@moretea-labs/forge 1.5.1 → 1.7.0

package/AGENTS.md

@@ -43,6 +43,8 @@ Treat ChatGPT as the controller and Forge as its repository execution layer. Cha
 
 ## Operating Rules
 
+- After a managed repository change is verified and committed/merged, push the delivered target branch to its configured remote promptly. Do not leave a successfully delivered commit only on local refs unless the user explicitly requested local-only delivery or the push is blocked by safety, permissions, authentication, or branch policy; surface the exact blocker when a push cannot complete.
+- Treat the Google Cloud `forge-cloud` VM experiment as retired infrastructure. Do not restart or reuse that VM for Forge Cloud. Any future remote Forge maintainer must use a separately evaluated host/transport and must demonstrate better latency and reliability than the local Forge path before adoption.
 - Sync `tasks/` whenever substantive repo changes are made.
 - Use `tasks/notes/<plan-stem>.notes.md` only for non-obvious slice decisions, deviations, tradeoffs, and open questions; `<plan-stem>` is the active plan filename without `plan-` and `.md` (for example `20260531-0045-governance-workflow`). Do not use notes as durable memory or a task log, and archive/promote them deliberately when the slice closes.
 - Treat hook execution as central-first: trusted repos run `~/.forge/hooks/` (bash shim) or the packaged CLI copy; this self-host repo pins `"hook_source": "repo"` in `.ai/harness/policy.json` so `.ai/hooks/` stays the live development runtime, with `assets/hooks/` as the product source mirrored on install. User-level `~/.claude/settings.json` and `~/.codex/hooks.json` are the host adapters.

package/CHANGELOG.md

@@ -4,6 +4,52 @@ All notable public Forge changes are recorded here. Release entries are tied to
 
 ## Unreleased
 
+## 1.7.0 - 2026-08-27
+
+### Persistent autonomous control
+
+- Add the durable Schedule → Work → ChatGPT conversation continuation contract, explicit round dispositions, effect-only Work/finalization semantics, and tab settlement after Controller release instead of immediately after prompt dispatch.
+- Keep transient Browser/connector readiness failures on bounded backoff without permanently disabling schedules, while authentication, consent, destructive actions, and other hard boundaries remain fail-closed.
+- Make real timer-origin continuation and the Continuous Evolution Supervisor a stable-release gate rather than treating schedule configuration alone as proof of autonomous operation.
+
+### Browser Runtime V3
+
+- Promote Browser Runtime V3 as the current browser architecture with one Controller Home BrowserSession authority, stable plugin-owned native tab identity, background-safe navigation, exact rebind, and explicit physical-input fallback.
+- Harden native replacement with strict postconditions, HTTP(S) settlement that rejects transitional `about:*` pages, destination-origin authorization, and preservation of user-owned tabs.
+- Improve Chrome/Vivaldi provider behavior, postcondition evidence, restart/rebind handling, and visual evidence integration without adding a second Browser authority.
+
+### Capabilities, plugins, and iOS
+
+- Add deterministic natural-intent capability discovery while keeping `plugin_action_execute` as the sole typed plugin executor and preserving the stable ChatGPT facade.
+- Add controller-global plugin profiles with repository overlays, including reusable App Store Connect credential references without copying private-key contents into repository state or tool output.
+- Add typed physical-device iOS build destinations and opt-in Xcode provisioning updates using file-backed App Store Connect key references, with bounded/redacted execution evidence.
+
+### Runtime, recovery, and governance
+
+- Continue converging Work/Plan/finalizer lifecycle authority, target-advancement validation, process/session fencing, source coherence, and whole-Runtime immutable activation/rollback under the independent Recovery boundary.
+- Keep ChatGPT as the semantic controller and Forge as the deterministic execution/control plane, with Direct-first execution and durable Work/Plan state only where continuity, isolation, recovery, scheduling, or external effects require it.
+- Tighten maintained architecture/documentation authority and capability-closure governance so stale Work or superseded design documents do not become parallel current truth.
+
+## 1.6.0 - 2026-08-16
+
+### Architecture V2 and execution governance
+
+- Complete the V2 Direct / bounded Work / Plan execution model, including isolated Work materialization, authoritative finalization, dead-Plan recovery, duplicate-writer prevention, and safer Work validation.
+- Decouple durable Work ownership from transient MCP transport sessions so scheduled and interactive ChatGPT execution can resume against stable controller leases and checkout identity.
+- Add bounded impact context and CodeGraph-aware retrieval while keeping routing, semantic context, and repository authority converged on one deterministic control path.
+
+### Performance and Runtime
+
+- Reduce controller hot-path overhead with canonical repository-root reuse, exact-file retrieval fast paths, Runtime proxy session reuse, batched Process identity probes, narrower service claims, and read-only SQLite diagnostics.
+- Preserve resumable Process/check execution while improving persisted-check retry idempotency, stale-process handling, worktree reconciliation, and release/runtime identity safety.
+- Keep the stable 19-tool ChatGPT surface while moving more domain behavior behind typed capability and plugin contracts.
+
+### Automation and plugins
+
+- Add Forge-native ChatGPT workflows, schedules, Work-bound browser watchers, cross-session workflow attribution, and more reliable ChatGPT mode/reasoning selection.
+- Add trusted external-plugin registration lifecycle support and official Forge Figma Bridge catalog installation; retire the bundled desktop helper in favor of the external provider boundary.
+- Improve plugin scope/compatibility handling, browser URL behavior, image artifact delivery, Gmail Unicode subjects, and automation history/configuration surfaces.
+
 ## 1.5.1 - 2026-08-13
 
