bryanb
/
Big-Link-Man
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fixed & Tested - Creates titles in batched of 25 for more diversity of ideas.

main
PeninsulaInd 2025-10-24 11:24:27 -05:00
parent 083a8cacdd
commit b29a3f3249
6 changed files with 712 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
JOB_FIELD_REFERENCE.md
View File

@ -28,6 +28,7 @@ min_h3_tags - Integer
max_h3_tags - Integer
models - {title, outline, content} - overrides job-level
interlinking - {links_per_article_min, links_per_article_max, see_also_min, see_also_max} - overrides job-level
anchor_text_config - {mode, custom_text} - overrides job-level for this tier only
```
## Field Behaviors
@ -38,10 +39,11 @@ interlinking - {links_per_article_min, links_per_article_max, see_also_
**models**: Use format "provider/model-name" (e.g., "openai/gpt-4o-mini")
**anchor_text_config**: Job-level only, applies to ALL tiers (no tier-specific option)
**anchor_text_config**: Can be set at job-level (all tiers) or tier-level (specific tier)
- "default" = Use master.config.json tier rules
- "override" = Replace with custom_text for all tiers
- "append" = Add custom_text to tier rules for all tiers
- "override" = Replace with custom_text
- "append" = Add custom_text to tier rules
- Tier-level config overrides job-level config for that tier
**tiered_link_count_range**: How many links to lower tier
- Tier1: Always 1 link to money site (this setting ignored)

484
docs/stories/story-2.6-batch-title-generation.md 100644
View File

@ -0,0 +1,484 @@
# Story 2.6: Batch Title Generation
## Overview
Refactor title generation to generate all titles for a tier in batches before article generation begins. This prevents title similarity issues that occur when titles are generated sequentially one at a time.
## Status
**PLANNED**
## Story Details
**As a User**, I want all article titles for a tier to be generated together in batches, so that the AI can ensure title diversity and prevent repetitive titles.
## Acceptance Criteria
### 1. Batch Title Generation Before Articles
**Status:** PENDING
- All titles for a tier are generated before any article content generation begins
- Titles are generated in batches of 25 (or the tier count if less than 25)
- AI prompt instructs generation of N distinct titles in a single call
- Each batch request includes instructions to ensure title diversity
### 2. Title File Persistence
**Status:** PENDING
- Generated titles written to: `debug_output/project_{id}_tier_{name}_titles_{timestamp}.txt`
- One title per line
- File is written before article generation loop begins
- Titles loaded from file and used sequentially during article generation
### 3. Console Output
**Status:** PENDING
- Print complete list of generated titles to console after generation
- Show title count and batch information
- Format: numbered list for easy review
### 4. Error Handling
**Status:** PENDING
- Retry entire batch on generation failure (up to 3 attempts)
- Fail tier processing after 3 failed batch attempts
- If AI returns fewer titles than requested (e.g., 20 instead of 25):
- Log warning to console
- Continue with partial batch
- Generate remaining titles in next batch or individually
### 5. Existing Title Validation
**Status:** PENDING
- Continue to validate individual titles (keyword presence, length)
- No new diversity or similarity validation required
- Existing validation logic unchanged
### 6. Backward Compatibility
**Status:** PENDING
- No changes to job file schema
- No changes to CLI interface
- Transparent change to users
- Article generation loop works with pre-generated titles
## Implementation Details
### Architecture Changes
#### 1. New Prompt Template
**File:** `src/generation/prompts/batch_title_generation.json`
**Format:**
```json
{
"system_message": "You are an expert creative content writer who creates compelling, search-optimized titles that attract clicks while accurately representing the content topic. When generating multiple titles, ensure each takes a unique angle or approach to maximize diversity. Be creative - the titles just need to be tangentially related to the search topic {keyword}. ",
"user_prompt": "Generate {count} distinct, creative titles for articles about: {keyword}\n\nRelated entities: {entities}\nRelated searches: {related_searches}\n\nIMPORTANT: Each title should take a different angle or approach. Ensure diversity across all titles.\n\nReturn exactly {count} titles, one per line. No numbering, quotes, or formatting - just the title text."
