chore(release): framework 4.34.0 — operator-provided calibrator identity

CHANGELOG.md

@@ -7,6 +7,22 @@ and this project uses [independent versioning](README.md#versioning) for Framewo
 
 ---
 
+## Framework 4.34.0 — 2026-07-08
+
+### Fixed (Framework)
+
+- **`straymark-audit-review`: the calibrator identity is now operator-provided, never
+  self-detected.** Same class of bug fixed for `straymark-audit-execute` in 4.33.0, but for
+  the consolidation step: when the review runs inside a router CLI (Qwen Code, Gemini CLI,
+  …), the `calibrator:` / `**Reviewer:**` fields would carry the CLI product name instead of
+  the operator-selected backend model. Step 1 now accepts an optional second argument
+  `/straymark-audit-review <CHARTER-ID> <CALIBRATOR-SLUG>`, a calibrator-identity note makes
+  the operator-provided identity authoritative and forbids the CLI product name, and a guard
+  verifies the written `calibrator:` and `**Reviewer:**` fields match the slug. Applied to
+  all four shipped copies (`.agent` workflow + `.claude`/`.gemini`/`.codex` skills).
+
+---
+
 ## Framework 4.33.0 — 2026-07-08
 
 ### Fixed (Framework)

README.md

@@ -277,7 +277,7 @@ StrayMark uses independent version tags for each component:
 
 | Component | Tag prefix | Example | Includes |
 | --- | --- | --- | --- |
-| Framework | `fw-` | `fw-4.33.0` | Templates (12 types), governance, directives, Charter template + schema |
+| Framework | `fw-` | `fw-4.34.0` | Templates (12 types), governance, directives, Charter template + schema |
 | CLI | `cli-` | `cli-3.30.0` | The `straymark` binary |
 | Loom (EXPERIMENTAL) | `loom-` | `loom-0.4.2` | The `straymark-loom` visualization server, downloaded on demand by `straymark loom serve` |
 

cli/tests/audit_skill_test.rs

@@ -247,6 +247,11 @@ fn straymark_audit_review_three_platforms_share_core_guidance() {
             body.contains("review.md"),
             "skill must produce the consolidated review.md document"
         );
+        // Calibrator identity is operator-provided (never the CLI product name).
+        assert!(
+            body.contains("router, not the model"),
+            "review skill must forbid substituting the CLI product name for the calibrator identity"
+        );
         // Six-section structure lifted from Sentinel skill.
         assert!(
             body.contains("Executive summary") || body.contains("executive summary"),

dist/.agent/workflows/straymark-audit-review.md

@@ -22,7 +22,7 @@ If only some audits have completed, **do not proceed** — invoking the skill wi
 
 ### 1. Resolve the Charter and verify report set
 
-Argument: a Charter identifier.
+Arguments: a Charter identifier, and an optional `<CALIBRATOR-SLUG>` — `/straymark-audit-review <CHARTER-ID> <CALIBRATOR-SLUG>`. The second argument is the operator-provided identity of the model performing this consolidation (see the calibrator-identity note before the frontmatter block below); it is never inferred from the CLI you are running in.
 
 ```bash
 ls -la .straymark/audits/<CHARTER-ID>/
@@ -93,12 +93,14 @@ Mark these as "Missed by all auditors" in the remediation plan.
 
 ### 5. Build the consolidated review.md
 
+**Calibrator identity — the operator sets it, never self-perception.** The `calibrator:` and `**Reviewer:**` fields name the **backend model** performing this consolidation. Take it from the optional 2nd argument `<CALIBRATOR-SLUG>` or from what the operator states in chat. The CLI you run inside (Qwen Code, Claude Code, Gemini CLI, …) is a **router, not the model**: writing its product name (`qwen-code`, `gemini-cli`, …) instead of the operator-selected backend model is a defect. Fallback only if the operator provided nothing: ask before writing. **Guard:** before finishing, re-read the written `review.md` and confirm `calibrator:` and `**Reviewer:**` both equal the operator-provided slug — not the CLI product name — and fix them if not.
+
 Write the consolidated analysis to `.straymark/audits/<CHARTER-ID>/review.md` with this structure (six sections, lifted from Sentinel's pre-StrayMark audit-review skill):
 
 ```markdown
 ---
 audit_role: calibrator-reconciler
-calibrator: <self-model-id>
+calibrator: <calibrator-slug>
 charter_id: <CHARTER-ID>
 git_range: "<range from prompt>"
 prompt_used: ../audit-prompt.md
@@ -118,7 +120,7 @@ findings_by_status:
 
