gitea-admin/gh-christianlouis-docuelevate
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(ui): add verbose worker log detail to processing history on file detail page

Browse Source 
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2026-02-11 09:06:30 +00:00
parent f7799e409d
commit b18f5ee13c
10 changed files with 213 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/tasks/embed_metadata_into_pdf.py
+20 -3
View File
@@ -98,7 +98,14 @@ def embed_metadata_into_pdf(self, local_file_path: str, extracted_text: str, met
local_file_path = alt_path
else:
logger.error(f"[{task_id}] Local file {local_file_path} not found, cannot embed metadata.")
log_task_progress(task_id, "embed_metadata_into_pdf", "failure", "File not found", file_id=file_id)
log_task_progress(
task_id, "embed_metadata_into_pdf", "failure", "File not found", file_id=file_id,
detail=(
f"Local file not found, cannot embed metadata.\n"
f"Tried path: {local_file_path}\n"
f"Also tried: {alt_path}"
),
)
return {"error": "File not found"}
# Work on a safe copy in a secure temporary directory
@@ -184,7 +191,14 @@ def embed_metadata_into_pdf(self, local_file_path: str, extracted_text: str, met
# Trigger the next step: final storage.
logger.info(f"[{task_id}] Queueing final storage task")
log_task_progress(
task_id, "embed_metadata_into_pdf", "success", "Metadata embedded, queuing finalization", file_id=file_id
task_id, "embed_metadata_into_pdf", "success", "Metadata embedded, queuing finalization", file_id=file_id,
detail=(
f"Metadata embedded into PDF successfully.\n"
f"Original file: {original_file}\n"
f"Final file: {final_file_path}\n"
f"Metadata JSON: {json_path}\n"
f"Suggested filename: {suggested_filename}.pdf"
),
)
finalize_document_storage.delay(original_file, final_file_path, metadata, file_id=file_id)
@@ -209,7 +223,10 @@ def embed_metadata_into_pdf(self, local_file_path: str, extracted_text: str, met
except Exception as e:
logger.exception(f"[{task_id}] Failed to embed metadata into {processed_file}: {e}")
log_task_progress(task_id, "embed_metadata_into_pdf", "failure", f"Exception: {str(e)}", file_id=file_id)
log_task_progress(
task_id, "embed_metadata_into_pdf", "failure", f"Exception: {str(e)}", file_id=file_id,
detail=f"Failed to embed metadata into {processed_file}.\nOriginal file: {original_file}\nException: {str(e)}",
)
# Clean up temporary file in case of error
if os.path.exists(processed_file):
try:
app/tasks/extract_metadata_with_gpt.py
+12 -4
View File
@@ -111,13 +111,17 @@ def extract_metadata_with_gpt(self, filename: str, cleaned_text: str, file_id: i
content = completion.choices[0].message.content
logger.info(f"[{task_id}] Raw classification response for {filename}: {content[:200]}...")
log_task_progress(task_id, "call_openai", "success", "Received OpenAI response", file_id=file_id)
log_task_progress(
task_id, "call_openai", "success", "Received OpenAI response", file_id=file_id,
detail=f"Raw classification response:\n{content}",
)
json_text = extract_json_from_text(content)
if not json_text:
logger.error(f"[{task_id}] Could not find valid JSON in GPT response for {filename}.")
log_task_progress(
task_id, "extract_metadata_with_gpt", "failure", "Invalid JSON in response", file_id=file_id
task_id, "extract_metadata_with_gpt", "failure", "Invalid JSON in response", file_id=file_id,
detail=f"Could not parse valid JSON from GPT response.\nRaw response:\n{content}",
)
return {}
@@ -143,7 +147,8 @@ def extract_metadata_with_gpt(self, filename: str, cleaned_text: str, file_id: i
logger.info(f"[{task_id}] Extracted metadata: {metadata}")
log_task_progress(
task_id, "parse_metadata", "success", f"Parsed metadata: {list(metadata.keys())}", file_id=file_id
task_id, "parse_metadata", "success", f"Parsed metadata: {list(metadata.keys())}", file_id=file_id,
detail=f"Extracted metadata:\n{json.dumps(metadata, ensure_ascii=False, indent=2)}",
)
# Trigger the next step: embedding metadata into the PDF
@@ -158,5 +163,8 @@ def extract_metadata_with_gpt(self, filename: str, cleaned_text: str, file_id: i
except Exception as e:
logger.exception(f"[{task_id}] OpenAI classification failed for {filename}: {e}")
log_task_progress(task_id, "extract_metadata_with_gpt", "failure", f"Exception: {str(e)}", file_id=file_id)
log_task_progress(
task_id, "extract_metadata_with_gpt", "failure", f"Exception: {str(e)}", file_id=file_id,
detail=f"OpenAI classification failed for {filename}.\nException: {str(e)}",
)
return {}
app/tasks/process_document.py
+10 -1
View File
@@ -52,7 +52,10 @@ def process_document(self, original_local_file: str, original_filename: str = No
if not os.path.exists(original_local_file):
logger.error(f"[{task_id}] File {original_local_file} not found.")
log_task_progress(task_id, "process_document", "failure", "File not found")
log_task_progress(
task_id, "process_document", "failure", "File not found",
detail=f"File not found on disk: {original_local_file}",
)
return {"error": "File not found"}
# 0. Compute the file hash and check for duplicates
@@ -104,6 +107,12 @@ def process_document(self, original_local_file: str, original_filename: str = No
"success",
"Duplicate file detected, skipping",
file_id=existing.id,
detail=(
f"Duplicate file detected.\n"
f"File hash: {filehash}\n"
f"Existing file record ID: {existing.id}\n"
f"Original filename: {original_filename}"
),
)
return {
"status": "duplicate_file",
app/tasks/upload_to_paperless.py
+6 -2
View File
@@ -245,13 +245,17 @@ def upload_to_paperless(self, file_path: str, file_id: int = None):
resp.raise_for_status()
except requests.exceptions.RequestException as exc:
error_msg = f"Failed to upload to Paperless: {exc}"
response_text = getattr(exc.response, "text", "<no response>")
logger.error(
f"[{task_id}] Failed to upload document '%s' to Paperless. Error: %s. Response=%s",
file_path,
exc,
getattr(exc.response, "text", "<no response>"),
response_text,
)
log_task_progress(
task_id, "upload_to_paperless", "failure", error_msg, file_id=file_id,
detail=f"Failed to upload document to Paperless.\nFile: {file_path}\nError: {exc}\nResponse: {response_text}",
)
log_task_progress(task_id, "upload_to_paperless", "failure", error_msg, file_id=file_id)
raise
raw_task_id = resp.text.strip().strip('"').strip("'")