 ### ChatGPT Secure Tunnel and package setup

package/CLAUDE.md

@@ -43,6 +43,8 @@ Treat ChatGPT as the controller and Forge as its repository execution layer. Cha
 
 ## Operating Rules
 
+- After a managed repository change is verified and committed/merged, push the delivered target branch to its configured remote promptly. Do not leave a successfully delivered commit only on local refs unless the user explicitly requested local-only delivery or the push is blocked by safety, permissions, authentication, or branch policy; surface the exact blocker when a push cannot complete.
+- Treat the Google Cloud `forge-cloud` VM experiment as retired infrastructure. Do not restart or reuse that VM for Forge Cloud. Any future remote Forge maintainer must use a separately evaluated host/transport and must demonstrate better latency and reliability than the local Forge path before adoption.
 - Sync `tasks/` whenever substantive repo changes are made.
 - Use `tasks/notes/<plan-stem>.notes.md` only for non-obvious slice decisions, deviations, tradeoffs, and open questions; `<plan-stem>` is the active plan filename without `plan-` and `.md` (for example `20260531-0045-governance-workflow`). Do not use notes as durable memory or a task log, and archive/promote them deliberately when the slice closes.
 - Treat hook execution as central-first: trusted repos run `~/.forge/hooks/` (bash shim) or the packaged CLI copy; this self-host repo pins `"hook_source": "repo"` in `.ai/harness/policy.json` so `.ai/hooks/` stays the live development runtime, with `assets/hooks/` as the product source mirrored on install. User-level `~/.claude/settings.json` and `~/.codex/hooks.json` are the host adapters.

package/DESIGN.md

@@ -218,9 +218,14 @@ Dark, persistent and quiet. It contains Forge identity, grouped navigation, and
 ### Command bar
 Each route owns a compact command bar: eyebrow, title, one-line purpose, refreshed time and route actions. `Open ChatGPT` remains globally available but visually secondary.
 
+## Page composition rules
+Each workspace has **one dominant information region** and at most one contextual secondary region. Pages are not collections of cards; layout, typography, aligned columns, whitespace and hairlines establish hierarchy before enclosure.
+
+Collections use rows or tables. A selected entity uses one contextual detail pane. Configuration uses titled sections with field rows. Metrics stay inline or in compact definition rows unless direct metric comparison is the task. Normal state is visually neutral; semantic color is reserved for exceptions, attention and explicit interaction.
+
 ## Core component grammar
 ### Metric strip
-Overview may show at most four coarse operational facts in one horizontal strip. Metrics share one surface and divider rhythm; they are not separate cards.
+Metric strips are exceptional. Use them only when comparing coarse operational facts is itself useful; never make equal metric cards the default page composition.
 
 ### Data list
 Primary scanning surface for Work, Capabilities and Repositories. Rows use hairline separators and bounded one-line context.
@@ -236,7 +241,7 @@ Use a 7px dot plus short text. Filled badges are exceptional.
 
 ## Page grammar
 ### Overview
-Command bar, one four-column metric strip, a deduplicated attention list capped to actionable groups, and a compact persistent-goals summary. No prompt composer, run timeline or grid of equal cards.
+Overview is a **cross-workspace status and attention surface**, not a collection manager. Keep it single-column and lightweight: first surface a bounded, deduplicated Needs attention list across Work, Automations, Capabilities, Repositories and System; then show one compact Workspace summary row for each owning workspace. Overview does not enumerate ordinary Work, group content by repository, expose collection filters or open a detail pane. It routes the user to the owning workspace for management. Healthy state stays compact and neutral. Activity feeds require authoritative event semantics and must never be inferred from `updatedAt` or other incidental timestamps. No prompt composer, run timeline, repository portfolio, equal metric grid or decorative posture hero.
 
 ### Automations
 Use a configuration-first table with Name, Schedule, Scope, Delivery, Status, Last and Next; filters Enabled / Paused / Attention / All; selected detail pane with exact source and Run/Pause/Resume. Never duplicate report body.

package/README.md

@@ -48,7 +48,7 @@ Setup persists progress and guides the selected path through the user-level Pack
 
 Then follow [Install and start](docs/tutorials/01-install-and-start.md) and [Connect ChatGPT](docs/tutorials/02-connect-chatgpt.md). A repository is optional during initial setup; add one later with `forge adopt --repo /path/to/your-project`. Upgrade an existing install with `npm install -g @moretea-labs/forge@latest`, verify with `forge --version`, then run `forge setup next` to reconcile newer Runtime/connector setup contracts.
 
-For a reviewed source checkout: `git clone https://github.com/moretea-labs/forge.git && cd forge && npm ci --ignore-scripts --no-audit --no-fund && npm install -g . --omit=optional --no-audit --no-fund`.
+For a reviewed source checkout: `git clone https://github.com/moretea-labs/forge.git && cd forge && bun install --frozen-lockfile && npm install -g . --omit=optional --no-audit --no-fund`.
 
