oh-my-opencode 4.18.1 → 4.18.2

package/packages/omo-codex/plugin/components/ultrawork/directive.md

@@ -105,9 +105,7 @@ notepad with a one-line reason each. Skipping a skill that fits the
 task is a defect. Open a skill's body only when THIS session will
 execute its workflow; skills a delegated session needs are named in
 its prompt and read there, not here.
-Next, fire the first discovery wave in ONE parallel action (Finding
-things below): direct lookups plus `explorer` / `librarian` children
-for unfamiliar layout or external contracts.
+Next, fire the first discovery wave under Finding things below.
 Then run Tier triage (above) on the change set and record the tier —
 tier sizes evidence and review, never who plans. Size planning by
 what the wave left UNDECIDED, not by how many steps you can list:
@@ -207,25 +205,27 @@ GOOD pair (test-first, ordered):
 BAD: "Implement feature" / "Fix bug" / "Add tests later" / writing
 production code before its failing test → rewrite.
 
-# Finding things (lead with these, parallel-flood the first wave)
+# Finding things (lead with these, code-mode the first wave)
 Never guess from memory — locate with the right tool, and re-read before
-you claim or change. Fire 3+ independent lookups in one action;
-serialize only when one output strictly feeds the next.
-- CodeGraph, when `codegraph_*` tools exist -> use `codegraph_explore`
-  first for how/where/what/flow questions and before edits; if absent,
-  inactive/uninitialized, or cold-start unavailable, keep moving with
-  Read/Grep/Glob/LSP and the ast-grep skill.
-- Repo-wide inspection, CLI smoke tests, git/history, bounded command
-  output → use native shell commands directly: `rg`, `rg --files`,
-  `cat`, and `git`. Narrow huge output before reading it.
-- Symbols — definitions, references, rename impact, diagnostics →
-  `lsp_goto_definition`, `lsp_find_references`, `lsp_symbols`,
-  `lsp_diagnostics`. Use the LSP, not text search, for anything
-  symbol-shaped.
-- Structural shapes — call/function/class/import patterns, codemods →
-  the `ast-grep` skill or `sg` CLI with `$VAR` / `$$$` metavars.
-- Text / strings / comments / logs → `rg`. File-name discovery →
-  `glob` / `find`. Verbatim content → `read`.
+you claim or change. **USE CODE MODE AGGRESSIVELY FOR BOUNDED WAVES.**
+When multiple independent tool calls produce results that can be materially
+filtered, joined, deduplicated, or reduced, make ONE `exec` / eval JavaScript
+program that calls eligible tools concurrently with `Promise.all` and emits only
+decision-relevant evidence. For shell-native repo work without programmatic
+tool access, use ONE Python script with `concurrent.futures`, `subprocess`,
+and utility functions to batch commands and reduce output. Keep direct calls
+when one result chooses the next action, outputs are already small, semantic
+judgment is required between calls, approval or side effects are involved,
+or native artifacts / citations must be preserved.
+- Architecture / flow / blast radius → `codegraph_explore` first when
+  `codegraph_*` exists; if unavailable, continue with repo tools and LSP.
+- **SYMBOLS REQUIRE LSP** — definitions, references, rename impact,
+  workspace symbols, and diagnostics use the available `lsp_*` tools, not
+  text search. Run diagnostics after edits and treat errors as blocking.
+- Repo text / filenames / history / bounded shell output → `rg`,
+  `rg --files`, `git`, and native utilities; narrow output in-program.
+- Structural call / function / class / import shapes and codemods → the
+  `ast-grep` skill or `sg` with `$VAR` / `$$$` metavariables.
 When discovery needs multiple angles or the module layout is
 unfamiliar, delegate to the `explorer` subagent (read-only codebase
 search, absolute-path results). For research that leaves the repo —
@@ -289,21 +289,39 @@ Until every success criterion PASSES with its evidence captured:
    vars. Append a one-line cleanup receipt to the notepad next to the
    artifact, e.g. `cleanup: killed 12345; tmux kill-session ulw-qa-foo;
    rm -rf /tmp/ulw.aB12cD`. No receipt → criterion stays in_progress.
-6. Verify: LSP diagnostics clean on changed files + full test suite
-   green (no skipped, no xfail added this turn).
+6. Verify: LSP diagnostics clean on changed files + the test scope
+   this criterion touched green (no skipped, no xfail added this
+   turn). Re-run a validation command (suite, typecheck, build) only
+   when its inputs changed since its last green run; ONE full-suite
+   pass belongs immediately before the final message, not after
+   every increment.
 7. Mark completed. Append non-obvious findings / learnings.
-8. After each increment, re-run every criterion's scenario. Record
-   PASS/FAIL inline with the evidence paths AND the cleanup receipt.
-   Loop until all PASS.
-
-Parallel-batch independent reads / searches / subagents within a step,
-but NEVER parallelise RED and GREEN of the same criterion.
+8. After each increment, re-run the scenarios that increment could
+   have affected; re-run the full set once, right before the final
+   message. Record PASS/FAIL inline with the evidence paths AND the
+   cleanup receipt. Loop until all PASS.
+
+Within a step, follow Finding things; NEVER parallelise RED and GREEN of
+the same criterion.
+
+# Waiting discipline (a poll costs a full model round)
+Every status check you issue as a tool call replays the entire
+accumulated context through the model. When a command will run long
+(installs, builds, test suites, containers, CI), run it to completion
+in ONE call with a timeout sized to the expected duration, or send
+output to a log file and read it once when a completion signal is
+expected. Never re-poll the same surface with empty reads or
+sub-minute waits — batch waiting into the fewest, longest blocking
+calls the harness allows, and do independent root work while the
+command runs. If two consecutive checks show no state change, double
+the wait before the next check or switch to a completion signal.
 