}
```
#### 2. ContentGenerator Service Enhancement
**File:** `src/generation/service.py`
**New Method:**
```python
def generate_titles_batch(
self,
project_id: int,
count: int,
batch_size: int = 25,
debug: bool = False,
model: Optional[str] = None
) -> List[str]:
"""
Generate multiple titles in batches
Args:
project_id: Project ID to generate titles for
count: Total number of titles needed
batch_size: Number of titles per AI call (default: 25)
debug: If True, save responses to debug_output/
model: Optional model override for this generation stage
Returns:
List of generated title strings
"""
# Load project data
# Loop in batches of batch_size
# For each batch:
# - Call AI with batch_title_generation prompt
# - Parse newline-separated titles
# - Validate each title
# - Retry batch up to 3 times on failure
# - Warn if fewer titles returned than requested
# Aggregate all titles
# Return list
```
**Key Details:**
- Use max_tokens: 100 * batch_size (e.g., 2500 for 25 titles)
- Temperature: 0.7 (same as current)
- Parse response by splitting on newlines
- Strip whitespace, quotes, numbering from each line
- Validate each title using existing validation logic
- 3 retry attempts per batch
#### 3. BatchProcessor Refactoring
**File:** `src/generation/batch_processor.py`
**New Method:**
```python
def _generate_all_titles_for_tier(
self,
project_id: int,
tier_name: str,
tier_config: TierConfig,
debug: bool
) -> str:
"""
Generate all titles for a tier and save to file
Args:
project_id: Project ID
tier_name: Name of tier (e.g., "tier1")
tier_config: Tier configuration
debug: Debug mode flag
Returns:
Path to generated titles file
"""
# Generate timestamp
# Call service.generate_titles_batch(count=tier_config.count)
# Create filename: debug_output/project_{id}_tier_{name}_titles_{timestamp}.txt
# Write titles to file (one per line)
# Print titles to console (numbered list)
# Return file path
```
**Modified Method:** `_process_tier()`
```python
def _process_tier(...):
"""Process a single tier with pre-generated titles"""
# NEW: Generate all titles first
click.echo(f"\n[{tier_name}] Generating {tier_config.count} titles in batches...")
titles_file = self._generate_all_titles_for_tier(
project_id, tier_name, tier_config, debug
)
# NEW: Load titles from file
with open(titles_file, 'r', encoding='utf-8') as f:
titles = [line.strip() for line in f if line.strip()]
click.echo(f"[{tier_name}] Generated {len(titles)} titles")
click.echo(f"[{tier_name}] Titles saved to: {titles_file}")
# NEW: Print titles to console
click.echo(f"\n[{tier_name}] Title List:")
for i, title in enumerate(titles, 1):
click.echo(f" {i}. {title}")
click.echo()
# EXISTING: Loop through articles
for article_num in range(1, tier_config.count + 1):
article_index = article_num - 1
# NEW: Get pre-generated title
if article_index < len(titles):
title = titles[article_index]
else:
click.echo(f" Warning: Not enough titles generated, skipping article {article_num}")
continue
# MODIFIED: Call with pre-generated title
self._generate_single_article(
project_id=project_id,
tier_name=tier_name,
tier_config=tier_config,
article_num=article_num,
article_index=article_index,
title=title, # NEW PARAMETER
keyword=keyword,
resolved_targets=resolved_targets,
debug=debug
)
```
**Modified Method:** `_generate_single_article()`
```python
def _generate_single_article(
self,
project_id: int,
tier_name: str,
tier_config: TierConfig,
article_num: int,
article_index: int,
title: str, # NEW PARAMETER
keyword: str,
resolved_targets: Dict[str, int],
debug: bool
):
"""Generate a single article with pre-generated title"""
prefix = f" [{article_num}/{tier_config.count}]"
# ... site assignment logic ...
# REMOVED: Title generation block
# click.echo(f"{prefix} Generating title...")
# title = self.generator.generate_title(...)
# NEW: Just use the provided title
click.echo(f"{prefix} Using title: \"{title}\"")
# EXISTING: Generate outline and content
click.echo(f"{prefix} Generating outline...")
outline = self.generator.generate_outline(...)
