@chrono-meta/fh-gate 1.4.5 → 1.4.7

package/CATALOG.md

@@ -8,6 +8,17 @@ AI reads this file first when searching past work. Open individual files for det
 
 <!-- Add entries in reverse date order (newest at top) -->
 
+### 2026-06-09 | forge-harness | #sidecar, #zero-config, #engine-resolution, #roadmap, #mode-c
+**File:** knowledge/shared/harness-core/multi_model_sidecar_strategy.md (+ hybrid_orchestration_architecture_roadmap.md)
+Added canonical §Sidecar Engine Resolution Protocol — Tier1 subscription-CLI → Tier2 API-key → Tier3 Claude-subagent guaranteed fallback. Principle: discovery automatic/free, invocation value-gated (intelligent default multi-AI, no hard-fail for Mode C). Wired pointers into goal-quench Step D / steel-quench runtime-adapter / harvest-loop Step 3.5-X; sim-conductor/pipeline-conductor/agent-composer inherit by reference. Source hybrid-orchestration design archived as proposed roadmap (versions→placeholders, Python pseudo-code→illustrative, non-shipped tagged Proposed). PR #80.
+- Decision: single-source resolution protocol — skills cite it instead of re-inventing "if available" probes.
+- Open: npm republish (machine-bound) — 3 npm-shipped SKILL.md changed; handed off to laptop via fh-be.
+
+### 2026-06-09 | forge-harness | #onboarding, #greeting, #3-axis-scaffold, #returning-user
+**File:** knowledge/shared/harness-core/fh_detail_protocols.md
+Returning-user greeting (Step 2): single free-form e.g. line → fixed 3-axis entry scaffold (① connect new → auto_project_mapping · ② resume existing → filled live from CATALOG · ③ jump to work), plus a "keep axes fixed, compose contents per situation" note. PR #80.
+- Decision: axis ② read live from CATALOG each session so the menu can't go stale — qasp-style clarity without rigidity.
+
 ### 2026-06-05 | _audit | sister-asset, gstack, field-harness, garry-tan
 **File:** tracks/_audit/session_2026_06_05_gstack-sister.md (private companion mirror)
 gstack (garrytan, ~66K stars) sister-asset cross-audit — the field/execution-harness counterpart to FH's meta/governance harness, both running on the Claude Code skill substrate. FH governs / gstack executes (composes, not competes). Bidirectional import (frictionless one-command install, opinionated front door, privacy-first telemetry) / propagate (post-ship governance gate, cross-project knowledge compounding, HITL promotion gate) lists recorded.

package/CLAUDE.md

@@ -335,8 +335,13 @@ Closing phrase detected ("wrap up", "done", "good work", "end session", etc.)
   → ④-b npm freshness — if any npm-shipped asset changed this session (the `package.json` `files[]`
        surface: skills · agents · README · AGENTS.md · CLAUDE.md · CHEATSHEET), **propose an npm
        republish**: version bump + Pre-Publish Surface Gate (`/public-surface-audit` + `/marketplace-gate`
-       Check 5) + `npm publish`. The npm-served README and shipped skills/agents freeze at publish time,
-       so updating FH assets without republishing leaves the package stale. **Propose, don't auto-publish.**
+       Check 5) + `npm publish` + **`git tag vX.Y.Z` on the bump commit + `git push origin vX.Y.Z`**
+       (tag at publish time, in lockstep with the version — keeps git tags aligned with npmjs.com so
+       Releases/Tags never drift). The npm-served README and shipped skills/agents freeze at publish
+       time, so updating FH assets without republishing leaves the package stale. **Propose, don't
+       auto-publish.** Tag drift caveat: when a bump rides inside a functional commit (no explicit
+       "bump" commit), tag *that* commit — otherwise the version ships to npm untagged (e.g. 1.4.4/1.4.5
+       shipped untagged, backfilled 2026-06-08).
   → ⑤ Card update ← ABSOLUTE LAST: must capture ①–④-b outcomes
   → ⑥ Commit card + push
 ```

package/README.md

@@ -75,6 +75,12 @@ claude plugin install -s user fh-meta@forge-harness
 cd ~/projects/{your-project} && claude
 ```
 
