Skip to content

fix(server): support Prime Agent 0.8.0 - #71

Merged
rynfar merged 1 commit into
pylonfrom
fix/prime-agent-080-compat
Aug 24, 2026
Merged

fix(server): support Prime Agent 0.8.0#71
rynfar merged 1 commit into
pylonfrom
fix/prime-agent-080-compat

Conversation

@rynfar

@rynfar rynfar commented Aug 24, 2026

Copy link
Copy Markdown
Collaborator

Prime Agent 0.8.0 keeps daemon protocol 7 but advances the schema to 22 and changes recovery, RLM roster, ACP completion, and process-isolation behavior. Without adaptation, recovered Pylon-owned workers could lose runtime context, ACP turns could settle before descendants, and nested harness state could leak into newly launched Prime processes.

This change:

  • supplies fresh client-owned worker recovery configuration and keeps model/thinking selections current;
  • uses the authoritative 0.8 RLM roster with strict bounded decoding and an older-version fallback;
  • consumes correlated ACP terminal-quiescence metadata and fails closed on invalid correlation;
  • removes private Prime worker variables and RLM_DEPTH from both daemon and ACP roots without removing public configuration;
  • records explicit integrate/defer decisions for every schema 17–22 capability and documents the 0.8 MCP migrations.

Verification:

  • 258 focused Prime/ACP tests
  • server typecheck
  • targeted lint and format checks
  • opt-in real-daemon integration against published Prime Agent 0.8.0 (real turn, cancellation, restart/resume, and cleanup)
  • two separate direct review passes

Implemented and reviewed with OpenAI GPT-5.4 via Prime Agent.


View with [code]smith Autofix with [code]smith
Need help on this PR? Tag @codesmith with what you need. Autofix is disabled.

@github-actions github-actions Bot added size:XL vouch:trusted PR author is trusted by repo permissions or the VOUCHED list. labels Aug 24, 2026
@rynfar
rynfar merged commit ffc2538 into pylon Aug 24, 2026
14 checks passed
@rynfar
rynfar deleted the fix/prime-agent-080-compat branch August 24, 2026 15:24
@github-actions

Copy link
Copy Markdown

Thread transfer impact

✅ Thread transfer remains within every enforced ceiling.

Provider Metric Main baseline This PR Impact PR ceiling
Codex Total thread wire 13.4 KiB 13.4 KiB −7 B (−0.1%) 15.1 KiB
Codex Thread snapshot wire 6.9 KiB 6.9 KiB +6 B (+0.1%) 7.3 KiB
Codex Live turn WebSocket wire 6.5 KiB 6.5 KiB −13 B (−0.2%) 7.8 KiB
Codex Live turn WebSocket decoded 55.0 KiB 55.0 KiB 0 B (0.0%) 66.4 KiB
Codex Live turn messages 16 16 0 (0.0%) 21
Claude Total thread wire 13.5 KiB 13.4 KiB −8 B (−0.1%) 15.1 KiB
Claude Thread snapshot wire 6.9 KiB 6.9 KiB −1 B (−0.0%) 7.3 KiB
Claude Live turn WebSocket wire 6.6 KiB 6.6 KiB −7 B (−0.1%) 7.8 KiB
Claude Live turn WebSocket decoded 55.8 KiB 55.8 KiB 0 B (0.0%) 66.4 KiB
Claude Live turn messages 16 16 0 (0.0%) 21

Baseline: fe83b3c · PR result: 8feb38c · Source CI: success

Scenario and decoded snapshot size

10 historical turns, 5 command tools per turn, 878.9 KiB retained MCP result per historical turn, and a 1.05 MiB retained result in the measured turn.

  • Codex decoded thread snapshot: 109.4 KiB
  • Claude decoded thread snapshot: 110.0 KiB

Updated in place by a trusted workflow. PR artifacts are strictly validated and never executed.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size:XL vouch:trusted PR author is trusted by repo permissions or the VOUCHED list.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant