[HamzaKhanBUIC]

Summary

Fixes #69.

Wires Settings.TOOL_OUTPUT_MAX_CHARS into get_agent() and exposes all documented configuration environment variables in docker-compose.yml.

Problem

1. �gentkit/api/deps.py:get_agent() omitted ool_output_max_chars when instantiating AgentConfig, causing the application to always use the hard-coded default (2000 chars) regardless of TOOL_OUTPUT_MAX_CHARS in the environment.
2. docker-compose.yml omitted SEARCH_API_KEY, RATE_LIMIT_PER_MIN, MAX_STEPS, TOOL_TIMEOUT_S, SESSION_TTL_S, TOOL_OUTPUT_MAX_CHARS, LLM_MAX_RETRIES, LLM_RETRY_BASE_DELAY_S, and LLM_RETRY_MAX_DELAY_S, running containerized deployments with hidden defaults and preventing web_search from functioning without manual compose edits.

Solution

• In �gentkit/api/deps.py: Passed ool_output_max_chars=settings.TOOL_OUTPUT_MAX_CHARS to AgentConfig(...).
• In docker-compose.yml: Exposed all documented environment variables with ${VAR:-...} fallback defaults.
• In docs/SPEC.md and docs/AGENTKIT_SPEC.md: Aligned documented variable list with the full Settings schema.
• In ests/unit/test_config.py:
  • Added unit test asserting get_agent() wires TOOL_OUTPUT_MAX_CHARS to �gent.config.tool_output_max_chars.
  • Added async integration test asserting tool outputs exceeding configured limits are truncated during agent execution.
  • Added test validating 100% parity between Settings.model_fields and docker-compose.yml �pi.environment.
  • Added test ensuring all settings remain documented in docs/SPEC.md and docs/AGENTKIT_SPEC.md.

Verification

• uv run pytest tests/unit/test_config.py -> 8/8 passed
• uv run ruff check . -> All checks passed
• uv run ruff format --check . -> 110 files already formatted
• uv run mypy agentkit tests/unit/test_config.py -> Success: no issues found in 43 source files
• Structural AST lint & Semgrep security check -> Clean

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.