# ... rest of method unchanged ...
```
### Console Output Example
```
[tier1] Generating 5 titles in batches...
[tier1] Generated 5 titles
[tier1] Titles saved to: debug_output/project_1_tier1_titles_20251024_143052.txt
[tier1] Title List:
1. Complete Guide to Shaft Machining: Techniques and Best Practices
2. Advanced CNC Shaft Machining: From Setup to Finish
3. Troubleshooting Common Shaft Machining Challenges
4. Precision Shaft Manufacturing: Tools and Equipment Guide
5. How to Optimize Shaft Machining Operations for Higher Output
Processing tier1: 5 articles...
[1/5] Assigned to site: getcnc.info (ID: 1)
[1/5] Using title: "Complete Guide to Shaft Machining: Techniques and Best Practices"
[1/5] Generating outline...
[1/5] Generated outline: 4 H2s, 8 H3s
[1/5] Generating content...
...
```
### Batch Size Logic
**Determining Batch Size:**
- If tier count <= 25: Use tier count (single batch)
- If tier count > 25: Use batches of 25
**Examples:**
- 5 articles: 1 batch of 5
- 20 articles: 1 batch of 20
- 25 articles: 1 batch of 25
- 50 articles: 2 batches of 25 each
- 100 articles: 4 batches of 25 each
### Error Scenarios
**Scenario 1: AI Call Fails**
- Retry entire batch (up to 3 attempts)
- After 3 failures: Fail tier processing
- Log error message to console
**Scenario 2: AI Returns Fewer Titles Than Requested**
```
Warning: Requested 25 titles but received 20. Continuing with partial batch.
```
- Continue with titles received
- Process remaining count in next batch
**Scenario 3: AI Returns More Titles Than Requested**
- Use first N titles (where N = requested count)
- Discard extras
**Scenario 4: Malformed Response**
- Retry batch (counts toward 3 attempts)
- Log parsing error
### File Management
**Title File Format:**
```
Complete Guide to Shaft Machining: Techniques and Best Practices
Advanced CNC Shaft Machining: From Setup to Finish
Troubleshooting Common Shaft Machining Challenges
Precision Shaft Manufacturing: Tools and Equipment Guide
How to Optimize Shaft Machining Operations for Higher Output
```
**File Location:**
- Directory: `debug_output/`
- Naming: `project_{project_id}_tier_{tier_name}_titles_{timestamp}.txt`
- Encoding: UTF-8
- Format: One title per line, no extra formatting
**File Lifecycle:**
- Created at start of tier processing
- Read once after creation
- Preserved for debugging/review
- Not deleted after processing
## Testing Strategy
### Unit Tests
**File:** `tests/unit/test_generation_service.py`
New tests:
- `test_generate_titles_batch_single_batch()` - 5 titles
- `test_generate_titles_batch_multiple_batches()` - 50 titles
- `test_generate_titles_batch_exact_25()` - 25 titles
- `test_generate_titles_batch_retry_on_failure()` - Failure handling
- `test_generate_titles_batch_partial_return()` - Fewer titles returned
- `test_generate_titles_batch_validation()` - Individual title validation
### Integration Tests
**File:** `tests/integration/test_batch_title_generation.py`
New tests:
- `test_tier_processing_with_batch_titles()` - Full tier with pre-generated titles
- `test_title_file_creation_and_loading()` - File I/O
- `test_console_output_formatting()` - Output validation
- `test_multiple_batches_aggregation()` - 100 articles across 4 batches
### Manual Testing
```bash
# Small batch (5 articles)
python main.py generate-batch -j jobs/test_shaft_machining.json -u admin -p password
# Medium batch (20 articles)
python main.py generate-batch -j jobs/tier2_20articles.json -u admin -p password
# Large batch (100 articles)
python main.py generate-batch -j jobs/tier3_100articles.json -u admin -p password