 # Consolidated audit review — <CHARTER-ID>
 
-**Reviewer:** <self-model-id>
+**Reviewer:** <calibrator-slug>
 **Date:** <YYYY-MM-DD>
 **Confidence:** [High | Medium]
 

dist/.claude/skills/straymark-audit-review/SKILL.md

@@ -2,6 +2,7 @@
 name: straymark-audit-review
 description: Consolidate N external auditor reports into a critical review document with verdicts, remediation plan, and auditor ratings. Then merge the external_audit YAML block into the Charter telemetry. Counterpart of /straymark-audit-prompt and /straymark-audit-execute.
 allowed-tools: Read, Write, Glob, Grep, Bash(straymark charter audit *, straymark charter status *, ls *, git diff *, git log *)
+argument-hint: "CHARTER-NN [CALIBRATOR-SLUG] (calibrator id is operator-provided, never self-detected)"
 ---
 
 # StrayMark Audit Review Skill
@@ -24,7 +25,7 @@ If only some audits have completed, **do not proceed** — invoking the skill wi
 
 ### 1. Resolve the Charter and verify report set
 
-Argument: a Charter identifier.
+Arguments: a Charter identifier, and an optional `<CALIBRATOR-SLUG>` — `/straymark-audit-review <CHARTER-ID> <CALIBRATOR-SLUG>`. The second argument is the operator-provided identity of the model performing this consolidation (see the calibrator-identity note before the frontmatter block below); it is never inferred from the CLI you are running in.
 
 ```bash
 ls -la .straymark/audits/<CHARTER-ID>/
@@ -95,12 +96,14 @@ Mark these as "Missed by all auditors" in the remediation plan.
 
 ### 5. Build the consolidated review.md
 
+**Calibrator identity — the operator sets it, never self-perception.** The `calibrator:` and `**Reviewer:**` fields name the **backend model** performing this consolidation. Take it from the optional 2nd argument `<CALIBRATOR-SLUG>` or from what the operator states in chat. The CLI you run inside (Qwen Code, Claude Code, Gemini CLI, …) is a **router, not the model**: writing its product name (`qwen-code`, `gemini-cli`, …) instead of the operator-selected backend model is a defect. Fallback only if the operator provided nothing: ask before writing. **Guard:** before finishing, re-read the written `review.md` and confirm `calibrator:` and `**Reviewer:**` both equal the operator-provided slug — not the CLI product name — and fix them if not.
+
 Write the consolidated analysis to `.straymark/audits/<CHARTER-ID>/review.md` with this structure (six sections, lifted from Sentinel's pre-StrayMark audit-review skill):
 
 ```markdown
 ---
 audit_role: calibrator-reconciler
-calibrator: <self-model-id>
+calibrator: <calibrator-slug>
 charter_id: <CHARTER-ID>
 git_range: "<range from prompt>"
 prompt_used: ../audit-prompt.md
@@ -120,7 +123,7 @@ findings_by_status:
 
 # Consolidated audit review — <CHARTER-ID>
 
-**Reviewer:** <self-model-id>
+**Reviewer:** <calibrator-slug>
 **Date:** <YYYY-MM-DD>
 **Confidence:** [High | Medium]
 

dist/.codex/skills/straymark-audit-review/SKILL.md

@@ -23,7 +23,7 @@ If only some audits have completed, **do not proceed** — invoking the skill wi
 
 ### 1. Resolve the Charter and verify report set
 
-Argument: a Charter identifier.
+Arguments: a Charter identifier, and an optional `<CALIBRATOR-SLUG>` — `/straymark-audit-review <CHARTER-ID> <CALIBRATOR-SLUG>`. The second argument is the operator-provided identity of the model performing this consolidation (see the calibrator-identity note before the frontmatter block below); it is never inferred from the CLI you are running in.
 
 ```bash
 ls -la .straymark/audits/<CHARTER-ID>/
@@ -94,12 +94,14 @@ Mark these as "Missed by all auditors" in the remediation plan.
 
 ### 5. Build the consolidated review.md
 
+**Calibrator identity — the operator sets it, never self-perception.** The `calibrator:` and `**Reviewer:**` fields name the **backend model** performing this consolidation. Take it from the optional 2nd argument `<CALIBRATOR-SLUG>` or from what the operator states in chat. The CLI you run inside (Qwen Code, Claude Code, Gemini CLI, …) is a **router, not the model**: writing its product name (`qwen-code`, `gemini-cli`, …) instead of the operator-selected backend model is a defect. Fallback only if the operator provided nothing: ask before writing. **Guard:** before finishing, re-read the written `review.md` and confirm `calibrator:` and `**Reviewer:**` both equal the operator-provided slug — not the CLI product name — and fix them if not.
+
 Write the consolidated analysis to `.straymark/audits/<CHARTER-ID>/review.md` with this structure (six sections, lifted from Sentinel's pre-StrayMark audit-review skill):
 
