mixdog 0.9.41 → 0.9.44

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (73) hide show
  1. package/package.json +3 -2
  2. package/scripts/agent-tag-reuse-smoke.mjs +124 -10
  3. package/scripts/ansi-color-capability-test.mjs +90 -0
  4. package/scripts/anthropic-oauth-refresh-race-test.mjs +59 -0
  5. package/scripts/arg-guard-test.mjs +16 -0
  6. package/scripts/compact-pressure-test.mjs +256 -1
  7. package/scripts/generate-runtime-manifest.mjs +39 -22
  8. package/scripts/grok-oauth-refresh-race-test.mjs +198 -0
  9. package/scripts/internal-comms-bench.mjs +0 -1
  10. package/scripts/internal-comms-smoke.mjs +38 -39
  11. package/scripts/internal-tools-normalization-test.mjs +52 -0
  12. package/scripts/maintenance-default-routes-test.mjs +164 -0
  13. package/scripts/max-output-recovery-test.mjs +49 -0
  14. package/scripts/mcp-client-normalization-test.mjs +45 -0
  15. package/scripts/openai-oauth-ws-1006-retry-test.mjs +123 -0
  16. package/scripts/provider-toolcall-test.mjs +23 -0
  17. package/scripts/result-classification-test.mjs +75 -0
  18. package/scripts/routing-corpus.mjs +1 -1
  19. package/scripts/shell-jobs-windows-hide-test.mjs +164 -0
  20. package/scripts/smoke.mjs +1 -1
  21. package/scripts/submit-commandbusy-race-test.mjs +99 -7
  22. package/scripts/tui-transcript-jitter-harness-entry.jsx +302 -0
  23. package/scripts/tui-transcript-jitter-harness.mjs +58 -0
  24. package/scripts/tui-transcript-perf-test.mjs +56 -1
  25. package/src/agents/reviewer/AGENT.md +5 -3
  26. package/src/rules/lead/lead-brief.md +5 -4
  27. package/src/runtime/agent/orchestrator/agent-runtime/agent-dispatch.mjs +40 -3
  28. package/src/runtime/agent/orchestrator/config.mjs +29 -14
  29. package/src/runtime/agent/orchestrator/internal-tools.mjs +16 -3
  30. package/src/runtime/agent/orchestrator/mcp/client.mjs +17 -1
  31. package/src/runtime/agent/orchestrator/providers/anthropic-oauth-credentials.mjs +49 -6
  32. package/src/runtime/agent/orchestrator/providers/anthropic-sse.mjs +14 -0
  33. package/src/runtime/agent/orchestrator/providers/grok-oauth.mjs +46 -21
  34. package/src/runtime/agent/orchestrator/providers/media-normalization.mjs +59 -2
  35. package/src/runtime/agent/orchestrator/providers/retry-classifier.mjs +5 -1
  36. package/src/runtime/agent/orchestrator/session/agent-loop.mjs +18 -0
  37. package/src/runtime/agent/orchestrator/session/context-utils.mjs +140 -81
  38. package/src/runtime/agent/orchestrator/session/loop/compact-policy.mjs +23 -5
  39. package/src/runtime/agent/orchestrator/session/loop/termination.mjs +3 -0
  40. package/src/runtime/agent/orchestrator/session/loop/tool-exec.mjs +12 -3
  41. package/src/runtime/agent/orchestrator/session/manager/ask-session.mjs +4 -2
  42. package/src/runtime/agent/orchestrator/session/result-classification.mjs +4 -1
  43. package/src/runtime/agent/orchestrator/session/tool-batch.mjs +7 -2
  44. package/src/runtime/agent/orchestrator/session/tool-envelope.mjs +8 -6
  45. package/src/runtime/agent/orchestrator/tools/builtin/arg-guard.mjs +15 -3
  46. package/src/runtime/agent/orchestrator/tools/builtin/shell-analysis.mjs +1 -1
  47. package/src/runtime/agent/orchestrator/tools/builtin/shell-jobs.mjs +7 -5
  48. package/src/runtime/memory/data/runtime-manifest.json +11 -11
  49. package/src/runtime/memory/lib/runtime-fetcher.mjs +1 -2
  50. package/src/runtime/memory/tool-defs.mjs +4 -3
  51. package/src/runtime/shared/tool-surface.mjs +1 -2
  52. package/src/session-runtime/context-status.mjs +8 -2
  53. package/src/standalone/agent-tool/render.mjs +2 -0
  54. package/src/standalone/agent-tool.mjs +267 -72
  55. package/src/standalone/explore-tool.mjs +17 -16
  56. package/src/tui/app/provider-setup-picker.mjs +1 -0
  57. package/src/tui/app/use-transcript-window.mjs +5 -1
  58. package/src/tui/components/StatusLine.jsx +11 -32
  59. package/src/tui/dist/index.mjs +257 -106