 ## Built in, and extensible
 
@@ -58,7 +58,7 @@ Forge ships typed local/browser/desktop/iOS/GitHub/Gmail/Calendar/Tasks/App Stor
 
 Local read/write grants are explicit and expiring; remote or destructive effects are distinguished from ordinary local work; high-impact actions require stronger confirmation. Full Access reduces repetitive prompts for normal work without removing the hard boundaries around secrets, destructive actions, and outside-workspace access. See [Security](SECURITY.md) and the [Security Model](docs/wiki/Security-Model.md).
 
-**Docs:** [Wiki](docs/wiki/Home.md) · [Support](SUPPORT.md) · [Contributing](CONTRIBUTING.md) · [Changelog](CHANGELOG.md). Current stable release: `1.5.1`; stable installs use npm `latest`.
+**Docs:** [Wiki](docs/wiki/Home.md) · [Support](SUPPORT.md) · [Contributing](CONTRIBUTING.md) · [Changelog](CHANGELOG.md). Current stable release: `1.7.0`; stable installs use npm `latest`.
 
 ---
 <a id="zh-cn"></a>
@@ -103,10 +103,10 @@ forge setup next     # 按每次显示的 Next 动作继续
 
 远程主控的 setup 会继续引导 Package Runtime、远程连接、主控配置和连接验证；对 ChatGPT，`--tunnel auto` 现在明确表示 **优先 OpenAI Secure MCP Tunnel**。Forge 保持 Canonical Runtime 私有，并安装一个仅监听 loopback 的 OAuth Gateway，再由官方 `tunnel-client` 出站连接 OpenAI。只有 Secure Tunnel 不可用时才显式选择 Cloudflare Tunnel、Tailscale Funnel、已有 HTTPS `/mcp` 或暂缓远程连接。本地 Codex/Claude 主控不需要 tunnel。ChatGPT App/connector 是应用身份，Secure Tunnel 只是网络传输层，因此切换网络不会产生另一套 Forge 工具 schema。
 
-继续阅读[安装与启动](docs/tutorials/01-install-and-start.zh-CN.md)和[连接 ChatGPT](docs/tutorials/02-connect-chatgpt.zh-CN.md)。仓库不是首次 setup 的前置条件，需要开发能力时再运行 `forge adopt --repo /path/to/your-project`。已安装用户升级：`npm install -g @moretea-labs/forge@latest`，确认 `forge --version` 后运行 `forge setup next` 让新版 setup 自动补齐 Runtime/connector 配置。源码安装：`git clone https://github.com/moretea-labs/forge.git && cd forge && npm ci --ignore-scripts --no-audit --no-fund && npm install -g . --omit=optional --no-audit --no-fund`。
+继续阅读[安装与启动](docs/tutorials/01-install-and-start.zh-CN.md)和[连接 ChatGPT](docs/tutorials/02-connect-chatgpt.zh-CN.md)。仓库不是首次 setup 的前置条件，需要开发能力时再运行 `forge adopt --repo /path/to/your-project`。已安装用户升级：`npm install -g @moretea-labs/forge@latest`，确认 `forge --version` 后运行 `forge setup next` 让新版 setup 自动补齐 Runtime/connector 配置。源码安装：`git clone https://github.com/moretea-labs/forge.git && cd forge && bun install --frozen-lockfile && npm install -g . --omit=optional --no-audit --no-fund`。
 
 Forge 内置本机、Browser、Desktop、iOS、GitHub、Gmail、Calendar、Tasks、App Store Connect、Resend 等类型化能力；公开 Provider 目录还有 **Forge Desktop Operator / Forge Design / Personal Knowledge Assistant**。详见[功能清单](docs/operations/features.zh-CN.md)与[插件管理](docs/forge-plugin-management.md)。
 
 安全上，普通本地修改、远程影响、破坏性操作、密钥和工作区外访问是不同边界；Full Access 不会取消高风险确认。详见[安全说明](SECURITY.md)和[安全模型](docs/wiki/Security-Model.md)。
 
-**文档：** [Wiki](docs/wiki/Home.md) · [支持](SUPPORT.md) · [贡献](CONTRIBUTING.md) · [更新日志](CHANGELOG.md)。当前稳定版为 `1.5.1`，稳定安装使用 npm `latest`。
+**文档：** [Wiki](docs/wiki/Home.md) · [支持](SUPPORT.md) · [贡献](CONTRIBUTING.md) · [更新日志](CHANGELOG.md)。当前稳定版为 `1.7.0`，稳定安装使用 npm `latest`。

package/README.zh-CN.md

@@ -62,7 +62,7 @@ forge setup next     # 按每次显示的 Next 动作继续
 
 ```bash
 git clone https://github.com/moretea-labs/forge.git && cd forge
-npm ci --ignore-scripts --no-audit --no-fund
+bun install --frozen-lockfile
 npm install -g . --omit=optional --no-audit --no-fund
 ```
 