 # Codex subagent reliability
 Every `multi_agent_v1.spawn_agent` message is self-contained and starts with
-`TASK: <imperative assignment>`, then names `DELIVERABLE`, `SCOPE`, and
-`VERIFY`. State that it is an executable assignment, not a context
-handoff. Use `fork_context: false` unless full history is truly
+`TASK: <imperative assignment>`, then names `DELIVERABLE`, `SCOPE`,
+`VERIFY`, and `STOP WHEN` — the observable condition that ends the
+child's run; a child without a stop condition wanders past its goal.
+State that it is an executable assignment, not a context handoff. Use `fork_context: false` unless full history is truly
 required; paste only the context the child needs. Full-history forks can
 make the child continue old parent context instead of the delegated task.
 If your tool list has a flat `spawn_agent` with a required `task_name` instead of `multi_agent_v1.*` (`multi_agent_v2`), rewrite: `fork_context: false` becomes `fork_turns: "none"`, `send_input` becomes `send_message`, finished agents end on their own (no `close_agent`; `followup_task` re-tasks, `interrupt_agent` stops), and `wait_agent` takes only `timeout_ms`, returning on any child mailbox activity.
@@ -413,7 +431,6 @@ message + present for approval.
 - Never suppress lints / errors / test failures. Never delete, skip,
   `.only`, `.skip`, `xfail`, or comment out tests to green the suite.
 - Never claim done from inference — only from captured evidence.
-- Parallel tool calls for any independent work.
 
 # Output discipline
 - First line literally: `ULTRAWORK MODE ENABLED!`

package/packages/omo-codex/plugin/components/ultrawork/hooks/hooks.json

@@ -7,7 +7,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook user-prompt-submit",
 						"timeout": 5,
-						"statusMessage": "(OmO 4.18.1) Checking Ultrawork Trigger"
+						"statusMessage": "(OmO 4.18.2) Checking Ultrawork Trigger"
 					}
 				]
 			}

package/packages/omo-codex/plugin/components/ultrawork/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@code-yeongyu/codex-ultrawork",
-	"version": "4.18.1",
+	"version": "4.18.2",
 	"description": "Codex plugin that injects the ultrawork orchestration directive and ships LazyCodex planning, review, QA, and gate agent roles.",
 	"type": "module",
 	"packageManager": "npm@11.12.1",

package/packages/omo-codex/plugin/components/ultrawork/skills/ultrawork/SKILL.md

@@ -112,9 +112,7 @@ notepad with a one-line reason each. Skipping a skill that fits the
 task is a defect. Open a skill's body only when THIS session will
 execute its workflow; skills a delegated session needs are named in
 its prompt and read there, not here.
-Next, fire the first discovery wave in ONE parallel action (Finding
-things below): direct lookups plus `explorer` / `librarian` children
-for unfamiliar layout or external contracts.
+Next, fire the first discovery wave under Finding things below.
 Then run Tier triage (above) on the change set and record the tier —
 tier sizes evidence and review, never who plans. Size planning by
 what the wave left UNDECIDED, not by how many steps you can list:
@@ -214,25 +212,27 @@ GOOD pair (test-first, ordered):
 BAD: "Implement feature" / "Fix bug" / "Add tests later" / writing
 production code before its failing test → rewrite.
 