  60. package/src/tui/engine/session-api.mjs +3 -0
  61. package/src/tui/engine/session-flow.mjs +19 -8
  62. package/src/tui/engine/turn.mjs +24 -2
  63. package/src/tui/engine.mjs +0 -1
  64. package/src/tui/index.jsx +3 -2
  65. package/src/tui/markdown/streaming-markdown.mjs +35 -9
  66. package/src/tui/statusline-ansi-bridge.mjs +17 -7
  67. package/src/ui/ansi.mjs +85 -5
  68. package/src/ui/statusline-agents.mjs +0 -8
  69. package/src/ui/statusline-format.mjs +7 -7
  70. package/src/ui/statusline.mjs +2 -4
  71. package/src/workflows/default/WORKFLOW.md +29 -20
  72. package/src/workflows/solo-review/WORKFLOW.md +47 -0
  73. package/src/workflows/bench/WORKFLOW.md +0 -60
@@ -1,60 +0,0 @@
1
- ---
2
- id: bench
3
- name: Bench
4
- description: "Autonomous headless benchmark workflow with directed execution and parallel cross-verification."
5
- hidden: true
6
- agents: worker, heavy-worker, reviewer, debugger, maintainer
7
- ---
8
-
9
- # Bench
10
-
11
- Autonomous headless run: no user exists. Never ask questions, propose plans
12
- for approval, or end the turn waiting — decide and proceed. Standing
13
- pre-approval covers every action: edits, state mutation, delegation, builds.
14
- Loop until the task is verified complete or provably blocked.
15
-
16
- The pipeline has exactly three stages. Lead directs and verifies it, but NEVER
17
- executes the work itself: no edits, answers, or artifact generation, regardless
18
- of task size, perceived simplicity, or number of steps.
19
-
20
- ## 1. Lead analysis and direction
21
- Lead performs real analysis first on EVERY task: task structure, required
22
- deliverables, boundaries, the task's own verification means, and solution
23
- direction. Convert it into clear execution direction and delegation briefs
24
- following the Lead brief contract.
25
-
26
- Hand the direction and briefs to executors. Analysis is not permission for
27
- Lead to implement any portion of the result: all edits, answer production, and
28
- artifact generation belong to executor sessions.
29
-
30
- ## 2. Executors perform the work
31
- Use Worker sessions, or Heavy Worker sessions for broad scopes, to execute the
32
- directed work. Multiple workers MAY fan out in parallel, one per independent
33
- scope. Keep ownership clear for each assigned deliverable.
34
-
35
- Executors build the answer or artifact and perform basic does-it-run checks.
36
- They are not a verification role and do not own acceptance, requirements
37
- judgment, or final correctness. Each executor reports its result to Lead.
38
-
39
- ## 3. Lead and Reviewer verify
40
-
41
- When executors report, Lead and Reviewer start cross-verification IN PARALLEL,
42
- never serially. Lead personally runs the task's own verification means, such
43
- as its test suite, grader script, simulator, or self-checkable output.
44
- Reviewer independently judges the result against every task requirement,
45
- including intent, correctness, boundaries, and deliverables.
46
-
47
- Judgment-type answers with no direct ground truth still require parallel
48
- cross-verification, even for a single small deliverable. Lead evaluates against
49
- available criteria while Reviewer independently judges requirements;
50
- perceived simplicity is no exemption.
51
-
52
- Merge any finding into a clear fix delta and return it to the SAME executor
53
- session owning the affected scope. The executor applies it and reports again.
54
- Lead and Reviewer repeat the same parallel cross-verification until both legs
55
- are clean; Lead never fixes or completes the work directly.
56
-
57
- Before declaring completion, Lead personally runs the task-required
58
- verification one final time and checks that every deliverable is present.
59
- Never end with a question, approval request, or proposed next step. Continue
60
- until verified complete or stop only when completion is provably blocked.