Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Bumps [h3](https://github.com/h3js/h3) from 1.15.5 to 1.15.8.
- [Release notes](https://github.com/h3js/h3/releases)
- [Changelog](https://github.com/h3js/h3/blob/main/CHANGELOG.md)
- [Commits](h3js/h3@v1.15.5...v1.15.8)

---
updated-dependencies:
- dependency-name: h3
  dependency-version: 1.15.8
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

Bumps [github.com/buger/jsonparser](https://github.com/buger/jsonparser) from 1.1.1 to 1.1.2.
- [Release notes](https://github.com/buger/jsonparser/releases)
- [Commits](buger/jsonparser@v1.1.1...v1.1.2)

---
updated-dependencies:
- dependency-name: github.com/buger/jsonparser
  dependency-version: 1.1.2
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

Bumps [h3](https://github.com/h3js/h3) from 1.15.8 to 1.15.9.
- [Release notes](https://github.com/h3js/h3/releases)
- [Changelog](https://github.com/h3js/h3/blob/v1.15.9/CHANGELOG.md)
- [Commits](h3js/h3@v1.15.8...v1.15.9)

---
updated-dependencies:
- dependency-name: h3
  dependency-version: 1.15.9
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* Validate yaml file inputs; added tests for inuts

* Updated changelog

* Apply suggestions from code review

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* Apply suggestions from code review

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* Apply suggestions from code review

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* Somehow bytes referernce was deleted

* Apply suggestions from code review

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* Apply suggestions from code review

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* Don't destroy GOOS and GOARCH in script

* Removed unsupported yaml and guide elements.

* Apply suggestions from code review

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* Put GOOS and GOARCH reset in finally block.

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* Add path to error reported in yaml validation error.

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* PR Feedback; tightened schema.

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* Removed else clause because it's apparently not idiomatic to go; Updated graders documentation.

* PR feedback; updated documentation; cspell clean

* Validate config of polymorphic graders; fixed a couple of copilot errors and test issues

* Standardize workers parameter as workers not max_workers.

* Tightened up examples; removed inline task examples because they're not supported

* cspell; fixed lint issue

* Copilot suggested fixes

* Document breaking change in workers config node; removed dead code

* Restored yaml formatting

* Restored yaml formatting 2

* Restored yaml formatting 2

* Restored yaml formatting 4

* Validate skill and task parsing strictly

* Validate eval-yaml.mdx files

* Further tightend up yaml parsing

* Further tightend up yaml parsing

* More PR feedback

* More PR feedback; consolidated a bunch of tests in trigger/spec_test.go

---------

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

…#191)

* upgrade squad

* fix: inject SKILL.md content, load trigger fixtures, pass MCP servers (#190, #186, #180)

- Re-add buildSkillSystemMessage() to inject SKILL.md content via
  SystemMessage (mode: append) on CreateSession/ResumeSession. Injects
  full body for the target skill and compact summaries for all skills.
  PR #140 removed this, relying solely on SkillDirectories, which only
  handles skill tool routing — not content injection.

- Load fixture files for trigger tests. trigger/runner.go now walks
  cfg.FixtureDir() once at init, caches ResourceFiles, and passes them
  on every trigger ExecutionRequest. Skips hidden dirs, vendor,
  node_modules, and files >1MB.

- Pass mcp_servers eval config to copilot session. Adds MCPServers field
  to ExecutionRequest, convertMCPServers() helper in both orchestration
  and trigger runners, and passthrough in copilot.go.

Closes #190
Closes #186
Closes #180

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

…#167)

- Add 10 missing waza run flags to README (--output-dir, --tags, --model,
  --recommend, --judge-model, --session-log, --session-dir, --no-summary,
  --update-snapshots, --skip-graders)
- Add waza session list/view commands to README
- Add waza grade and waza session sections to site CLI reference
- Add missing waza run flags to site CLI reference
- Create .waza.yaml project configuration reference page
- Fix grader descriptions for tool_constraint and trigger
- Fix trigger_tests → trigger reference in cli.mdx
- Fix HTML comments → MDX comments in eval-yaml.mdx, graders.mdx, schema.mdx

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* feat: add eval coverage grid generator #82

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix: address review feedback on PR #92

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix: address PR #92 coverage command review comments

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix: coverage pct counts only fully covered skills, document threshold

- CoveragePct now counts only 'Full' (≥2 grader types) skills, not Partial
- Add comment clarifying that Full requires tasks + multiple grader types
- Update summary line to say 'fully covered'

Addresses wbreza review feedback on PR #92.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* docs: Document waza coverage levels and percentage calculation

* fix: gofmt formatting in cmd_coverage.go

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix: address Copilot review feedback on PR #92

- Validate root path is a directory, not just exists
- Update help text to mention both eval.yaml and eval.yml
- Update CLI docs to reference eval.yaml/eval.yml consistently
- Add test for file-path rejection

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix: handle tasks_from in eval coverage classification

Eval specs using tasks_from instead of inline tasks were misclassified
as Partial coverage. Now tasks_from is parsed and treated as having
tasks for coverage purposes. Updated docs to clarify both forms qualify.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix: address review feedback for coverage command

- Parse failures now warn to stderr instead of aborting the report,
  making waza coverage usable in repos with broken eval files.
- Use tabwriter placeholders for emoji to fix column alignment.
- Updated test to match new warn-not-error behavior.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>