@@ -78,4 +78,4 @@ Forge 把读取、普通本地写入、远程操作、破坏性操作、工作
 
 [中文文档中心](docs/README.zh-CN.md) · [Wiki](docs/wiki/Home.md) · [SUPPORT.md](SUPPORT.md) · [CONTRIBUTING.md](CONTRIBUTING.md) · [CHANGELOG.md](CHANGELOG.md)
 
-当前稳定版本是 `1.5.1`，稳定安装使用 npm `latest`。
+当前稳定版本是 `1.7.0`，稳定安装使用 npm `latest`。

package/SKILL.md

@@ -40,8 +40,8 @@ Automatic routing remains authoritative when the user does not provide a mode di
 
 A leading mode directive is an opt-in instruction to ChatGPT's Forge router. It applies only to the current request, is removed from the objective before execution, and never bypasses permissions, Runtime authority, protected-path rules, approvals, or destructive/remote-write confirmation.
 
-- `-plan` or `/plan`: force the reviewed planning path. Planning is read-only: inspect repository state and call `controller_context_pack` with `structural_context=required` so CodeGraph symbol/reference/dependency/impact evidence is used when the index is ready; load only relevant architecture/ADR/design/README material, then create or revise the existing PlanContract. Review the PlanContract before approval. Do not start mutation until the reviewed plan is approved and execution is explicitly bound to an approved plan step. If CodeGraph is unavailable or stale, keep the degraded evidence warning visible and use bounded current-source context instead of pretending graph coverage exists.
-- `-debug` or `/debug`: force evidence-first debugging. Reproduce or characterize the failure, then prefer `controller_context_pack` with `structural_context=auto` to isolate callers, dependencies, and the smallest causal surface before patching and focused verification. The directive does not force an Agent or durable Work; existing routing still chooses Direct, bounded Work, or an optional worker from the actual scope and risk.
+- `-plan` or `/plan`: force the reviewed planning path. Planning is read-only: inspect repository state and call `rh_context` search with `structural_context=required` so CodeGraph symbol/reference/dependency/impact evidence is used when the index is ready; load only relevant architecture/ADR/design/README material, then create or revise the existing PlanContract. Review the PlanContract before approval. Do not start mutation until the reviewed plan is approved and execution is explicitly bound to an approved plan step. If CodeGraph is unavailable or stale, keep the degraded evidence warning visible and use bounded current-source context instead of pretending graph coverage exists.
+- `-debug` or `/debug`: force evidence-first debugging. Reproduce or characterize the failure, then prefer repeated `rh_context` search with `structural_context=auto` to isolate callers, dependencies, and the smallest causal surface before patching and focused verification. The directive does not force an Agent or durable Work; existing routing still chooses Direct, bounded Work, or an optional worker from the actual scope and risk.
 
 A bare directive with no objective should return/explain that mode's working contract and must not mutate repository state. Mode directives are not sticky across turns unless the user repeats them or explicitly asks to continue the same active Plan/Work.
 

package/THIRD_PARTY_NOTICES.md

@@ -1,6 +1,6 @@
 # Third-party notices
 
-This inventory covers the direct runtime and development dependencies declared by `@moretea-labs/forge@1.5.1`.
+This inventory covers the direct runtime and development dependencies declared by `@moretea-labs/forge@1.7.0`.
 
 License values come from `package-lock.json` where available. For lock entries without a license field, the declared license was verified from package metadata during release preparation. This file is informational and does not replace the license text distributed by each dependency.
 

package/agents/openai.yaml

@@ -1,4 +1,4 @@
 interface:
   display_name: "forge"
   short_description: "Operate Forge workflows for repository planning, execution, verification, migration, audit, and repair"
-  default_prompt: "Use Forge to inspect this repository, choose the smallest appropriate workflow, and carry out or plan the requested work with bounded evidence and verification."
+  default_prompt: "Use Forge to inspect this repository, choose the smallest appropriate workflow, and carry out or plan the requested work with bounded evidence and verification. After verified repository delivery, promptly push the committed/merged target branch to its configured remote unless the user explicitly requested local-only delivery or the push is blocked; report any blocker precisely."

package/assets/hooks/hook-input.sh

@@ -26,10 +26,12 @@ hook_read_stdin_once() {
 
   if [[ -t 0 ]]; then
     HOOK_STDIN_JSON=""
+    export HOOK_STDIN_JSON
     return
   fi
 
   HOOK_STDIN_JSON="$(cat 2>/dev/null || true)"
+  export HOOK_STDIN_JSON
 }
 
 hook_json_extract_with_bun() {
@@ -275,11 +277,6 @@ hook_get_session_id() {
   local arg="${1:-}"
   local parsed=""
 
-  if [[ -n "${HOOK_SESSION_ID:-}" ]]; then
-    printf '%s' "$HOOK_SESSION_ID"
-    return
-  fi
-
   parsed="$(hook_json_get '.session_id' '')"
   if [[ -n "$parsed" ]]; then
     HOOK_SESSION_ID="$parsed"
@@ -296,13 +293,19 @@ hook_get_session_id() {
     return
   fi
 
-  if [[ -n "${CLAUDE_SESSION_ID:-${CODEX_SESSION_ID:-}}" ]]; then
-    HOOK_SESSION_ID="${CLAUDE_SESSION_ID:-${CODEX_SESSION_ID:-}}"
-    export HOOK_SESSION_ID
+  if [[ -n "${HOOK_SESSION_ID:-}" ]]; then
     printf '%s' "$HOOK_SESSION_ID"
     return
   fi
 