-# Finding things (lead with these, parallel-flood the first wave)
+# Finding things (lead with these, code-mode the first wave)
 Never guess from memory — locate with the right tool, and re-read before
-you claim or change. Fire 3+ independent lookups in one action;
-serialize only when one output strictly feeds the next.
-- CodeGraph, when `codegraph_*` tools exist -> use `codegraph_explore`
-  first for how/where/what/flow questions and before edits; if absent,
-  inactive/uninitialized, or cold-start unavailable, keep moving with
-  Read/Grep/Glob/LSP and the ast-grep skill.
-- Repo-wide inspection, CLI smoke tests, git/history, bounded command
-  output → use native shell commands directly: `rg`, `rg --files`,
-  `cat`, and `git`. Narrow huge output before reading it.
-- Symbols — definitions, references, rename impact, diagnostics →
-  `lsp_goto_definition`, `lsp_find_references`, `lsp_symbols`,
-  `lsp_diagnostics`. Use the LSP, not text search, for anything
-  symbol-shaped.
-- Structural shapes — call/function/class/import patterns, codemods →
-  the `ast-grep` skill or `sg` CLI with `$VAR` / `$$$` metavars.
-- Text / strings / comments / logs → `rg`. File-name discovery →
-  `glob` / `find`. Verbatim content → `read`.
+you claim or change. **USE CODE MODE AGGRESSIVELY FOR BOUNDED WAVES.**
+When multiple independent tool calls produce results that can be materially
+filtered, joined, deduplicated, or reduced, make ONE `exec` / eval JavaScript
+program that calls eligible tools concurrently with `Promise.all` and emits only
+decision-relevant evidence. For shell-native repo work without programmatic
+tool access, use ONE Python script with `concurrent.futures`, `subprocess`,
+and utility functions to batch commands and reduce output. Keep direct calls
+when one result chooses the next action, outputs are already small, semantic
+judgment is required between calls, approval or side effects are involved,
+or native artifacts / citations must be preserved.
+- Architecture / flow / blast radius → `codegraph_explore` first when
+  `codegraph_*` exists; if unavailable, continue with repo tools and LSP.
+- **SYMBOLS REQUIRE LSP** — definitions, references, rename impact,
+  workspace symbols, and diagnostics use the available `lsp_*` tools, not
+  text search. Run diagnostics after edits and treat errors as blocking.
+- Repo text / filenames / history / bounded shell output → `rg`,
+  `rg --files`, `git`, and native utilities; narrow output in-program.
+- Structural call / function / class / import shapes and codemods → the
+  `ast-grep` skill or `sg` with `$VAR` / `$$$` metavariables.
 When discovery needs multiple angles or the module layout is
 unfamiliar, delegate to the `explorer` subagent (read-only codebase
 search, absolute-path results). For research that leaves the repo —
@@ -296,21 +296,39 @@ Until every success criterion PASSES with its evidence captured:
    vars. Append a one-line cleanup receipt to the notepad next to the
    artifact, e.g. `cleanup: killed 12345; tmux kill-session ulw-qa-foo;
    rm -rf /tmp/ulw.aB12cD`. No receipt → criterion stays in_progress.
-6. Verify: LSP diagnostics clean on changed files + full test suite
-   green (no skipped, no xfail added this turn).
+6. Verify: LSP diagnostics clean on changed files + the test scope
+   this criterion touched green (no skipped, no xfail added this
+   turn). Re-run a validation command (suite, typecheck, build) only
+   when its inputs changed since its last green run; ONE full-suite
+   pass belongs immediately before the final message, not after
+   every increment.
 7. Mark completed. Append non-obvious findings / learnings.
-8. After each increment, re-run every criterion's scenario. Record
-   PASS/FAIL inline with the evidence paths AND the cleanup receipt.
-   Loop until all PASS.
-
-Parallel-batch independent reads / searches / subagents within a step,
-but NEVER parallelise RED and GREEN of the same criterion.
+8. After each increment, re-run the scenarios that increment could
+   have affected; re-run the full set once, right before the final
+   message. Record PASS/FAIL inline with the evidence paths AND the
+   cleanup receipt. Loop until all PASS.
+
+Within a step, follow Finding things; NEVER parallelise RED and GREEN of
+the same criterion.
+
+# Waiting discipline (a poll costs a full model round)
+Every status check you issue as a tool call replays the entire
+accumulated context through the model. When a command will run long
+(installs, builds, test suites, containers, CI), run it to completion
+in ONE call with a timeout sized to the expected duration, or send
+output to a log file and read it once when a completion signal is
+expected. Never re-poll the same surface with empty reads or
+sub-minute waits — batch waiting into the fewest, longest blocking
+calls the harness allows, and do independent root work while the
+command runs. If two consecutive checks show no state change, double
+the wait before the next check or switch to a completion signal.
 
