Release v0.5.1

Author: dgilperez

CHANGELOG.md

@@ -5,6 +5,12 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.5.1] - 2026-03-20
+
+### Fixed
+- Claude stop hook now resolves its real source path before loading shared helpers, so symlinked installs under `~/.claude/hooks/stop-hook.sh` no longer fail with missing helper-library errors
+- Added regression coverage for running the stop hook through a symlinked install path
+
 ## [0.5.0] - 2026-03-20
 
 ### Added
@@ -109,6 +115,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Multi-language support in MEASURE phase (Elixir, Python, JavaScript, Ruby, Go)
 - Simultaneous multi-KPI completion gate
 
+[0.5.1]: https://github.com/DjinnFoundry/forge-loop/releases/tag/v0.5.1
 [0.5.0]: https://github.com/DjinnFoundry/forge-loop/releases/tag/v0.5.0
 [0.4.2]: https://github.com/DjinnFoundry/forge-loop/releases/tag/v0.4.2
 [0.4.1]: https://github.com/DjinnFoundry/forge-loop/releases/tag/v0.4.1

README.md

@@ -21,7 +21,7 @@
 **Forge Core with first-class drivers for [Claude Code](https://docs.anthropic.com/en/docs/claude-code) and Codex/manual workflows.**
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
-[![Version](https://img.shields.io/badge/version-0.5.0-green.svg)](CHANGELOG.md)
+[![Version](https://img.shields.io/badge/version-0.5.1-green.svg)](CHANGELOG.md)
 
 Forge is a protocol plus adapters. The protocol defines task success, KPI guardrails, state, strategy rotation, evaluation cadence, and completion rules. The bundled drivers make that protocol run inside Claude Code and Codex/manual workflows.
 
@@ -73,7 +73,7 @@ The bundled Codex/manual adapter in this repo:
 - `.codex/forge/` state layout for per-project sessions
 - shared shell state helpers reused across drivers
 
-Both drivers are first-class in `v0.5.0`. The difference is automation depth:
+Both drivers are first-class in `v0.5.1`. The difference is automation depth:
 Claude gets hook-driven iteration; Codex gets manual driver scripts that print
 the next prompt and manage session state.
 
@@ -85,7 +85,7 @@ the next prompt and manage session state.
 | Codex CLI | First-class manual driver | Install script, `forge-init`, `forge-continue`, `forge-cancel`, project-local state |
 | Other agents / plain shell | Protocol-only | Reuse the protocol and state model manually |
 
-Forge is not claiming native parity across agent runtimes. `v0.5.0` ships two real drivers with different control surfaces.
+Forge is not claiming native parity across agent runtimes. `v0.5.1` ships two real drivers with different control surfaces.
 
 ---
 

VERSION

@@ -1 +1 @@
-0.5.0
+0.5.1

hooks/stop-hook.sh

@@ -7,7 +7,18 @@
 
 set -euo pipefail
 
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+SOURCE_PATH="${BASH_SOURCE[0]}"
+while [[ -L "$SOURCE_PATH" ]]; do
+  LINK_DIR="$(cd "$(dirname "$SOURCE_PATH")" && pwd)"
+  TARGET_PATH="$(readlink "$SOURCE_PATH")"
+  if [[ "$TARGET_PATH" == /* ]]; then
+    SOURCE_PATH="$TARGET_PATH"
+  else
+    SOURCE_PATH="${LINK_DIR}/${TARGET_PATH}"
+  fi
+done
+
+SCRIPT_DIR="$(cd "$(dirname "$SOURCE_PATH")" && pwd)"
 source "${SCRIPT_DIR}/../scripts/forge-state-lib.sh"
 
 # Read hook input from stdin

skills/forge/SKILL.md

@@ -49,7 +49,7 @@ Forge has two layers:
 - **Success contract** — task objective plus explicit or derived completion checks
 - **Driver** — runtime-specific integration that launches the loop, persists state, and handles pause/continue mechanics
 
-`v0.5.0` ships two first-class drivers:
+`v0.5.1` ships two first-class drivers:
 
 - **Claude Code** — command, agent, and stop-hook integration are bundled here
 - **Codex** — `forge-init`, `forge-continue`, `forge-cancel`, and `forge-status` manage a manual loop with project-local state

tests/stop-hook.test.sh

@@ -84,6 +84,21 @@ run_hook() {
     | (cd "${repo_dir}" && bash "${HOOK_PATH}")
 }
 
+run_hook_via_symlink() {
+  local repo_dir="$1"
+  local install_dir
+  install_dir="$(mktemp -d)"
+  mkdir -p "${install_dir}/hooks"
+  ln -s "${HOOK_PATH}" "${install_dir}/hooks/stop-hook.sh"
+
+  local output
+  output="$(printf '{"transcript_path":"%s"}\n' "${repo_dir}/transcript.jsonl" \
+    | (cd "${repo_dir}" && bash "${install_dir}/hooks/stop-hook.sh"))"
+
+  rm -rf "${install_dir}"
+  printf '%s' "$output"
+}
+
 with_repo() {
   local test_name="$1"
   local repo_dir
@@ -202,6 +217,18 @@ test_exact_promise_marker_finishes() {
   fi
 }
 
+test_symlinked_hook_resolves_helper_library() {
+  local repo_dir="$1"
+  write_state "${repo_dir}" "true" "1" "null"
+  write_transcript "${repo_dir}" "regular output"
+
+  local output
+  output="$(run_hook_via_symlink "${repo_dir}")"
+
+  assert_contains "$output" '"decision": "block"' "symlinked hook should still continue the loop"
+  assert_equals "2" "$(state_field "${repo_dir}" "iteration")" "symlinked hook should increment iteration"
+}
+
 main() {
   with_repo test_regular_output_continues
   with_repo test_embedded_complete_marker_does_not_finish
@@ -211,6 +238,7 @@ main() {
   with_repo test_paused_loops_stay_paused
   with_repo test_embedded_promise_marker_does_not_finish
   with_repo test_exact_promise_marker_finishes
+  with_repo test_symlinked_hook_resolves_helper_library
 
   echo "stop-hook tests passed"
 }