* Integrate litellm for multi-provider LLM support
* recover the default config yaml
* Use litellm.acompletion for native async support
* fix tob
* Rename llm_complete/allm_complete to llm_completion/llm_acompletion, remove unused llm_complete_stream
* Pin litellm to version 1.82.0
* resolve comments
* args from cli is used to overrides config.yaml
* Fix get_page_tokens hardcoded model default
Pass opt.model to get_page_tokens so tokenization respects the
configured model instead of always using gpt-4o-2024-11-20.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* Remove explicit openai dependency from requirements.txt
openai is no longer directly imported; it comes in as a transitive
dependency of litellm. Pinning it explicitly risks version conflicts.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* Restore openai==1.101.0 pin in requirements.txt
litellm==1.82.0 and openai-agents have conflicting openai version
requirements, but openai==1.101.0 works at runtime for both.
The pin is necessary to prevent litellm from pulling in openai>=2.x
which would break openai-agents.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* Remove explicit openai dependency from requirements.txt
openai is not directly used; it comes in as a transitive dependency
of litellm. No openai-agents in this branch so no pin needed.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix an litellm error log
* resolve comments
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
The loop variable `list_index = page_index - start_index` was
overwriting the outer `list_index = incorrect_item['list_index']`,
causing results to be written back to wrong index positions.
Rename the loop variable to `page_list_idx` to avoid shadowing.
Closes#66
Issues are opened by external users who don't have write permissions.
Add allowed_non_write_users: "*" so claude-code-action runs for all
issue authors, not just repo collaborators.
Backfill workflow triggers issue-dedupe via gh workflow run, which
makes the actor github-actions. Add it to allowed_bots so
claude-code-action accepts the trigger.
- Only retry 403 when rate-limit headers indicate throttling, not permission errors
- Add fetchAllComments() with pagination for issues with 100+ comments
- Add pagination loop in backfill workflow to handle repos with 200+ open issues
Replace the copilot-generated inline search logic with a claude-code-action
based architecture inspired by anthropic/claude-code's approach:
- Add .claude/commands/dedupe.md with 5-parallel-search strategy
- Add scripts/comment-on-duplicates.sh with 3-day grace period warning
- Rewrite issue-dedupe.yml to use claude-code-action + /dedupe command
- Rewrite autoclose script to check bot comments, human activity, and thumbsdown
- Rewrite backfill to trigger dedupe workflow per issue with rate limiting
- Add concurrency control, timeout, input validation, and rate limit retry
- Remove gh.sh (unnecessary), backfill-dedupe.js (replaced by workflow trigger)
The while loop exit condition used len(chat_history), but chat_history
was rebuilt every iteration with exactly 2 elements, making the check
len(chat_history) > 5 never true.
Replace with explicit attempt counter and max_attempts limit.