 ```markdown
 ---
 audit_role: calibrator-reconciler
-calibrator: <self-model-id>
+calibrator: <calibrator-slug>
 charter_id: <CHARTER-ID>
 git_range: "<range from prompt>"
 prompt_used: ../audit-prompt.md
@@ -119,7 +121,7 @@ findings_by_status:
 
 # Consolidated audit review — <CHARTER-ID>
 
-**Reviewer:** <self-model-id>
+**Reviewer:** <calibrator-slug>
 **Date:** <YYYY-MM-DD>
 **Confidence:** [High | Medium]
 

dist/.gemini/skills/straymark-audit-review/SKILL.md

@@ -23,7 +23,7 @@ If only some audits have completed, **do not proceed** — invoking the skill wi
 
 ### 1. Resolve the Charter and verify report set
 
-Argument: a Charter identifier.
+Arguments: a Charter identifier, and an optional `<CALIBRATOR-SLUG>` — `/straymark-audit-review <CHARTER-ID> <CALIBRATOR-SLUG>`. The second argument is the operator-provided identity of the model performing this consolidation (see the calibrator-identity note before the frontmatter block below); it is never inferred from the CLI you are running in.
 
 ```bash
 ls -la .straymark/audits/<CHARTER-ID>/
@@ -94,12 +94,14 @@ Mark these as "Missed by all auditors" in the remediation plan.
 
 ### 5. Build the consolidated review.md
 
+**Calibrator identity — the operator sets it, never self-perception.** The `calibrator:` and `**Reviewer:**` fields name the **backend model** performing this consolidation. Take it from the optional 2nd argument `<CALIBRATOR-SLUG>` or from what the operator states in chat. The CLI you run inside (Qwen Code, Claude Code, Gemini CLI, …) is a **router, not the model**: writing its product name (`qwen-code`, `gemini-cli`, …) instead of the operator-selected backend model is a defect. Fallback only if the operator provided nothing: ask before writing. **Guard:** before finishing, re-read the written `review.md` and confirm `calibrator:` and `**Reviewer:**` both equal the operator-provided slug — not the CLI product name — and fix them if not.
+
 Write the consolidated analysis to `.straymark/audits/<CHARTER-ID>/review.md` with this structure (six sections, lifted from Sentinel's pre-StrayMark audit-review skill):
 
 ```markdown
 ---
 audit_role: calibrator-reconciler
-calibrator: <self-model-id>
+calibrator: <calibrator-slug>
 charter_id: <CHARTER-ID>
 git_range: "<range from prompt>"
 prompt_used: ../audit-prompt.md
@@ -119,7 +121,7 @@ findings_by_status:
 
 # Consolidated audit review — <CHARTER-ID>
 
-**Reviewer:** <self-model-id>
+**Reviewer:** <calibrator-slug>
 **Date:** <YYYY-MM-DD>
 **Confidence:** [High | Medium]
 

dist/.straymark/00-governance/AGENT-RULES.md

@@ -412,4 +412,4 @@ When a project accumulates a high volume of AILOGs across multiple Charters and
 
 ---
 
-*StrayMark fw-4.33.0 | [Strange Days Tech](https://strangedays.tech)*
+*StrayMark fw-4.34.0 | [Strange Days Tech](https://strangedays.tech)*

dist/.straymark/00-governance/C4-DIAGRAM-GUIDE.md

@@ -234,4 +234,4 @@ Use a Level 1 (Context) diagram to illustrate:
 
 ---
 
-*StrayMark fw-4.33.0 | [Strange Days Tech](https://strangedays.tech)*
+*StrayMark fw-4.34.0 | [Strange Days Tech](https://strangedays.tech)*

dist/.straymark/00-governance/DOCUMENTATION-POLICY.md

@@ -319,4 +319,4 @@ See also [ADR-2025-01-20-001] for architectural context.
 