+  parsed="${CLAUDE_SESSION_ID:-${CODEX_SESSION_ID:-${SESSION_KEY:-}}}"
+  if [[ -n "$parsed" ]]; then
+    HOOK_SESSION_ID="$parsed"
+    export HOOK_SESSION_ID
+    printf '%s' "$parsed"
+    return
+  fi
+
   printf '%s' ""
 }
 

package/assets/hooks/lib/session-state.sh

@@ -17,16 +17,15 @@ session_state_new_session_id() {
 session_state_resolve_key() {
   local session_id_file="$1"
   local arg="${2:-}"
-  local session_key="${HOOK_SESSION_ID:-}"
+  local session_key=""
 
-  if [[ -z "$session_key" ]] && declare -F hook_get_session_id >/dev/null 2>&1; then
+  # An event payload is more specific than ambient host state. This matters for
+  # forwarded or replayed hook input, where the parent process can belong to a
+  # different host session than the event being handled.
+  if declare -F hook_get_session_id >/dev/null 2>&1; then
     session_key="$(hook_get_session_id "$arg")"
   fi
 
-  if [[ -z "$session_key" ]]; then
-    session_key="${CLAUDE_SESSION_ID:-${CODEX_SESSION_ID:-${SESSION_KEY:-}}}"
-  fi
-
   if [[ -n "$session_key" ]]; then
     mkdir -p "$(dirname "$session_id_file")" 2>/dev/null || true
     printf '%s\n' "$session_key" > "$session_id_file" 2>/dev/null || true
@@ -34,10 +33,14 @@ session_state_resolve_key() {
     return
   fi
 
-  if [[ -z "$session_key" ]] && [[ -s "$session_id_file" ]]; then
+  if [[ -s "$session_id_file" ]]; then
     session_key="$(cat "$session_id_file" 2>/dev/null || true)"
   fi
 
+  if [[ -z "$session_key" ]]; then
+    session_key="${HOOK_SESSION_ID:-${CLAUDE_SESSION_ID:-${CODEX_SESSION_ID:-${SESSION_KEY:-}}}}"
+  fi
+
   if [[ -z "$session_key" ]]; then
     session_key="$(session_state_new_session_id)"
     mkdir -p "$(dirname "$session_id_file")" 2>/dev/null || true

package/assets/hooks/lib/workflow-state.sh

@@ -575,16 +575,21 @@ workflow_cleanup_candidate() {
     [[ -e "$metadata" ]] || continue
     slug="$(basename "$metadata" .json)"
     [[ -n "$slug" ]] || continue
-    printf '%s\t%s\t\n' "$slug" "${branch_prefix}${slug}"
-    return 0
+    branch="${branch_prefix}${slug}"
+    # Controller metadata can outlive a terminal worktree after a Home
+    # migration. It is not cleanup work unless a Git branch or worktree still
+    # exists; otherwise it must never keep a fresh resume packet stale.
+    if git show-ref --verify --quiet "refs/heads/${branch}"; then
+      printf '%s\t%s\t\n' "$slug" "$branch"
+      return 0
+    fi
   done
 
   return 1
 }
 
 workflow_next_action() {
-  local active_plan task_state total done next_pending contract_file review_file checks_file checks_error
-  local external_status external_state external_reviewer external_source external_message expected_source
+  local active_plan task_state total done next_pending contract_file checks_file checks_error
   local target current_branch slug candidate branch worktree command message
 
   active_plan="$(get_active_plan || true)"
@@ -602,38 +607,19 @@ workflow_next_action() {
     fi
 
     contract_file="$(workflow_active_contract || true)"
-    review_file="$(workflow_active_review || true)"
     checks_file="$(workflow_checks_file)"
 
-    if [[ -z "$review_file" || ! -f "$review_file" ]]; then
-      printf 'review\t/review\tStage the completed module diff first; then run /review and record a sprint review before finishing this worktree.\n'
-      return 0
-    fi
-
-    if ! workflow_review_recommends_pass "$review_file"; then
-      printf 'review\t/review\tStage the completed module diff first; then run /review until %s records Recommendation: pass.\n' "$review_file"
-      return 0
-    fi
-
     if [[ -z "$contract_file" || ! -f "$contract_file" ]]; then
       printf 'check\t/check\tStage the completed module diff first; then regenerate the active sprint contract and run /review.\n'
       return 0
     fi
 
-    external_status="$(workflow_external_acceptance_status "$review_file")"
-    IFS=$'\t' read -r external_state external_reviewer external_source external_message <<< "$external_status"
-    if [[ "$external_state" != "pass" && "$external_state" != "manual_override" ]]; then
-      expected_source="$(workflow_external_acceptance_expected_source)"
-      printf 'check\t/check\tStage the completed module diff first; then %s Run external acceptance via %s and record ## External Acceptance Advice in %s.\n' "${external_message:-External acceptance is missing.}" "$expected_source" "$review_file"
-      return 0
-    fi
-
     if [[ ! -f "$checks_file" ]]; then
       printf 'review\t/review\tStage the completed module diff first; then run /review and verify-sprint so %s exists.\n' "$checks_file"
       return 0
     fi
 