```
**Validation Checklist:**
- [ ] Titles file created in debug_output/
- [ ] All titles printed to console
- [ ] No duplicate/similar titles in batch
- [ ] Article generation uses pre-generated titles
- [ ] "Generating title..." message removed from article loop
- [ ] "Using title: ..." message present instead
## Design Decisions
### Why Batches of 25?
- Balances context window usage vs API efficiency
- Allows AI to see enough titles to ensure diversity
- Reasonable token count (~2500 output tokens)
- Easy to retry on failure
### Why Write to File?
- Provides debugging artifact
- Separates title generation from article pipeline
- Enables manual review if needed
- Fault tolerance: titles preserved if article generation crashes
### Why Not Store in Database First?
- Simpler implementation
- No partial GeneratedContent records
- Clear separation of concerns
- File serves as intermediate format
### Why Print to Console?
- Immediate visibility for user
- Quick sanity check on title quality
- Helps identify if batch generation is working
- Minimal cost (just console output)
### Why Allow Partial Batches?
- More resilient to AI inconsistencies
- Better than failing entire tier
- Warning provides visibility
- Can continue processing with available titles
## Known Limitations
1. **No Similarity Scoring**: Does not quantitatively measure title diversity
2. **No Manual Review Step**: Fully automated, no approval gate
3. **Sequential Batches**: Batches generated sequentially, not in parallel
4. **Fixed Batch Size**: 25 is hardcoded (not configurable per job)
5. **No Title Regeneration**: Can't regenerate individual bad titles
## Migration Notes
**No Breaking Changes:**
- CLI interface unchanged
- Job file schema unchanged
- Database schema unchanged
- Existing validation unchanged
**Transparent to Users:**
- Only console output differs
- New debug files appear
- Articles generated same way
## Files Created/Modified
### New Files:
- `src/generation/prompts/batch_title_generation.json` - Batch title prompt
- `tests/unit/test_batch_title_generation.py` - Unit tests
- `tests/integration/test_batch_title_generation.py` - Integration tests
- `docs/stories/story-2.6-batch-title-generation.md` - This document
### Modified Files:
- `src/generation/service.py` - Add generate_titles_batch() method
- `src/generation/batch_processor.py` - Refactor _process_tier() and _generate_single_article()
- `src/generation/ai_client.py` - May need token limit adjustments (if hardcoded)
## Performance Impact
**Before (Sequential):**
- Title per article: ~3-5 seconds
- 25 articles: ~75-125 seconds for titles alone
**After (Batch):**
- 25 titles in 1 batch: ~8-12 seconds
- 25 articles: ~8-12 seconds for all titles
**Improvement:**
- ~85% faster title generation
- Better API efficiency (fewer calls)
- Improved title diversity (subjective)
## Next Steps
After Story 2.6 completion:
- Monitor title quality and diversity in production
- Consider adding similarity scoring if issues persist
- Potential future: Manual review step for Tier 1 titles
- Potential future: Configurable batch size in job files
## Completion Checklist
- [ ] Create batch_title_generation.json prompt
- [ ] Add generate_titles_batch() to ContentGenerator
- [ ] Add _generate_all_titles_for_tier() to BatchProcessor
- [ ] Refactor _process_tier() for batch titles
- [ ] Modify _generate_single_article() signature
- [ ] Implement title file I/O
- [ ] Add console output formatting
- [ ] Implement retry logic (3 attempts)
- [ ] Implement partial batch handling
- [ ] Write unit tests
- [ ] Write integration tests
- [ ] Manual testing with 5, 20, 100 article batches
- [ ] Update documentation
- [ ] Code review
## Success Metrics
**Primary:**
- All titles generated before article content generation
- Titles stored in debug_output files
- Article generation uses pre-generated titles
**Secondary:**
- Subjectively less repetitive titles (manual review)
