Test files were being included in coverage reports, causing misleading "patch coverage" warnings and inflated percentages. Lines in except blocks or if/else branches show as uncovered even when tests run.

Either we would end up putting very long config values into the default.py file, or we end up with a trashy default config. It's better to require to always sourcing a config.

* Ref: Switch to pydantic for internal representations Closes #491 * fixes * add pydantic to deps

* Ref: Move extra run scripts to extra/ * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix hardcoded paths * also fix doc links --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

updates: - [github.com/astral-sh/ruff-pre-commit: v0.14.8 → v0.14.9](https://github.com/astral-sh/ruff-pre-commit/compare/v0.14.8...v0.14.9) Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Bumps [actions/cache](https://github.com/actions/cache) from 4 to 5. - [Release notes](https://github.com/actions/cache/releases) - [Changelog](https://github.com/actions/cache/blob/main/RELEASES.md) - [Commits](https://github.com/actions/cache/compare/v4...v5) --- updated-dependencies: - dependency-name: actions/cache dependency-version: '5' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* chore: remove the timestamp field in OpenAI Response API requests * Update src/minisweagent/models/litellm_response_api_model.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Kilian Lieret <kilian.lieret@posteo.de> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

The timeout_template was rendering command output without truncation, causing 41MB+ messages when commands like `grep -R` hit recursive symlinks and produced massive warning output before timing out. This adds the same truncation logic used in action_observation_template: - Output < 10000 chars: shown in full - Output >= 10000 chars: first 5000 + last 5000 chars with warning

Add reraise=True to all @retry decorators so that when retries are exhausted, the original exception is re-raised instead of being wrapped in a RetryError. This ensures proper error tracking and analysis by preserving the original exception type. Fixes #635

This is important if we have more spinners than fit on the screen

This avoids errors about allowed keys from mistral, for example (because of the timestamp key)

updates: - [github.com/astral-sh/ruff-pre-commit: v0.14.7 → v0.14.8](https://github.com/astral-sh/ruff-pre-commit/compare/v0.14.7...v0.14.8) Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

This might sometimes avoid cryptic error messages about missing providers

updates: - [github.com/astral-sh/ruff-pre-commit: v0.14.6 → v0.14.7](https://github.com/astral-sh/ruff-pre-commit/compare/v0.14.6...v0.14.7) Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

* fix: resolve docs build warning and remove temperature defaults - Fix mkdocs strict mode warning by documenting specific symbols instead of full module in inspector.md - Remove default temperature from config files (mini.yaml, default.yaml, github_issue.yaml) - Delete unused mini_no_temp.yaml config file * Update inspector documentation Removed specific class references in inspector documentation. * docs: remove references to deleted mini_no_temp.yaml Update troubleshooting guide and config README to reflect that temperature is no longer set by default in config files. * Update troubleshooting documentation for model support

Add documentation pages for: - RequestyModel (new model provider) - Inspector (trajectory viewer CLI) - mini-extra (central CLI entry point) - config (global config manager)

* CI: Make test_whitelist_actions_bypass_confirmation more robust (#484) The test was flaky due to race conditions: 1. Thread started before UI was fully mounted 2. Used fixed 0.2s timeout instead of polling Changes: - Wait 0.2s for UI to be ready before starting thread - Poll for command to appear in screen with 5s timeout - Consistent with fix in #611 for test_log_message_filtering Fixes #484 * Update tests/agents/test_interactive_textual.py --------- Co-authored-by: Kilian Lieret <kilian.lieret@posteo.de>

updates: - [github.com/astral-sh/ruff-pre-commit: v0.14.5 → v0.14.6](https://github.com/astral-sh/ruff-pre-commit/compare/v0.14.5...v0.14.6) Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Closes #616 Closes #615