@agentskit/harness 0.11.0 → 0.12.0

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.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@agentskit/harness",
3
- "version": "0.11.0",
3
+ "version": "0.12.0",
4
4
  "description": "Portable, evidence-backed development harness for coding agents.",
5
5
  "type": "module",
6
6
  "bin": {
@@ -2,9 +2,9 @@
2
2
  "type": "agentskit-harness-release-manifest",
3
3
  "schemaVersion": 1,
4
4
  "package": "@agentskit/harness",
5
- "version": "0.11.0",
5
+ "version": "0.12.0",
6
6
  "channel": "latest",
7
- "sourceRevision": "b8cfe596e5f30f2c373b89f00f271079b296feaf",
7
+ "sourceRevision": "922d2444ef48bfc89e58ccbe0553efc06a09c877",
8
8
  "requiredChecks": [
9
9
  "typecheck",
10
10
  "test",
@@ -32,5 +32,5 @@
32
32
  "pilot-benchmark"
33
33
  ],
34
34
  "nextBaseline": "benchmarks/harness-0.4.0-baseline.json",
35
- "digest": "9fd3e219da299dab39477062cb3c17296e18cc6b707bceb42436cdb75afd281b"
35
+ "digest": "439805502a4fdd074491269cf733b4144f968ac2ef4b32a6271a4c21102ecc7a"
36
36
  }
package/release/notes.md CHANGED
@@ -1,3 +1,16 @@
1
+ # 0.12.0 release candidate
2
+
3
+ Reuses Orca instead of reinventing it, where Orca's own tooling gives a better answer than the harness's own
4
+ heuristics: `loop deliver` escalations now fold in the dispatched worker's own terminal output (best-effort,
5
+ `terminal read --screen`) so a human sees the worker's own diagnosis instead of a generic idle/no-PR message; slot
6
+ assessment prefers Orca's `diagnostics memory` (macOS's real memory-pressure reading) and real per-session RSS over
7
+ the harness's own `vm_stat` approximation and static per-agent guess, which were measured roughly 2x more
8
+ conservative at the same instant. Also ships an installable `ak-harness-loop` Orca Skill documenting the loop's
9
+ commands and the operational constraints this release's investigation confirmed (Orca's orchestration mutations —
10
+ `run-create`/`task-create`/`worker-start`/`send` — require a live coordinator terminal pane and cannot be called
11
+ from the loop's headless `tick`/`deliver`, verified from every angle tried). Publication remains gated on a merge
12
+ to `main` through npm Trusted Publishing.
13
+
1
14
  # 0.11.0 release candidate
2
15
 
3
16
  Read-only loop observability for the keep-pushing SDLC loop: deterministic anomaly detection and operating metrics