+> ⚠️ **Plugin-only is partial synergy.** You get the skills and agents, but **not** Layer 1 — the
+> `CLAUDE.md` governance (active onboarding, the 4-axis gate, mode branching) and the compounding
+> context (`tracks/` memory accumulation, `harvest-loop` learning). Each skill runs the same in
+> isolation; what's missing is the orchestration that makes them compound across sessions. Clone the
+> hub (above) when you want the full set, not just the tools.
+
 > 🚪 **New here / just want the skills?** Start with the opinionated front door —
 > [`templates/starter_profile.md`](templates/starter_profile.md): one install command, a curated
 > first-five skills, and a zero-install governance gate (`npx … fh-gate`). The other 28 skills wait

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@chrono-meta/fh-gate",
-  "version": "1.4.5",
+  "version": "1.4.7",
   "description": "FH runtime adapters — run FH governance, skills, and agents via Claude or Codex with machine-parseable gates.",
   "license": "MIT",
   "keywords": [

package/plugins/fh-meta/skills/goal-quench/SKILL.md

@@ -274,6 +274,8 @@ max mode never installs anything silently — discovery and synergy-check are su
 
 Runs after Step C (or after Step B if no capability gap). Selects an adversarial sidecar based on the task's quality-risk profile — distinct from Step C's capability-gap sidecar, which addresses missing tools. Step D's sidecar addresses **blind-spot risk**: the generator and reviewer sharing the same reasoning distribution.
 
+> **Availability resolution**: "Gemini sidecar if available" / "if external CLIs available" below is decided by the canonical Tier 1→2→3 recipe in `knowledge/shared/harness-core/multi_model_sidecar_strategy.md §Sidecar Engine Resolution Protocol` — discovery is automatic, invocation stays value-gated. Tier 3 (Claude sub-agent) guarantees this step never hard-fails even with zero external CLIs/keys.
+
 **Scope → sidecar routing table**:
 
 | Task scope signal | Sidecar | Invocation point |

package/plugins/fh-meta/skills/harvest-loop/SKILL.md

@@ -115,7 +115,7 @@ Output final proposal list → Y: PR creation / N: persist to tracks/_meta/fh_si
 
 **Fallback** (deep-insight not installed): Inline synthesis. Apply same judgment matrix. If quality low → Step 3.75 Critic processes as CONDITIONAL PASS.
 
-**Step 3.5-X** (optional): Cross-session 2nd validation when 2+ HIGH-grade items exist. External CLI (gemini/codex) or cross-session Claude. Items flagged as over-promoted → downgrade HIGH → MED.
+**Step 3.5-X** (optional): Cross-session 2nd validation when 2+ HIGH-grade items exist. External CLI (gemini/codex) or cross-session Claude. Items flagged as over-promoted → downgrade HIGH → MED. External CLI availability is resolved via `knowledge/shared/harness-core/multi_model_sidecar_strategy.md §Sidecar Engine Resolution Protocol` (Tier 1→2→3; Tier 3 = cross-session Claude — no hard-fail when no external CLI exists).
 
 > **Detail**: See `SKILL_detail.md §Step3-5X` — bash execution scripts for external CLI and cross-session Claude fallback — read when running Step 3.5-X validation.
 

package/plugins/fh-meta/skills/steel-quench/SKILL.md

@@ -80,6 +80,8 @@ For the target artifact, scan installed agents for a domain-specific adversarial
 2. Built-in fallback: `fh-commons:quench-challenger` (general-purpose adversarial review)
 3. GAP for high-risk artifact: query `/plugin-recommender "adversarial reviewer for [artifact_type]"` → user: install / skip / use fallback
 
+> **Sidecar availability** for a cross-provider challenger (Gemini/Codex, Wave 5) is resolved via the Tier 1→2→3 recipe in `knowledge/shared/harness-core/multi_model_sidecar_strategy.md §Sidecar Engine Resolution Protocol`; Tier 3 = the `fh-commons:quench-challenger` Claude sub-agent below (guaranteed fallback — same-provider, so model-access not cross-provider diversity).
+
 **Runtime adapter note**: In Claude Code, invoke the fallback as an isolated `Agent(subagent_type="fh-commons:quench-challenger")`. In Codex-primary or other non-Claude runtimes, use the FH adapter instead:
 
 ```bash