Skip to content

Evals #170

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
davidabram wants to merge 27 commits into
base: main
Choose a base branch
from
Draft

Evals #170

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
27 commits
Select commit Hold shift + click to select a range
7dc282b
next-task: Implement reviewed task execution workflow
davidabram Jul 27, 2026
32d84fb
change-to-plan: Implement context-driven plan authoring
davidabram Jul 27, 2026
578d09a
validate: Add final validation and plan context sync workflows
davidabram Jul 27, 2026
e7c745a
pkl: Rebuild generation around workflow packages
davidabram Jul 27, 2026
7cdaec5
build: Generate Pkl payloads in Cargo OUT_DIR
davidabram Jul 27, 2026
58899e0
config: Generate root OpenCode and Claude workflows
davidabram Jul 27, 2026
6cb1a4f
context: Canonicalize workflow execution rules
davidabram Jul 27, 2026
ceac341
build: Add pre-Cargo Pkl payload generation
davidabram Jul 27, 2026
2726542
context-sync: Simplify task synchronization reports
davidabram Jul 27, 2026
873b114
commit: Restore the atomic commit workflow
davidabram Jul 27, 2026
67d913a
setup: Add additive context baseline bootstrap
davidabram Jul 28, 2026
9b37965
claude: Implement Markdown workflow result packages
davidabram Jul 28, 2026
4133819
config: Render Claude workflows as single-skill packages
davidabram Jul 29, 2026
fa204e3
config: Promote the Claude composite renderer to a shared module
davidabram Jul 29, 2026
2fc64fd
config: Render Pi as thin prompts and workflow skill packages
davidabram Jul 29, 2026
d0d569a
config: Render OpenCode as thin commands and workflow skill packages
davidabram Jul 29, 2026
406efe5
context: Record cross-target single-skill workflow packages
davidabram Jul 29, 2026
bc09266
config: Regenerate Pi and OpenCode targets as single-skill workflow p…
davidabram Jul 29, 2026
2aab6c8
pkl: Centralize workflow metadata and generation contracts
davidabram Jul 29, 2026
800dcb4
pkl: Refactor workflow composition and generated-input production
davidabram Jul 29, 2026
aa347bf
workflows: Enforce canonical execution and output layouts
davidabram Jul 29, 2026
49e7b4f
workflows: Linearize composite workflow skills into single top-to-bot…
davidabram Jul 30, 2026
c4def4c
workflows: Add decision recording gate
davidabram Jul 30, 2026
3e0a351
workflows: Restore /handover as the fifth canonical cross-target work…
davidabram Jul 30, 2026
d9e9bb2
pkl: Fix stray blank-line joins and guard output-dedup regressions
davidabram Jul 30, 2026
7ee1eb6
skills: Add Effect v4 authoring skill to all three harness targets
davidabram Jul 30, 2026
5756496
plans: Add workflow-eval-harness plan for /change-to-plan conformance
davidabram Jul 30, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
60 changes: 0 additions & 60 deletions .claude/agents/shared-context-code.md
View file
Open in desktop

This file was deleted.

66 changes: 0 additions & 66 deletions .claude/agents/shared-context-plan.md
View file
Open in desktop

This file was deleted.

18 changes: 5 additions & 13 deletions .claude/commands/change-to-plan.md
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

43 changes: 5 additions & 38 deletions .claude/commands/commit.md
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

18 changes: 6 additions & 12 deletions .claude/commands/handover.md
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

25 changes: 5 additions & 20 deletions .claude/commands/next-task.md
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

16 changes: 5 additions & 11 deletions .claude/commands/validate.md
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

Loading
Loading