diff --git a/CHANGELOG.md b/CHANGELOG.md index 9c2a092f..38914207 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,6 +1,6 @@ # Changelog -## [1.6.5.0] - 2026-04-23 +## [1.10.1.0] - 2026-04-23 ## **We tried to make Opus 4.7 faster with a prompt. Measurement said it got slower. Pulled the bullet.** diff --git a/TODOS.md b/TODOS.md index f9585e7f..cfe61548 100644 --- a/TODOS.md +++ b/TODOS.md @@ -1252,14 +1252,14 @@ Shipped in v0.6.5. TemplateContext in gen-skill-docs.ts bakes skill name into pr ## Completed -### Overlay efficacy harness + Opus 4.7 fanout nudge removal (v1.6.5.0) +### Overlay efficacy harness + Opus 4.7 fanout nudge removal (v1.10.1.0) - Built `test/skill-e2e-overlay-harness.test.ts`, a parametric periodic-tier eval that drives `@anthropic-ai/claude-agent-sdk` and measures first-turn fanout rate (overlay-ON vs overlay-OFF) across registered fixtures - Measured the original "Fan out explicitly" overlay nudge: baseline Opus 4.7 = 70% first-turn fanout on toy prompt, with our nudge = 10%, with Anthropic's own canonical `` text = 0% - Removed the counterproductive nudge from `model-overlays/opus-4-7.md` - Shipped 36-test free-tier unit suite for the SDK runner + strict fixture validator - Registered `overlay-harness-opus-4-7-fanout-{toy,realistic}` in E2E_TOUCHFILES and E2E_TIERS - Total investigation cost: ~$7 across 3 eval runs -**Completed:** v1.6.5.0 +**Completed:** v1.10.1.0 ### CI eval pipeline (v0.9.9.0) - GitHub Actions eval upload on Ubicloud runners ($0.006/run) diff --git a/VERSION b/VERSION index 51b0f476..3647b707 100644 --- a/VERSION +++ b/VERSION @@ -1 +1 @@ -1.6.5.0 +1.10.1.0 diff --git a/package.json b/package.json index faead288..9ccd0901 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "gstack", - "version": "1.6.5.0", + "version": "1.10.1.0", "description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.", "license": "MIT", "type": "module",