-    if ! checks_error="$(workflow_checks_pass "$checks_file" "$contract_file" "$review_file")"; then
+    if ! checks_error="$(workflow_checks_pass "$checks_file" "$contract_file")"; then
       printf 'check\t/check\tStage the completed module diff first; then resolve check evidence: %s\n' "$checks_error"
       return 0
     fi
@@ -641,7 +627,7 @@ workflow_next_action() {
     target="$(workflow_target_branch)"
     current_branch="$(workflow_current_branch)"
     if workflow_is_linked_worktree && [[ -n "$current_branch" && "$current_branch" != "$target" ]]; then
-      printf 'finish\tbash scripts/contract-worktree.sh finish\tReview/checks pass; finish and fast-forward merge this contract worktree.\n'
+      printf 'review\t/review\tCheck evidence passed. Freshly review user intent, affected domains, downstream consumers, and state transitions; then finish this contract worktree.\n'
       return 0
     fi
   fi
@@ -1282,151 +1268,10 @@ workflow_write_run_summary() {
 EOF_RUN
 }
 
-workflow_review_recommends_pass() {
-  local review_file="${1:-}"
-  [[ -n "$review_file" && -f "$review_file" ]] || return 1
-  grep -Eq '^> \*\*Recommendation\*\*:[[:space:]]*pass[[:space:]]*$' "$review_file"
-}
-
-workflow_external_acceptance_expected_reviewer() {
-  local host="${HOOK_HOST:-}"
-
-  if [[ -z "$host" ]]; then
-    if [[ -n "${CODEX_RUN_ID:-}${CODEX_SESSION_ID:-}${CODEX_THREAD_ID:-}${CODEX_SHELL:-}${CODEX_INTERNAL_ORIGINATOR_OVERRIDE:-}" ]]; then
-      host="codex"
-    elif [[ -n "${CLAUDE_RUN_ID:-}${CLAUDE_SESSION_ID:-}" ]]; then
-      host="claude"
-    else
-      host="claude"
-    fi
-  fi
-
-  if [[ "$host" == "codex" ]]; then
-    printf 'Claude'
-  else
-    printf 'Codex'
-  fi
-}
-
-workflow_external_acceptance_source_for_reviewer() {
-  local reviewer="${1:-}"
-  case "$(printf '%s' "$reviewer" | tr '[:upper:]' '[:lower:]')" in
-    claude) printf 'claude-review' ;;
-    *) printf 'codex-review' ;;
-  esac
-}
-
-workflow_external_acceptance_expected_source() {
-  local reviewer="${1:-}"
-  reviewer="${reviewer:-$(workflow_external_acceptance_expected_reviewer)}"
-  workflow_external_acceptance_source_for_reviewer "$reviewer"
-}
-
-workflow_external_acceptance_section() {
-  local review_file="${1:-}"
-  [[ -n "$review_file" && -f "$review_file" ]] || return 1
-  awk '
-    /^##[[:space:]]+External Acceptance Advice[[:space:]]*$/ { in_section = 1; next }
-    /^##[[:space:]]+/ && in_section { exit }
-    in_section { print }
-  ' "$review_file"
-}
-
-workflow_external_acceptance_field() {
-  local section="${1:-}"
-  local label="${2:-}"
-  printf '%s\n' "$section" |
-    sed -nE "s/^> \\*\\*${label}\\*\\*:[[:space:]]*([^[:space:]].*)[[:space:]]*$/\\1/p" |
-    head -n 1 |
-    sed -E 's/[[:space:]]+$//'
-}
-
-workflow_external_acceptance_status() {
-  local review_file="${1:-}"
-  local expected_reviewer="${2:-}"
-  local expected_source section acceptance reviewer source p1_blockers manual_override
-  local acceptance_lc reviewer_lc source_lc expected_reviewer_lc expected_source_lc p1_lc
-
-  expected_reviewer="${expected_reviewer:-$(workflow_external_acceptance_expected_reviewer)}"
-  expected_source="$(workflow_external_acceptance_expected_source "$expected_reviewer")"
-