- Faster title generation (85% improvement)
- No regression in title quality validation
## Notes
- This change addresses user feedback about title similarity
- Batch generation allows AI to "see" all titles and ensure diversity
- File-based approach provides debugging capability
- No changes to downstream systems (outline, content, interlinking)
- Maintains existing validation and error handling patterns

87
src/generation/batch_processor.py
View File

@ -5,6 +5,8 @@ Batch processor for content generation jobs
from typing import Dict, Any, Optional
import click
import os
from pathlib import Path
from datetime import datetime
from src.generation.service import ContentGenerator
from src.generation.job_config import JobConfig, Job, TierConfig
from src.generation.deployment_assignment import validate_and_resolve_targets, assign_site_for_article
@ -73,6 +75,54 @@ class BatchProcessor:
self._print_summary()
def _generate_all_titles_for_tier(
self,
project_id: int,
tier_name: str,
tier_config: TierConfig,
debug: bool,
model: Optional[str] = None
) -> str:
"""
Generate all titles for a tier and save to file
Args:
project_id: Project ID
tier_name: Name of tier (e.g., "tier1")
tier_config: Tier configuration
debug: Debug mode flag
model: Optional model override for title generation
Returns:
Path to generated titles file
"""
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
titles = self.generator.generate_titles_batch(
project_id=project_id,
count=tier_config.count,
batch_size=25,
debug=debug,
model=model
)
debug_dir = Path("debug_output")
debug_dir.mkdir(exist_ok=True)
filename = f"project_{project_id}_tier_{tier_name}_titles_{timestamp}.txt"
filepath = debug_dir / filename
with open(filepath, 'w', encoding='utf-8') as f:
for title in titles:
f.write(title + '\n')
click.echo(f"\n[{tier_name}] Title List:")
for i, title in enumerate(titles, 1):
click.echo(f" {i}. {title}")
click.echo()
return str(filepath)
def _process_single_job(
self,
job: Job,
@ -149,18 +199,41 @@ class BatchProcessor:
debug: bool,
continue_on_error: bool
):
"""Process all articles for a tier"""
"""Process all articles for a tier with pre-generated titles"""
click.echo(f" {tier_name}: Generating {tier_config.count} articles")
project = self.project_repo.get_by_id(project_id)
keyword = project.main_keyword
models = job.models if job.models else None
click.echo(f"\n[{tier_name}] Generating {tier_config.count} titles in batches...")
titles_file = self._generate_all_titles_for_tier(
project_id,
tier_name,
tier_config,
debug,
model=models.title if models else None
)
with open(titles_file, 'r', encoding='utf-8') as f:
titles = [line.strip() for line in f if line.strip()]
click.echo(f"[{tier_name}] Generated {len(titles)} titles")
click.echo(f"[{tier_name}] Titles saved to: {titles_file}")
targets_for_tier = resolved_targets if tier_name == "tier1" else {}
for article_num in range(1, tier_config.count + 1):
self.stats["total_articles"] += 1
article_index = article_num - 1
if article_index >= len(titles):
click.echo(f" Warning: Not enough titles generated, skipping article {article_num}")
continue
title = titles[article_index]
try:
self._generate_single_article(
project_id,
@ -168,6 +241,7 @@ class BatchProcessor:
tier_config,
article_num,
article_index,
title,
keyword,
targets_for_tier,
debug
@ -213,11 +287,12 @@ class BatchProcessor:
tier_config: TierConfig,
article_num: int,
article_index: int,
title: str,
keyword: str,
resolved_targets: Dict[str, int],
debug: bool
):
"""Generate a single article"""
"""Generate a single article with pre-generated title"""
prefix = f" [{article_num}/{tier_config.count}]"
models = self.current_job.models if hasattr(self, 'current_job') and self.current_job.models else None
@ -230,13 +305,7 @@ class BatchProcessor:
elif resolved_targets:
click.echo(f"{prefix} No site assignment (index {article_index} >= {len(resolved_targets)} targets)")
click.echo(f"{prefix} Generating title...")
