87 Commits

Include renames

• chore: tune challenge matrix and debug prompts
  lda 2026-06-29 19:25:35 +07:00
  Verified e0315f295c
• fix: smooth draft schema projection ux
  lda 2026-06-29 18:55:22 +07:00
  Verified 5f520d74bd
• fix: address workflow authoring review findings
  lda 2026-06-29 11:04:22 +07:00
  Verified 746e4f7a2a
• feat: add debug profile for agent challenge UX mining
  lda 2026-06-29 00:13:52 +07:00
  Verified f4a1c5f850
• fix: harden agent challenge run capture
  lda 2026-06-28 21:18:24 +07:00
  Verified 8b751da402
• feat: filter recent challenge summaries
  lda 2026-06-28 19:07:58 +07:00
  Verified f35fda1a22
• docs: prepare agent challenge reruns
  lda 2026-06-28 01:39:54 +07:00
  Verified 67ada5cbc4
• fix: address semantic draft review nits
  lda 2026-06-27 17:59:49 +07:00
  Verified c2bb5728b6
• fix: classify trial store reads as store access
  lda 2026-06-25 17:01:06 +07:00
  Verified 2d2477fb12
• feat: summarize agent challenge matrix runs
  lda 2026-06-25 04:03:40 +07:00
  Verified 8e93e3dd66
• fix: address challenge harness review findings
  lda 2026-06-25 02:16:05 +07:00
  Verified 6a14d0fd03
• test: add concurrent agent challenge matrix
  lda 2026-06-24 18:33:48 +07:00
  Verified f87c4701f7
• test: harden agent challenge evidence reports
  lda 2026-06-24 17:52:29 +07:00
  Verified 9c68bcd75f
• test: stage report challenge input fixtures
  lda 2026-06-24 13:30:07 +07:00
  Verified e4d163a0cf
• docs: make workflow skills cli-first
  lda 2026-06-24 00:30:04 +07:00
  Verified 69c39da10d
• fix: refine agent challenge policy categories
  lda 2026-06-23 20:50:47 +07:00
  Verified 05dff5bc25
• fix: pass report workflow notes by value
  lda 2026-06-23 20:44:02 +07:00
  Verified 371677fa3f
• docs: add agent challenge evaluation runbook
  lda 2026-06-23 17:41:14 +07:00
  Verified 7741248704
• fix: separate policy validity from coverage
  lda 2026-06-23 17:35:07 +07:00
  Verified 07d6595500
• feat: generate auditable agent trial reports
  lda 2026-06-23 02:14:03 +07:00
  Verified 3bb9eacb25
• fix: normalize real opencode trial evidence
  lda 2026-06-23 01:12:08 +07:00
  Verified 7ef58e8860
• feat: migrate agent challenges to manifests
  lda 2026-06-23 01:00:31 +07:00
  Verified bc851ea99c
• feat: add profiled agent challenge harness
  lda 2026-06-23 00:19:31 +07:00
  Verified 893872f821
• docs: record agent challenge skill bundle
  lda 2026-06-22 22:55:39 +07:00
  Verified 3c3cd0e241
• slop on my agent skills removed + notes
  lda 2026-06-22 21:48:12 +07:00
  Verified 86aba7332c
• fix: retain agent challenge parse errors
  lda 2026-06-16 21:42:49 +07:00
  Verified b62d7e5889
• refactor: share agent challenge harness
  lda 2026-06-16 19:53:19 +07:00
  Verified be2239e716
• docs: expand report workflow case study
  lda 2026-06-16 15:38:28 +07:00
  Verified 21880601fc
• docs: tighten browser challenge reporting rules
  lda 2026-06-15 23:44:47 +07:00
  Verified 32da68e05f
• fix: address browser challenge review nits
  lda 2026-06-15 22:47:08 +07:00
  Verified 6836c9c972
• fmt, fix
  lda 2026-06-15 22:37:59 +07:00
  Verified e8152fd4e6
• fix: apply coderabbit reviews
  lda 2026-06-15 22:29:27 +07:00
  Verified fe0b2b4f4d
• feat: smooth browser challenge harness runs
  lda 2026-06-15 21:54:47 +07:00
  Verified fe473b9f8a
• feat: auto-save browser challenge reports
  lda 2026-06-15 21:15:31 +07:00
  Verified 008103ac15
• refactor: extract browser challenge harness modules
  lda 2026-06-15 19:38:46 +07:00
  Verified 66eaa4a67d
• refactor: split browser challenge harness helpers
  lda 2026-06-15 19:38:12 +07:00
  Verified 8d67e87a71
• feat: add focused draft cli edits
  lda 2026-06-15 18:27:27 +07:00
  Verified 97076479f1
• fix: allocate browser challenge trial numbers globally
  lda 2026-06-15 06:41:42 +07:00
  Verified 577fb4707a
• fix: allocate unique browser challenge workspaces
  lda 2026-06-15 06:36:06 +07:00
  Verified 48e155d048
• fix: generate browser challenge workspace config
  lda 2026-06-15 06:29:25 +07:00
  Verified 3b19884919
• fix: correct browser challenge workspace source path
  lda 2026-06-15 06:23:46 +07:00
  Verified 73dc1d958a
• feat: stage per-trial browser challenge workspaces
  lda 2026-06-15 06:15:30 +07:00
  Verified 6e2c3b8879
• fix: remove generated browser challenge answer file
  lda 2026-06-15 06:03:06 +07:00
  Verified 10f6d7d1bc
• docs: add draft patch and plan artifact workflow guidance
  lda 2026-06-15 05:34:05 +07:00
  Verified 49011464fc
• feat: make browser challenge harness local first
  lda 2026-06-15 05:05:24 +07:00
  Verified bee5ead63e
• fix: guard stop_server against TOCTOU race on unix
  lda 2026-06-15 03:55:50 +07:00
  Verified 29864b85fd
• feat: stage rpc server for opencode challenge
  lda 2026-06-15 03:51:39 +07:00
  Verified 552fd24d69
• feat: parse structured challenge reports
  lda 2026-06-15 03:12:52 +07:00
  Verified 57d4fa57a8
• fix: classify opencode text events and helper scripts
  lda 2026-06-15 03:07:04 +07:00
  Verified ef9bb41687
• docs: clarify opencode attach semantics
  lda 2026-06-15 02:48:46 +07:00
  Verified cf1e61a393