 ---
 
-*StrayMark fw-4.33.0 | [Strange Days Tech](https://strangedays.tech)*
+*StrayMark fw-4.34.0 | [Strange Days Tech](https://strangedays.tech)*

dist/.straymark/00-governance/FOLLOW-UPS-BACKLOG-PATTERN.md

@@ -316,4 +316,4 @@ Contributed via [issue #111](https://github.com/StrangeDaysTech/straymark/issues
 
 ---
 
-*StrayMark fw-4.33.0 | [Strange Days Tech](https://strangedays.tech)*
+*StrayMark fw-4.34.0 | [Strange Days Tech](https://strangedays.tech)*

dist/.straymark/00-governance/QUICK-REFERENCE.md

@@ -262,4 +262,4 @@ Mark `review_required: true` when:
 
 ---
 
-*StrayMark fw-4.33.0 | [Strange Days Tech](https://strangedays.tech)*
+*StrayMark fw-4.34.0 | [Strange Days Tech](https://strangedays.tech)*

dist/.straymark/00-governance/i18n/es/AGENT-RULES.md

@@ -412,4 +412,4 @@ Cuando un proyecto acumula un volumen alto de AILOGs a lo largo de múltiples Ch
 
 ---
 
-*StrayMark fw-4.33.0 | [Strange Days Tech](https://strangedays.tech)*
+*StrayMark fw-4.34.0 | [Strange Days Tech](https://strangedays.tech)*

dist/.straymark/00-governance/i18n/es/C4-DIAGRAM-GUIDE.md

@@ -234,4 +234,4 @@ Usar un diagrama de Nivel 1 (Contexto) para ilustrar:
 
 ---
 
-*StrayMark fw-4.33.0 | [Strange Days Tech](https://strangedays.tech)*
+*StrayMark fw-4.34.0 | [Strange Days Tech](https://strangedays.tech)*

dist/.straymark/00-governance/i18n/es/DOCUMENTATION-POLICY.md

@@ -312,4 +312,4 @@ Ver también [ADR-2025-01-20-001] para contexto arquitectónico.
 
 ---
 
-*StrayMark fw-4.33.0 | [Strange Days Tech](https://strangedays.tech)*
+*StrayMark fw-4.34.0 | [Strange Days Tech](https://strangedays.tech)*

dist/.straymark/00-governance/i18n/es/FOLLOW-UPS-BACKLOG-PATTERN.md

@@ -316,4 +316,4 @@ Contribuido vía [issue #111](https://github.com/StrangeDaysTech/straymark/issue
 
 ---
 
-*StrayMark fw-4.33.0 | [Strange Days Tech](https://strangedays.tech)*
+*StrayMark fw-4.34.0 | [Strange Days Tech](https://strangedays.tech)*

dist/.straymark/00-governance/i18n/es/QUICK-REFERENCE.md

@@ -234,4 +234,4 @@ Marcar `review_required: true` cuando:
 
 ---
 
-*StrayMark fw-4.33.0 | [Strange Days Tech](https://strangedays.tech)*
+*StrayMark fw-4.34.0 | [Strange Days Tech](https://strangedays.tech)*

dist/.straymark/00-governance/i18n/zh-CN/AGENT-RULES.md

@@ -407,4 +407,4 @@ confidence: high | medium | low
 
 ---
 
-*StrayMark fw-4.33.0 | [Strange Days Tech](https://strangedays.tech)*
+*StrayMark fw-4.34.0 | [Strange Days Tech](https://strangedays.tech)*

dist/.straymark/00-governance/i18n/zh-CN/C4-DIAGRAM-GUIDE.md

@@ -234,4 +234,4 @@ Rel(api, db, "Reads/Writes", "SQL")
 
 ---
 
-*StrayMark fw-4.33.0 | [Strange Days Tech](https://strangedays.tech)*
+*StrayMark fw-4.34.0 | [Strange Days Tech](https://strangedays.tech)*

dist/.straymark/00-governance/i18n/zh-CN/DOCUMENTATION-POLICY.md

@@ -311,4 +311,4 @@ review_outcome: approved                # approved | revisions_requested | rejec
 
 ---
 
-*StrayMark fw-4.33.0 | [Strange Days Tech](https://strangedays.tech)*
+*StrayMark fw-4.34.0 | [Strange Days Tech](https://strangedays.tech)*

dist/.straymark/00-governance/i18n/zh-CN/FOLLOW-UPS-BACKLOG-PATTERN.md

@@ -316,4 +316,4 @@ straymark followups promote FU-NNN        # 自动化 FU → TDE 提升(见上
 
