Feishu Literature Manager

User provides: topic + number of papers
           ↓
1. Create Feishu Bitable
           ↓
2. Create all 17 required fields
           ↓
3. Search PubMed for papers
           ↓
4. Parse and validate results
           ↓
5. Extract complete metadata
           ↓
6. Translate titles and abstracts
           ↓
7. Add papers to table (PARALLEL CALLS)
           ↓
8. Set table permissions (full_access)
           ↓
9. Report completion

User provides: research topic + specific focus + table URL + number of papers
           ↓
1. Parse table URL to get app_token and table_id
           ↓
2. Get existing records to extract current PMIDs
           ↓
3. Search PubMed with focused keywords
           ↓
4. Filter out existing PMIDs (deduplication)
           ↓
5. Score and rank papers by relevance
           ↓
6. Select top N papers
           ↓
7. Fetch XML data for selected papers
           ↓
8. Parse metadata and translate
           ↓
9. Add papers to table (PARALLEL CALLS - 5-10 at a time)
           ↓
10. Report completion with summary

User requests: topic + N papers (N > 5)
           ↓
Calculate batches: ceil(N / 5)
           ↓
For each batch (5 papers):
  1. Fetch PMIDs for this batch
  2. Retrieve XML data
  3. Parse metadata
  4. Translate titles and abstracts
  5. Add all 5 papers to table with COMPLETE fields
  6. Report batch completion
           ↓
Continue to next batch
           ↓
All batches complete → Report final status

Batch 1 (Papers 1-5):
  - Fetch PMIDs 1-5
  - Get XML data
  - Parse and translate
  - Add 5 papers with complete fields (including 摘要)
  - Report: "第一批完成，已添加5篇文献"

Batch 2 (Papers 6-10):
  - Fetch PMIDs 6-10
  - Get XML data
  - Parse and translate
  - Add 5 papers with complete fields (including 摘要)
  - Report: "第二批完成，已添加5篇文献"

Final Report: "任务全部完成！共添加10篇文献"

// CORRECT: Parallel calls (5-10 papers at once)
<function_calls>
<invoke name="feishu_bitable_create_record">
<parameter name="app_token">xxx</parameter>
<parameter name="table_id">xxx</parameter>
<parameter name="fields">{paper 1 data}</parameter>
</invoke>
<invoke name="feishu_bitable_create_record">
<parameter name="app_token">xxx</parameter>
<parameter name="table_id">xxx</parameter>
<parameter name="fields">{paper 2 data}</parameter>
</invoke>
<invoke name="feishu_bitable_create_record">
<parameter name="app_token">xxx</parameter>
<parameter name="table_id">xxx</parameter>
<parameter name="fields">{paper 3 data}</parameter>
</invoke>
... (up to 10 calls at once)
</function_calls>

// WRONG: Sequential calls (SLOW!)
<function_calls>
<invoke name="feishu_bitable_create_record">...</invoke>
</function_calls>
// Wait for response...
<function_calls>
<invoke name="feishu_bitable_create_record">...</invoke>
</function_calls>
// Wait for response...

# Step 1: Prepare all paper data
papers_data = [prepare_paper_data(p) for p in papers[:10]]

# Step 2: Make parallel calls (submit all at once)
# All 10 feishu_bitable_create_record calls in same function_calls block
results = parallel_add_papers(papers_data)

# Step 3: Report results
print(f"Successfully added {len(results)} papers in one batch!")

# Extract app_token from URL
# URL format: https://xxx.feishu.cn/base/APP_TOKEN?table=TABLE_ID
# Or: https://xxx.feishu.cn/wiki/xxx?table=TABLE_ID

# Get existing records
records = feishu_bitable_list_records(
    app_token=app_token,
    table_id=table_id,
    page_size=500  # Get all records
)

# Extract existing PMIDs
existing_pmids = set()
for record in records['records']:
    pmid = record['fields'].get('PMID')
    if pmid:
        existing_pmids.add(pmid)

print(f"Existing records: {len(records['records'])}, Unique PMIDs: {len(existing_pmids)}")

# Combine research topic with specific focus
# Example: "胃神经内分泌肿瘤" + "药物临床研究"

# Search terms for different focuses:
FOCUS_KEYWORDS = {
    "药物临床研究": [
        "chemotherapy", "targeted therapy", "PRRT", "somatostatin analog",
        "everolimus", "sunitinib", "octreotide", "lanreotide", "immunotherapy",
        "PD-1", "PD-L1", "temozolomide", "capecitabine", "177Lu", "Lutetium",
        "clinical trial", "phase", "randomized", "treatment"
    ],
    "手术治疗": [
        "surgery", "resection", "gastrectomy", "endoscopic resection",
        "lymph node dissection", "surgical outcome"
    ],
    "诊断方法": [
        "diagnosis", "biomarker", "PET/CT", "endoscopy", "pathology",
        "immunohistochemistry", "molecular marker"
    ],
    "预后评估": [
        "prognosis", "survival", "outcome", "risk factor", "nomogram"
    ]
}

# Build search query
search_query = f"({topic}) AND ({' OR '.join(focus_keywords)})"

# Search PubMed
response = curl(f"https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term={search_query}&retmax=50&retmode=json&sort=pub_date")

new_pmids = [pmid for pmid in response['idlist'] if pmid not in existing_pmids]

print(f"Found {len(response['idlist'])} papers, {len(new_pmids)} are new")

# Fetch detailed info for new PMIDs
xml_data = curl(f"https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id={','.join(new_pmids)}&retmode=xml")

# Score each paper
def score_paper(paper, focus):
    score = 0
    title = paper['title'].lower()
    abstract = paper['abstract'].lower()[:500]
    
    # High relevance: keyword in title
    for kw in FOCUS_KEYWORDS.get(focus, []):
        if kw.lower() in title:
            score += 3
        if kw.lower() in abstract:
            score += 1
    
    # Neuroendocrine in title
    if 'neuroendocrine' in title or 'net' in title:
        score += 2
    
    # Clinical trial/phase in title
    if 'trial' in title or 'phase' in title:
        score += 2
    
    return score

# Sort by score
scored_papers = [(score_paper(p, focus), p) for p in papers]
scored_papers.sort(reverse=True, key=lambda x: x[0])

# Select top N
selected_papers = [p for score, p in scored_papers[:number_requested]]

# Prepare all paper data
papers_data = [prepare_full_paper_data(p) for p in selected_papers]

# Make PARALLEL API calls (5-10 at a time)
# Submit all feishu_bitable_create_record calls in SAME function_calls block
results = parallel_add_papers(papers_data)

# Report results
print(f"✅ Added {len(results)} papers successfully!")