 # Codex subagent reliability
 Every `multi_agent_v1.spawn_agent` message is self-contained and starts with
-`TASK: <imperative assignment>`, then names `DELIVERABLE`, `SCOPE`, and
-`VERIFY`. State that it is an executable assignment, not a context
-handoff. Use `fork_context: false` unless full history is truly
+`TASK: <imperative assignment>`, then names `DELIVERABLE`, `SCOPE`,
+`VERIFY`, and `STOP WHEN` — the observable condition that ends the
+child's run; a child without a stop condition wanders past its goal.
+State that it is an executable assignment, not a context handoff. Use `fork_context: false` unless full history is truly
 required; paste only the context the child needs. Full-history forks can
 make the child continue old parent context instead of the delegated task.
 If your tool list has a flat `spawn_agent` with a required `task_name` instead of `multi_agent_v1.*` (`multi_agent_v2`), rewrite: `fork_context: false` becomes `fork_turns: "none"`, `send_input` becomes `send_message`, finished agents end on their own (no `close_agent`; `followup_task` re-tasks, `interrupt_agent` stops), and `wait_agent` takes only `timeout_ms`, returning on any child mailbox activity.
@@ -420,7 +438,6 @@ message + present for approval.
 - Never suppress lints / errors / test failures. Never delete, skip,
   `.only`, `.skip`, `xfail`, or comment out tests to green the suite.
 - Never claim done from inference — only from captured evidence.
-- Parallel tool calls for any independent work.
 
 # Output discipline
 - First line literally: `ULTRAWORK MODE ENABLED!`

package/packages/omo-codex/plugin/components/ulw-loop/directive.md

@@ -105,9 +105,7 @@ notepad with a one-line reason each. Skipping a skill that fits the
 task is a defect. Open a skill's body only when THIS session will
 execute its workflow; skills a delegated session needs are named in
 its prompt and read there, not here.
-Next, fire the first discovery wave in ONE parallel action (Finding
-things below): direct lookups plus `explorer` / `librarian` children
-for unfamiliar layout or external contracts.
+Next, fire the first discovery wave under Finding things below.
 Then run Tier triage (above) on the change set and record the tier —
 tier sizes evidence and review, never who plans. Size planning by
 what the wave left UNDECIDED, not by how many steps you can list:
@@ -207,25 +205,27 @@ GOOD pair (test-first, ordered):
 BAD: "Implement feature" / "Fix bug" / "Add tests later" / writing
 production code before its failing test → rewrite.
 