title = self.generator.generate_title(
project_id,
debug=debug,
model=models.title if models else None
)
click.echo(f"{prefix} Generated title: \"{title}\"")
click.echo(f"{prefix} Using title: \"{title}\"")
click.echo(f"{prefix} Generating outline...")
outline = self.generator.generate_outline(

39
src/generation/job_config.py
View File

@ -77,6 +77,7 @@ class TierConfig:
max_h2_tags: int
min_h3_tags: int
max_h3_tags: int
anchor_text_config: Optional[AnchorTextConfig] = None
@dataclass
@ -305,6 +306,22 @@ class JobConfig:
"""Parse tier configuration with defaults (object format)"""
defaults = TIER_DEFAULTS.get(tier_name, TIER_DEFAULTS["tier3"])
# Parse tier-level anchor_text_config if present
anchor_text_config = None
if "anchor_text_config" in tier_data:
anchor_text_data = tier_data["anchor_text_config"]
if not isinstance(anchor_text_data, dict):
raise ValueError(f"'{tier_name}.anchor_text_config' must be an object")
if "mode" not in anchor_text_data:
raise ValueError(f"'{tier_name}.anchor_text_config' must have 'mode' field")
mode = anchor_text_data["mode"]
if mode not in ["default", "override", "append"]:
raise ValueError(f"'{tier_name}.anchor_text_config' mode must be 'default', 'override', or 'append'")
custom_text = anchor_text_data.get("custom_text")
if custom_text is not None and not isinstance(custom_text, list):
raise ValueError(f"'{tier_name}.anchor_text_config' custom_text must be an array")
anchor_text_config = AnchorTextConfig(mode=mode, custom_text=custom_text)
return TierConfig(
count=tier_data.get("count", 1),
min_word_count=tier_data.get("min_word_count", defaults["min_word_count"]),
@ -312,7 +329,8 @@ class JobConfig:
min_h2_tags=tier_data.get("min_h2_tags", defaults["min_h2_tags"]),
max_h2_tags=tier_data.get("max_h2_tags", defaults["max_h2_tags"]),
min_h3_tags=tier_data.get("min_h3_tags", defaults["min_h3_tags"]),
max_h3_tags=tier_data.get("max_h3_tags", defaults["max_h3_tags"])
max_h3_tags=tier_data.get("max_h3_tags", defaults["max_h3_tags"]),
anchor_text_config=anchor_text_config
)
def _parse_tier_from_array(self, tier_name: str, tier_data: dict) -> TierConfig:
@ -322,6 +340,22 @@ class JobConfig:
# Array format uses "article_count" instead of "count"
count = tier_data.get("article_count", tier_data.get("count", 1))
# Parse tier-level anchor_text_config if present
anchor_text_config = None
if "anchor_text_config" in tier_data:
anchor_text_data = tier_data["anchor_text_config"]
if not isinstance(anchor_text_data, dict):
raise ValueError(f"'{tier_name}.anchor_text_config' must be an object")
if "mode" not in anchor_text_data:
raise ValueError(f"'{tier_name}.anchor_text_config' must have 'mode' field")
mode = anchor_text_data["mode"]
if mode not in ["default", "override", "append"]:
raise ValueError(f"'{tier_name}.anchor_text_config' mode must be 'default', 'override', or 'append'")
custom_text = anchor_text_data.get("custom_text")
if custom_text is not None and not isinstance(custom_text, list):
raise ValueError(f"'{tier_name}.anchor_text_config' custom_text must be an array")
anchor_text_config = AnchorTextConfig(mode=mode, custom_text=custom_text)
return TierConfig(
count=count,
min_word_count=tier_data.get("min_word_count", defaults["min_word_count"]),
@ -329,7 +363,8 @@ class JobConfig:
min_h2_tags=tier_data.get("min_h2_tags", defaults["min_h2_tags"]),
max_h2_tags=tier_data.get("max_h2_tags", defaults["max_h2_tags"]),
min_h3_tags=tier_data.get("min_h3_tags", defaults["min_h3_tags"]),
max_h3_tags=tier_data.get("max_h3_tags", defaults["max_h3_tags"])
max_h3_tags=tier_data.get("max_h3_tags", defaults["max_h3_tags"]),
anchor_text_config=anchor_text_config
)
def get_jobs(self) -> list[Job]:

94
src/generation/service.py
