partial index - Store layer: UpsertSystemSkill, delete protection, IsSystemSkill - ListAccessible auto-includes system skills (no grants needed) - ListWithGrantStatus returns is_system field - Dependency scanner: auto-detect deps from scripts/ or skill-manifest.json - Dependency checker: verify system binaries, Python/Node packages - Seeder: seed bundled skills into DB on startup (idempotent via hash) - Gateway wiring: GOCLAW_BUNDLED_SKILLS_DIR env for bundled skills - HTTP: delete guard (403), slug conflict check (409), rescan-deps endpoint - UI: System badge, hide delete for system skills, rescan deps button - Agent skills tab: "Always available" for system skills - i18n: en/vi/zh keys for system skills, deps scanning * feat(skills): conditional system prompt, skill manifests, and Zip Slip fix - System prompt: only show package list when python3/node are available - Add skill-manifest.json for pdf, docx, xlsx, pptx bundled skills - Fix Zip Slip vulnerability in office/unpack.py (all 3 copies) * refactor(skills): extract shared office code to _shared/ and deduplicate Move office scripts (pack, unpack, validate, schemas, validators) from duplicated copies in docx/xlsx/pptx to skills/_shared/office/ with symlinks. Remove soffice.py (non-functional in containers) and update SKILL.md references to use soffice binary directly. Update seeder copyDir to follow symlinks. Removes ~45K lines of duplicate code across 3 skills. * fix(skills): address code review findings for system skills integration - H1: Remove dead symlink branch in copyDir (filepath.Walk follows symlinks) - H3: Fix rescan-deps to query ALL skills (including archived) and re-activate when deps become available; add ListAllSkills() + Status field to SkillInfo - H4: Add Status field to SkillCreateParams, stop overloading Visibility - M1: Batch Python/Node dep checks into single subprocess per runtime - M4: Add rows.Err() check in ListSkills to prevent caching partial results * feat(skills): async dep checking with realtime WS events Split Seed() into sync DB upsert + async CheckDepsAsync() goroutine. Gateway startup no longer blocks on Python/Node subprocess dep checks. - Seed() returns seeded skills list, all initially status="active" - CheckDepsAsync() runs in background, emits skill.deps.checked per-skill - skill.deps.complete event emitted when all checks finish - Each failed dep check: archives skill + BumpVersion() for immediate cache invalidation so next agent turn picks up the change - UI: use-query-invalidation listens to skill.deps.* events → auto-refresh skills list in realtime * feat(skills): system skills integration with toggle, dep checking, and per-item install - Add is_system, deps, enabled columns to skills table (migration 017) - Seed bundled core skills (pdf, docx, pptx, xlsx, skill-creator) on startup - PYTHONPATH-based dep detection — eliminates false positives from local modules - Per-item dep install UI with individual status (installing/success/error) - Enable/disable toggle for core and custom skills (independent of dep status) - Re-run dep check when skill is toggled back on - Inline skill thresholds: 40 skills / 5000 tokens before switching to search mode - Fix UpsertSystemSkill: backfill null file_hash without bumping DB version - Remove redundant skill-manifest.json files (replaced by deps JSONB column) - Show author from frontmatter in custom skills tab - Runtime checker for python3/pip3/node/npm availability - WS events for dep checking/installing progress - docs: add 15-core-skills-system.md, 16-skill-publishing.md --------- Co-authored-by: Goon <duy@wearetopgroup.com>
108 lines
3.2 KiB
Python
108 lines
3.2 KiB
Python
import json
|
|
import sys
|
|
|
|
from pypdf import PdfReader, PdfWriter
|
|
from pypdf.annotations import FreeText
|
|
|
|
|
|
|
|
|
|
def transform_from_image_coords(bbox, image_width, image_height, pdf_width, pdf_height):
|
|
x_scale = pdf_width / image_width
|
|
y_scale = pdf_height / image_height
|
|
|
|
left = bbox[0] * x_scale
|
|
right = bbox[2] * x_scale
|
|
|
|
top = pdf_height - (bbox[1] * y_scale)
|
|
bottom = pdf_height - (bbox[3] * y_scale)
|
|
|
|
return left, bottom, right, top
|
|
|
|
|
|
def transform_from_pdf_coords(bbox, pdf_height):
|
|
left = bbox[0]
|
|
right = bbox[2]
|
|
|
|
pypdf_top = pdf_height - bbox[1]
|
|
pypdf_bottom = pdf_height - bbox[3]
|
|
|
|
return left, pypdf_bottom, right, pypdf_top
|
|
|
|
|
|
def fill_pdf_form(input_pdf_path, fields_json_path, output_pdf_path):
|
|
|
|
with open(fields_json_path, "r") as f:
|
|
fields_data = json.load(f)
|
|
|
|
reader = PdfReader(input_pdf_path)
|
|
writer = PdfWriter()
|
|
|
|
writer.append(reader)
|
|
|
|
pdf_dimensions = {}
|
|
for i, page in enumerate(reader.pages):
|
|
mediabox = page.mediabox
|
|
pdf_dimensions[i + 1] = [mediabox.width, mediabox.height]
|
|
|
|
annotations = []
|
|
for field in fields_data["form_fields"]:
|
|
page_num = field["page_number"]
|
|
|
|
page_info = next(p for p in fields_data["pages"] if p["page_number"] == page_num)
|
|
pdf_width, pdf_height = pdf_dimensions[page_num]
|
|
|
|
if "pdf_width" in page_info:
|
|
transformed_entry_box = transform_from_pdf_coords(
|
|
field["entry_bounding_box"],
|
|
float(pdf_height)
|
|
)
|
|
else:
|
|
image_width = page_info["image_width"]
|
|
image_height = page_info["image_height"]
|
|
transformed_entry_box = transform_from_image_coords(
|
|
field["entry_bounding_box"],
|
|
image_width, image_height,
|
|
float(pdf_width), float(pdf_height)
|
|
)
|
|
|
|
if "entry_text" not in field or "text" not in field["entry_text"]:
|
|
continue
|
|
entry_text = field["entry_text"]
|
|
text = entry_text["text"]
|
|
if not text:
|
|
continue
|
|
|
|
font_name = entry_text.get("font", "Arial")
|
|
font_size = str(entry_text.get("font_size", 14)) + "pt"
|
|
font_color = entry_text.get("font_color", "000000")
|
|
|
|
annotation = FreeText(
|
|
text=text,
|
|
rect=transformed_entry_box,
|
|
font=font_name,
|
|
font_size=font_size,
|
|
font_color=font_color,
|
|
border_color=None,
|
|
background_color=None,
|
|
)
|
|
annotations.append(annotation)
|
|
writer.add_annotation(page_number=page_num - 1, annotation=annotation)
|
|
|
|
with open(output_pdf_path, "wb") as output:
|
|
writer.write(output)
|
|
|
|
print(f"Successfully filled PDF form and saved to {output_pdf_path}")
|
|
print(f"Added {len(annotations)} text annotations")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
if len(sys.argv) != 4:
|
|
print("Usage: fill_pdf_form_with_annotations.py [input pdf] [fields.json] [output pdf]")
|
|
sys.exit(1)
|
|
input_pdf = sys.argv[1]
|
|
fields_json = sys.argv[2]
|
|
output_pdf = sys.argv[3]
|
|
|
|
fill_pdf_form(input_pdf, fields_json, output_pdf)
|