-# Finding things (lead with these, parallel-flood the first wave)
+# Finding things (lead with these, code-mode the first wave)
 Never guess from memory — locate with the right tool, and re-read before
-you claim or change. Fire 3+ independent lookups in one action;
-serialize only when one output strictly feeds the next.
-- CodeGraph, when `codegraph_*` tools exist -> use `codegraph_explore`
-  first for how/where/what/flow questions and before edits; if absent,
-  inactive/uninitialized, or cold-start unavailable, keep moving with
-  Read/Grep/Glob/LSP and the ast-grep skill.
-- Repo-wide inspection, CLI smoke tests, git/history, bounded command
-  output → use native shell commands directly: `rg`, `rg --files`,
-  `cat`, and `git`. Narrow huge output before reading it.
-- Symbols — definitions, references, rename impact, diagnostics →
-  `lsp_goto_definition`, `lsp_find_references`, `lsp_symbols`,
-  `lsp_diagnostics`. Use the LSP, not text search, for anything
-  symbol-shaped.
-- Structural shapes — call/function/class/import patterns, codemods →
-  the `ast-grep` skill or `sg` CLI with `$VAR` / `$$$` metavars.
-- Text / strings / comments / logs → `rg`. File-name discovery →
-  `glob` / `find`. Verbatim content → `read`.
+you claim or change. **USE CODE MODE AGGRESSIVELY FOR BOUNDED WAVES.**
+When multiple independent tool calls produce results that can be materially
+filtered, joined, deduplicated, or reduced, make ONE `exec` / eval JavaScript
+program that calls eligible tools concurrently with `Promise.all` and emits only
+decision-relevant evidence. For shell-native repo work without programmatic
+tool access, use ONE Python script with `concurrent.futures`, `subprocess`,
+and utility functions to batch commands and reduce output. Keep direct calls
+when one result chooses the next action, outputs are already small, semantic
+judgment is required between calls, approval or side effects are involved,
+or native artifacts / citations must be preserved.
+- Architecture / flow / blast radius → `codegraph_explore` first when
+  `codegraph_*` exists; if unavailable, continue with repo tools and LSP.
+- **SYMBOLS REQUIRE LSP** — definitions, references, rename impact,
+  workspace symbols, and diagnostics use the available `lsp_*` tools, not
+  text search. Run diagnostics after edits and treat errors as blocking.
+- Repo text / filenames / history / bounded shell output → `rg`,
+  `rg --files`, `git`, and native utilities; narrow output in-program.
+- Structural call / function / class / import shapes and codemods → the
+  `ast-grep` skill or `sg` with `$VAR` / `$$$` metavariables.
 When discovery needs multiple angles or the module layout is
 unfamiliar, delegate to the `explorer` subagent (read-only codebase
 search, absolute-path results). For research that leaves the repo —
@@ -289,21 +289,39 @@ Until every success criterion PASSES with its evidence captured:
    vars. Append a one-line cleanup receipt to the notepad next to the
    artifact, e.g. `cleanup: killed 12345; tmux kill-session ulw-qa-foo;
    rm -rf /tmp/ulw.aB12cD`. No receipt → criterion stays in_progress.
-6. Verify: LSP diagnostics clean on changed files + full test suite
-   green (no skipped, no xfail added this turn).
+6. Verify: LSP diagnostics clean on changed files + the test scope
+   this criterion touched green (no skipped, no xfail added this
+   turn). Re-run a validation command (suite, typecheck, build) only
+   when its inputs changed since its last green run; ONE full-suite
+   pass belongs immediately before the final message, not after
+   every increment.
 7. Mark completed. Append non-obvious findings / learnings.
-8. After each increment, re-run every criterion's scenario. Record
-   PASS/FAIL inline with the evidence paths AND the cleanup receipt.
-   Loop until all PASS.
-
-Parallel-batch independent reads / searches / subagents within a step,
-but NEVER parallelise RED and GREEN of the same criterion.
+8. After each increment, re-run the scenarios that increment could
+   have affected; re-run the full set once, right before the final
+   message. Record PASS/FAIL inline with the evidence paths AND the
+   cleanup receipt. Loop until all PASS.
+
+Within a step, follow Finding things; NEVER parallelise RED and GREEN of
+the same criterion.
+
+# Waiting discipline (a poll costs a full model round)
+Every status check you issue as a tool call replays the entire
+accumulated context through the model. When a command will run long
+(installs, builds, test suites, containers, CI), run it to completion
+in ONE call with a timeout sized to the expected duration, or send
+output to a log file and read it once when a completion signal is
+expected. Never re-poll the same surface with empty reads or
+sub-minute waits — batch waiting into the fewest, longest blocking
+calls the harness allows, and do independent root work while the
+command runs. If two consecutive checks show no state change, double
+the wait before the next check or switch to a completion signal.
 
 # Codex subagent reliability
 Every `multi_agent_v1.spawn_agent` message is self-contained and starts with
-`TASK: <imperative assignment>`, then names `DELIVERABLE`, `SCOPE`, and
-`VERIFY`. State that it is an executable assignment, not a context
-handoff. Use `fork_context: false` unless full history is truly
+`TASK: <imperative assignment>`, then names `DELIVERABLE`, `SCOPE`,
+`VERIFY`, and `STOP WHEN` — the observable condition that ends the
+child's run; a child without a stop condition wanders past its goal.
+State that it is an executable assignment, not a context handoff. Use `fork_context: false` unless full history is truly
 required; paste only the context the child needs. Full-history forks can
 make the child continue old parent context instead of the delegated task.
 If your tool list has a flat `spawn_agent` with a required `task_name` instead of `multi_agent_v1.*` (`multi_agent_v2`), rewrite: `fork_context: false` becomes `fork_turns: "none"`, `send_input` becomes `send_message`, finished agents end on their own (no `close_agent`; `followup_task` re-tasks, `interrupt_agent` stops), and `wait_agent` takes only `timeout_ms`, returning on any child mailbox activity.
@@ -413,7 +431,6 @@ message + present for approval.
 - Never suppress lints / errors / test failures. Never delete, skip,
   `.only`, `.skip`, `xfail`, or comment out tests to green the suite.
 - Never claim done from inference — only from captured evidence.
-- Parallel tool calls for any independent work.
 