View File

@ -7,7 +7,7 @@ import json
from html import unescape
from pathlib import Path
from datetime import datetime
from typing import Optional, Tuple
from typing import Optional, Tuple, List
from src.generation.ai_client import AIClient, PromptManager
from src.database.repositories import ProjectRepository, GeneratedContentRepository, SiteDeploymentRepository
from src.templating.service import TemplateService
@ -75,6 +75,98 @@ class ContentGenerator:
return title
def generate_titles_batch(
self,
project_id: int,
count: int,
batch_size: int = 25,
debug: bool = False,
model: Optional[str] = None
) -> List[str]:
"""
Generate multiple titles in batches
Args:
project_id: Project ID to generate titles for
count: Total number of titles needed
batch_size: Number of titles per AI call (default: 25)
debug: If True, save responses to debug_output/
model: Optional model override for this generation stage
Returns:
List of generated title strings
"""
project = self.project_repo.get_by_id(project_id)
if not project:
raise ValueError(f"Project {project_id} not found")
entities_str = ", ".join(project.entities or [])
related_str = ", ".join(project.related_searches or [])
all_titles = []
titles_remaining = count
while titles_remaining > 0:
current_batch_size = min(batch_size, titles_remaining)
system_msg, user_prompt = self.prompt_manager.format_prompt(
"batch_title_generation",
keyword=project.main_keyword,
entities=entities_str,
related_searches=related_str,
count=current_batch_size
)
batch_titles = None
for attempt in range(3):
try:
response = self.ai_client.generate_completion(
prompt=user_prompt,
system_message=system_msg,
max_tokens=100 * current_batch_size,
temperature=0.7,
override_model=model
)
lines = response.strip().split('\n')
batch_titles = []
for line in lines:
line = line.strip()
if not line:
continue
line = re.sub(r'^\d+[\.\)]\s*', '', line)
line = line.strip('"').strip("'")
if line:
batch_titles.append(line)
if len(batch_titles) < current_batch_size:
print(f"Warning: Requested {current_batch_size} titles but received {len(batch_titles)}. Continuing with partial batch.")
if len(batch_titles) > current_batch_size:
batch_titles = batch_titles[:current_batch_size]
break
except Exception as e:
if attempt == 2:
raise ValueError(f"Failed to generate batch after 3 attempts: {e}")
print(f"Batch generation attempt {attempt + 1} failed: {e}, retrying...")
if batch_titles:
all_titles.extend(batch_titles)
titles_remaining -= len(batch_titles)
else:
raise ValueError("Failed to generate any titles in batch")
if debug:
for i, title in enumerate(all_titles, 1):
self._save_debug_output(
project_id, f"batch_title_{i}", title, "txt"
)
return all_titles
def generate_outline(
self,
project_id: int,

13
src/interlinking/content_injection.py
View File

@ -276,12 +276,21 @@ def _get_anchor_texts_for_tier(
job_config,
count: int = 5
) -> List[str]:
"""Get anchor texts for a tier, applying job config overrides"""
"""Get anchor texts for a tier, applying tier-level or job-level config overrides"""
# Get default tier-based anchor texts
default_anchors = get_anchor_text_for_tier(tier, project, count)
# Apply job config overrides if present
# Check tier-level config first, then fall back to job-level
anchor_text_config = None
# Try tier-level config
if hasattr(job_config, 'tiers') and tier in job_config.tiers:
tier_config = job_config.tiers[tier]
if hasattr(tier_config, 'anchor_text_config'):
anchor_text_config = tier_config.anchor_text_config
# Fall back to job-level config if no tier-level config
if not anchor_text_config:
if hasattr(job_config, 'anchor_text_config'):
anchor_text_config = job_config.anchor_text_config
elif isinstance(job_config, dict):