-  if [[ -z "$review_file" || ! -f "$review_file" ]]; then
-    printf 'missing\t-\t-\tExternal acceptance review file is missing: %s\n' "${review_file:-tasks/reviews/<slug>.review.md}"
-    return 0
-  fi
-
-  section="$(workflow_external_acceptance_section "$review_file" || true)"
-  if [[ -z "$section" ]]; then
-    printf 'missing\t-\t-\tExternal acceptance section is missing from %s.\n' "$review_file"
-    return 0
-  fi
-
-  acceptance="$(workflow_external_acceptance_field "$section" "External Acceptance")"
-  reviewer="$(workflow_external_acceptance_field "$section" "External Reviewer")"
-  source="$(workflow_external_acceptance_field "$section" "External Source")"
-  p1_blockers="$(
-    printf '%s\n' "$section" |
-      sed -nE 's/^- P1 blockers:[[:space:]]*([^[:space:]].*)[[:space:]]*$/\1/p' |
-      head -n 1 |
-      sed -E 's/[[:space:]]+$//'
-  )"
-  manual_override="$(
-    printf '%s\n' "$section" |
-      sed -nE 's/^-?[[:space:]]*Manual Override:[[:space:]]*([^[:space:]].*)[[:space:]]*$/\1/p' |
-      head -n 1 |
-      sed -E 's/[[:space:]]+$//'
-  )"
-
-  if [[ -n "$manual_override" ]]; then
-    printf 'manual_override\t%s\t%s\tManual override recorded for external acceptance: %s\n' "${reviewer:--}" "${source:--}" "$manual_override"
-    return 0
-  fi
-
-  acceptance_lc="$(printf '%s' "$acceptance" | tr '[:upper:]' '[:lower:]')"
-  reviewer_lc="$(printf '%s' "$reviewer" | tr '[:upper:]' '[:lower:]')"
-  source_lc="$(printf '%s' "$source" | tr '[:upper:]' '[:lower:]')"
-  expected_reviewer_lc="$(printf '%s' "$expected_reviewer" | tr '[:upper:]' '[:lower:]')"
-  expected_source_lc="$(printf '%s' "$expected_source" | tr '[:upper:]' '[:lower:]')"
-  p1_lc="$(printf '%s' "$p1_blockers" | tr '[:upper:]' '[:lower:]')"
-
-  if [[ "$acceptance_lc" != "pass" ]]; then
-    printf 'fail\t%s\t%s\tExternal acceptance is %s; expected pass from %s via %s.\n' "${reviewer:--}" "${source:--}" "${acceptance:-missing}" "$expected_reviewer" "$expected_source"
-    return 0
-  fi
-
-  if [[ "$reviewer_lc" != "$expected_reviewer_lc" ]]; then
-    printf 'fail\t%s\t%s\tExternal reviewer is %s; expected %s.\n' "${reviewer:--}" "${source:--}" "${reviewer:-missing}" "$expected_reviewer"
-    return 0
-  fi
-
-  if [[ "$source_lc" != "$expected_source_lc" ]]; then
-    printf 'fail\t%s\t%s\tExternal source is %s; expected %s.\n' "${reviewer:--}" "${source:--}" "${source:-missing}" "$expected_source"
-    return 0
-  fi
-
-  if [[ "$p1_lc" != "none" ]]; then
-    printf 'fail\t%s\t%s\tExternal acceptance has P1 blockers: %s\n' "${reviewer:--}" "${source:--}" "${p1_blockers:-missing}"
-    return 0
-  fi
-
-  printf 'pass\t%s\t%s\tExternal acceptance passed.\n' "$reviewer" "$source"
-}
-
-workflow_external_acceptance_pass() {
-  local review_file="${1:-}"
-  local expected_reviewer="${2:-}"
-  local row status
-
-  row="$(workflow_external_acceptance_status "$review_file" "$expected_reviewer")"
-  status="${row%%$'\t'*}"
-  [[ "$status" == "pass" || "$status" == "manual_override" ]]
-}
-
 workflow_checks_pass() {
   local checks_file="${1:-}"
   local contract_file="${2:-}"
-  local review_file="${3:-}"
-  local status source exit_code check_contract check_review
+  local status source exit_code check_contract
 
