- Added new entries to .gitignore for development and internal files.
- Updated `pyproject.toml` to include `logfire` and modified dependency specifications.
- Enhanced `uv.lock` with new package versions and added `babel`, `backrefs`, and `ghp-import` packages.

…rrect endpoint. This change ensures proper connectivity for the model's API interactions.

…cements. Introduce `POST /v2/extract` for body-based extraction, maintaining existing `GET /v2/extract/{full_path}` functionality. Implement `V2ExtractRequest` model for request validation and update API to handle new endpoint. Enhance documentation and tests to reflect these changes, ensuring improved extraction capabilities and user experience.

…ce the `gimie` function to manage exceptions more effectively, including specific handling for HTTP and connection errors. Update repository analysis logging to provide clearer insights on GIMIE output and analysis success. Additionally, refactor cache management to ensure robust data persistence with improved error logging for cache operations.

… devcontainer configuration to include SSH support and modify post-create commands. Introduce a new script to set the VS Code user's password at container start, enhancing security and usability.

…configuration. Add instructions for local .env setup to enhance security and usability.

…vironment. Add .env.example for environment variable configuration and update devcontainer.json to utilize docker-compose for service management, enhancing container orchestration and usability.

…improve post-create command. Add UV_CACHE_DIR to avoid root-owned cache issues and ensure proper cache directory creation during setup.

…optional DNS configuration. Update documentation to clarify environment variable setup for improved container networking and usability.

…tup. Add DNS resolver instructions to .env.example and include .uv-cache/ in .gitignore to prevent cache files from being tracked. Adjust schema paths in AGENTS.md and scripts for consistency with new directory structure.

…ship assessment and linked entities enrichment. Add main agent for fetching repository information, EPFL assessment prompts, and linked entities enrichment tools. Implement organization enrichment module for enhanced metadata analysis. Establish logging and configuration validation for robust agent management.

… warnings from agents and modules. Clean up unused files related to legacy imports across various components, streamlining the codebase for improved maintainability.

…text for improved context loading. Remove unused graph-related imports and clean up deprecated code in API and related modules, enhancing maintainability and performance.

…mponents. Clean up unused imports and environment variable checks, streamlining the codebase for improved maintainability and performance.

…apture_provider_snapshots.py, generate_mock_data.py, and related testing files to streamline the codebase and enhance maintainability.

…umentation. Update .env.example with additional environment variables and descriptions for improved clarity. Modify .gitignore to include logs and cache directories. Introduce new async job handling for the extraction process in the API, along with companion endpoints for job status retrieval. Update AGENTS.md and API reference documentation to reflect new tools and functionalities.

…etection. Introduce a new pipeline stage for determining parent-child relationships among organizations using an LLM agent. Add prompts for LLM input and output formatting, ensuring compliance with hierarchy rules. Update API to integrate the new stage and handle warnings for rejected relationships.

… Introduce `_is_link_veracity_enabled` and `_resolve_max_concurrent_agents` functions to manage environment variable settings for link verification and concurrent processing limits. Update orchestration logic to utilize these new configurations, enhancing performance and flexibility in the extraction process.

…ndle empty schema:author arrays. This function salvages repository entities by assigning a fallback owner from the reconciled graph when reconciliation results in an empty author array, addressing a known bug in the validation process. Update imports and module exports accordingly.

…n. This addition enables the Qdrant vector database for enhanced data storage and retrieval capabilities within the development environment. Update the service configuration with appropriate ports, volumes, and restart policies.

…nd enhance .env.example with additional configuration options. Update documentation to reflect new environment variables for improved clarity and usability in the development environment.

…e, RenkuLab, and EPFL Graph indices. Update AGENTS.md and justfile with new indexer commands and documentation for improved clarity and usability. Modify mkdocs.yml to reflect new documentation structure and sections.

…tes and specific `/v2/*` endpoints. Update documentation to reflect new API security requirements, including the introduction of `API_TOKEN` for protected routes. Enhance `justfile` commands to include authorization headers for cache management and extraction tests. Add new `discover` and `hydrate` protocols for federated indexing, along with corresponding CLI commands and documentation.

… GitHub Enterprise variable and add new context summary scout mode configuration. Enhance AGENTS.md and getting-started.md with updated Open Pulse Ontology version and additional details on the extraction process. Modify index.md and rag-indices.md to reflect changes in data storage layout and improve clarity on indexer configurations.

…r transient errors and add GitHub rate limit probing. Update .env.example to include configuration for maximum retry attempts. Modify API health checks to report GitHub rate limit status. Introduce validation for organization handles against GitHub API to ensure accurate entity representation.

….0.0

Feat/open pulse ontology v2.0.0

…cle prompt

Profile of one hybrid extraction on a 50-person paper-heavy repo
(deeplabcut/deeplabcut): person stage 5:06, **article stage 12:00 on a
single LLM agent invocation that fired 100+ tool calls**, membership
stage 6:37 — total ~25 min, dominated by serial waits and an
unbounded article-agent tool-call loop.

Three independent quick wins, each tunable per deployment:

1. `max_concurrent_agents` default 3→8 in the orchestrator (and the
   `V2_MAX_CONCURRENT_AGENTS` env-resolver default in the API layer
   raised 6→8). Person/membership stages are bottlenecked on the
   `asyncio.Semaphore`, not the LLM provider — bumping the cap absorbs
   wider-fanout repos without saturating RCP.

2. New `_default_usage_limits()` in `V2LLMRuntime`: caps every
   agent invocation at 25 model requests + 50 tool calls via
   pydantic-ai's `UsageLimits`. Without a cap the article agent could
   keep cross-validating the same DOI across five tools indefinitely.
   Overridable per-call (existing kw-only signature) or globally via
   `V2_LLM_REQUEST_LIMIT` / `V2_LLM_TOOL_CALLS_LIMIT`. The cap turns
   runaway loops into clean `LLMRuntimeError` that the per-stage
   runner already handles as a per-item warning.

3. Tightened the article agent system prompt with two "stop early"
   rules: emit immediately once a concrete DOI/title is found (no
   cross-validation past two sources), and emit `{}` after two
   consecutive empty searches instead of looping. The LLM was doing
   ~25 OpenAlex calls per agent invocation chasing the same paper.

Expected impact on the profiled repo: ~25 min → ~10 min wall time. No
schema, API, or routing changes — caps are tunable and conservative
defaults.