 ---
 
-*StrayMark fw-4.33.0 | [Strange Days Tech](https://strangedays.tech)*
+*StrayMark fw-4.34.0 | [Strange Days Tech](https://strangedays.tech)*

dist/.straymark/00-governance/i18n/zh-CN/QUICK-REFERENCE.md

@@ -234,4 +234,4 @@ risk_level: low | medium | high | critical
 
 ---
 
-*StrayMark fw-4.33.0 | [Strange Days Tech](https://strangedays.tech)*
+*StrayMark fw-4.34.0 | [Strange Days Tech](https://strangedays.tech)*

dist/dist-manifest.yml

@@ -1,4 +1,4 @@
-version: "4.33.0"
+version: "4.34.0"
 description: "StrayMark distribution manifest"
 repository: "https://github.com/StrangeDaysTech/straymark"
 

docs/adopters/CLI-REFERENCE.md

@@ -45,7 +45,7 @@ StrayMark uses **independent version tags** for each component:
 
 | Component | Tag prefix | Example | What it includes |
 |-----------|-----------|---------|------------------|
-| Framework | `fw-` | `fw-4.33.0` | Templates (12 types), governance docs, directives, Charter template + schema |
+| Framework | `fw-` | `fw-4.34.0` | Templates (12 types), governance docs, directives, Charter template + schema |
 | CLI | `cli-` | `cli-3.30.0` | The `straymark` binary |
 | Loom (EXPERIMENTAL) | `loom-` | `loom-0.4.2` | The `straymark-loom` visualization server, downloaded on demand by `straymark loom serve` |
 

docs/i18n/es/README.md

@@ -240,7 +240,7 @@ StrayMark usa tags de versión independientes para cada componente:
 
 | Componente | Prefijo de tag | Ejemplo | Incluye |
 |------------|---------------|---------|---------|
-| Framework | `fw-` | `fw-4.33.0` | Plantillas (12 tipos), gobernanza, directivas, plantilla + schema de Charter |
+| Framework | `fw-` | `fw-4.34.0` | Plantillas (12 tipos), gobernanza, directivas, plantilla + schema de Charter |
 | CLI | `cli-` | `cli-3.30.0` | El binario `straymark` |
 | Loom (EXPERIMENTAL) | `loom-` | `loom-0.4.2` | El servidor de visualización `straymark-loom`, descargado bajo demanda por `straymark loom serve` |
 

docs/i18n/es/adopters/CLI-REFERENCE.md

@@ -45,7 +45,7 @@ StrayMark usa **tags de versión independientes** para cada componente:
 
 | Componente | Prefijo de tag | Ejemplo | Qué incluye |
 |------------|---------------|---------|-------------|
-| Framework | `fw-` | `fw-4.33.0` | Plantillas (12 tipos), docs de gobernanza, directivas |
+| Framework | `fw-` | `fw-4.34.0` | Plantillas (12 tipos), docs de gobernanza, directivas |
 | CLI | `cli-` | `cli-3.30.0` | El binario `straymark` |
 | Loom (EXPERIMENTAL) | `loom-` | `loom-0.4.2` | El servidor de visualización `straymark-loom`, descargado bajo demanda por `straymark loom serve` |
 

docs/i18n/zh-CN/README.md

@@ -258,7 +258,7 @@ StrayMark 为每个组件使用独立的版本标签：
 
 | 组件 | 标签前缀 | 示例 | 包含内容 |
 |------|----------|------|----------|
-| Framework | `fw-` | `fw-4.33.0` | 模板（12 种类型）、治理文档、指令、Charter 模板 + schema |
+| Framework | `fw-` | `fw-4.34.0` | 模板（12 种类型）、治理文档、指令、Charter 模板 + schema |
 | CLI | `cli-` | `cli-3.30.0` | `straymark` 二进制文件 |
 | Loom（实验性） | `loom-` | `loom-0.4.2` | `straymark-loom` 可视化服务器，由 `straymark loom serve` 按需下载 |
 

docs/i18n/zh-CN/adopters/CLI-REFERENCE.md

@@ -45,7 +45,7 @@ StrayMark 为每个组件使用**独立的版本标签**：
 
 | 组件 | 标签前缀 | 示例 | 包含内容 |
 |------|----------|------|----------|
-| Framework | `fw-` | `fw-4.33.0` | 模板（12 种类型）、治理文档、指令 |
+| Framework | `fw-` | `fw-4.34.0` | 模板（12 种类型）、治理文档、指令 |
 | CLI | `cli-` | `cli-3.30.0` | `straymark` 二进制文件 |
 | Loom（实验性） | `loom-` | `loom-0.4.2` | `straymark-loom` 可视化服务器，由 `straymark loom serve` 按需下载 |