   if [[ -z "$checks_file" || ! -s "$checks_file" ]]; then
     echo "Structured checks file is missing or empty: ${checks_file:-"(none)"}"
@@ -1438,7 +1283,6 @@ workflow_checks_pass() {
     source="$(jq -r '.source // empty' "$checks_file" 2>/dev/null || true)"
     exit_code="$(jq -r '.exit_code // empty' "$checks_file" 2>/dev/null || true)"
     check_contract="$(jq -r '.contract.file // .contract // empty' "$checks_file" 2>/dev/null || true)"
-    check_review="$(jq -r '.review.file // .review // empty' "$checks_file" 2>/dev/null || true)"
 
     if [[ "$status" != "pass" ]]; then
       echo "Structured checks are not passing in $checks_file (status=${status:-missing})."
@@ -1456,10 +1300,6 @@ workflow_checks_pass() {
       echo "Structured checks are stale for contract ${check_contract:-missing}; expected $contract_file."
       return 1
     fi
-    if [[ -n "$review_file" && "$check_review" != "$review_file" ]]; then
-      echo "Structured checks are stale for review ${check_review:-missing}; expected $review_file."
-      return 1
-    fi
     return 0
   fi
 
@@ -1479,10 +1319,6 @@ workflow_checks_pass() {
     echo "Structured checks do not reference current contract $contract_file."
     return 1
   fi
-  if [[ -n "$review_file" ]] && ! grep -Fq "\"file\":\"$review_file\"" "$checks_file" && ! grep -Fq "\"file\": \"$review_file\"" "$checks_file"; then
-    echo "Structured checks do not reference current review $review_file."
-    return 1
-  fi
 }
 
 workflow_contract_allows_path() {
@@ -1512,7 +1348,7 @@ workflow_contract_allows_path() {
         section="allowed_paths"
         continue
         ;;
-      exit_criteria:|files_exist:|tests_pass:|commands_succeed:|files_contain:|artifacts_exist:|qa_scores:|manual_checks:)
+      exit_criteria:|files_exist:|tests_pass:|commands_succeed:|files_contain:|artifacts_exist:)
         section=""
         continue
         ;;

package/assets/hooks/post-tool-observer.sh

@@ -47,9 +47,15 @@ case "$tool_name" in
     ;;
 esac
 
-if [[ -n "${CODEX_SESSION_ID:-${CODEX_AGENT_NAME:-}}" ]] || [[ "$session_source" =~ [Cc]odex ]]; then
+# An event source is explicit evidence. Inherited host variables are only a
+# fallback for payloads that omit it, such as local compatibility shims.
+if [[ "$session_source" =~ [Cc]odex ]]; then
   host="codex"
-elif [[ -n "${CLAUDE_SESSION_ID:-${CLAUDE_AGENT_NAME:-}}" ]] || [[ "$session_source" =~ [Cc]laude ]]; then
+elif [[ "$session_source" =~ [Cc]laude ]]; then
+  host="claude"
+elif [[ -n "${CODEX_SESSION_ID:-${CODEX_AGENT_NAME:-}}" ]]; then
+  host="codex"
+elif [[ -n "${CLAUDE_SESSION_ID:-${CLAUDE_AGENT_NAME:-}}" ]]; then
   host="claude"
 fi
 

package/assets/hooks/pre-edit-guard.sh

@@ -79,17 +79,13 @@ is_workflow_surface_path() {
 
 edit_plan_gate_mode() {
   local mode="${FORGE_EDIT_PLAN_GATE:-}"
-  if [[ -z "$mode" ]]; then
-    mode="$(workflow_policy_get '.guards.edit_plan_gate' 'advice')"
-  fi
-  printf '%s' "$mode"
+  [[ -z "$mode" ]] && mode="$(workflow_policy_get '.guards.edit_plan_gate' 'advice')"
+  [[ "$mode" == "off" ]] && printf 'off' || printf 'advice'
 }
 
-# Edit-layer plan gate: the deterministic enforcement point for "no
-# implementation edits without an approved plan". The prompt layer only
-# advises (natural-language intent guessing is unreliable); this gate keys
-# off path + plan state. Modes: advice (default) | enforce | off, via
-# FORGE_EDIT_PLAN_GATE or policy .guards.edit_plan_gate.
+# Plan/spec lifecycle is Controller context, never write authorization. This
+# compatibility hook may advise; real enforcement remains path/private-surface,
+# authorization, lease and fencing boundaries.
 run_edit_plan_gate() {
   local mode gate_plan gate_status
   mode="$(edit_plan_gate_mode)"
@@ -99,31 +95,13 @@ run_edit_plan_gate() {
 
   if [[ ! -f "docs/spec.md" ]]; then
     echo "[SpecGuard] Implementation edit without docs/spec.md: $FILE_PATH"
-    if [[ "$mode" == "advice" ]]; then
-      echo "[SpecGuard] Advisory: run bash scripts/new-spec.sh and capture stable product intent."
-    else
-      hook_structured_error \
-        "SpecGuard" \
-        "Implementation edit to $FILE_PATH without docs/spec.md." \
-        "Run bash scripts/new-spec.sh and capture stable product intent before implementing." \
-        "missing_artifact"
-      exit 2
-    fi
+    echo "[SpecGuard] Advisory: capture stable product intent when it materially helps this change."
   fi
 
   gate_plan="$(get_active_plan || true)"
   if [[ -z "$gate_plan" || ! -f "$gate_plan" ]]; then
     echo "[PlanStatusGuard] No active plan covers implementation edit: $FILE_PATH"
-    if [[ "$mode" == "advice" ]]; then
-      echo "[PlanStatusGuard] Advisory: capture the approved plan with bash scripts/capture-plan.sh --slug <slug> --title <title> --status Approved --execute"
-    else
-      hook_structured_error \
-        "PlanStatusGuard" \
-        "Implementation edit to $FILE_PATH without an active plan." \
-        "Capture the approved planning output with bash scripts/capture-plan.sh --slug <slug> --title <title> --status Approved --execute, or set policy .guards.edit_plan_gate to advice/off for this repo." \
-        "missing_artifact"
-      exit 2
-    fi
+    echo "[PlanStatusGuard] Advisory: use a Plan only when ChatGPT has chosen staged/dependency coordination."
     return 0
   fi
 
@@ -131,16 +109,7 @@ run_edit_plan_gate() {
   case "$gate_status" in
     Draft|Annotating)
       echo "[PlanStatusGuard] Plan status is '$gate_status' in $gate_plan; implementation edit: $FILE_PATH"
-      if [[ "$mode" == "advice" ]]; then
-        echo "[PlanStatusGuard] Advisory: complete the annotation cycle and move the plan to Approved before implementation."
-      else
-        hook_structured_error \
-          "PlanStatusGuard" \
-          "Implementation edit to $FILE_PATH while plan status is $gate_status in $gate_plan." \
-          "Complete the annotation cycle and move the plan to Approved before implementation." \
-          "state_violation"
-        exit 2
-      fi
+      echo "[PlanStatusGuard] Advisory: this Plan is not execution-ready; ordinary Direct work remains independent."
       ;;
   esac
 }