 # Output discipline
 - First line literally: `ULTRAWORK MODE ENABLED!`

package/packages/omo-codex/plugin/components/ulw-loop/dist/cli.js

@@ -2943,7 +2943,7 @@ function boulderContinuationWillFire(cwd, sessionId) {
       const entry = work;
       const sessionIds = Array.isArray(entry["session_ids"]) ? entry["session_ids"] : [];
       const continuable = entry["status"] === "active" || entry["status"] === "paused";
-      return continuable && sessionIds.includes(`codex:${sessionId}`) && boulderPlanHasRemainingTask(cwd, entry);
+      return continuable && sessionIds.includes(`codex:${sessionId}`) && boulderPlanHasChecklist(cwd, entry);
     });
   } catch (error) {
     if (error instanceof Error)
@@ -2961,7 +2961,7 @@ function transcriptShowsContextPressure(transcriptPath) {
     throw error;
   }
 }
-function boulderPlanHasRemainingTask(cwd, entry) {
+function boulderPlanHasChecklist(cwd, entry) {
   const activePlan = entry["active_plan"];
   if (typeof activePlan !== "string" || activePlan.trim().length === 0)
     return false;
@@ -2970,7 +2970,7 @@ function boulderPlanHasRemainingTask(cwd, entry) {
   const candidates = typeof worktree === "string" && worktree.trim().length > 0 && !isAbsolute2(activePlan) ? [join3(isAbsolute2(worktree) ? worktree : join3(cwd, worktree), activePlan), planPath] : [planPath];
   for (const candidate of candidates) {
     try {
-      return readFileSync4(candidate, "utf8").split(/\r?\n/).some((line) => line.startsWith("- [ ] "));
+      return readFileSync4(candidate, "utf8").split(/\r?\n/).some((line) => line.startsWith("- [ ] ") || line.startsWith("- [x] ") || line.startsWith("- [X] "));
     } catch (error) {
       if (!(error instanceof Error))
         throw error;

package/packages/omo-codex/plugin/components/ulw-loop/dist/stop-resume-hook.js

@@ -139,7 +139,7 @@ function boulderContinuationWillFire(cwd, sessionId) {
             const entry = work;
             const sessionIds = Array.isArray(entry["session_ids"]) ? entry["session_ids"] : [];
             const continuable = entry["status"] === "active" || entry["status"] === "paused";
-            return continuable && sessionIds.includes(`codex:${sessionId}`) && boulderPlanHasRemainingTask(cwd, entry);
+            return continuable && sessionIds.includes(`codex:${sessionId}`) && boulderPlanHasChecklist(cwd, entry);
         });
     }
     catch (error) {
@@ -159,10 +159,9 @@ function transcriptShowsContextPressure(transcriptPath) {
         throw error;
     }
 }
-// start-work-continuation only fires while its plan checklist has remaining
-// items; a boulder work whose plan is exhausted (or unreadable) leaves the
-// Stop event to this hook.
-function boulderPlanHasRemainingTask(cwd, entry) {
+// start-work-continuation owns an active Boulder plan until its final gate marks
+// the work complete, including the zero-remaining checklist state.
+function boulderPlanHasChecklist(cwd, entry) {
     const activePlan = entry["active_plan"];
     if (typeof activePlan !== "string" || activePlan.trim().length === 0)
         return false;
@@ -175,7 +174,7 @@ function boulderPlanHasRemainingTask(cwd, entry) {
         try {
             return readFileSync(candidate, "utf8")
                 .split(/\r?\n/)
-                .some((line) => line.startsWith("- [ ] "));
+                .some((line) => line.startsWith("- [ ] ") || line.startsWith("- [x] ") || line.startsWith("- [X] "));
         }
         catch (error) {
             if (!(error instanceof Error))

package/packages/omo-codex/plugin/components/ulw-loop/hooks/hooks.json

@@ -7,7 +7,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook user-prompt-submit --with-ultrawork",
 						"timeout": 10,
-						"statusMessage": "(OmO 4.18.1) Checking Ulw-Loop Steering"
+						"statusMessage": "(OmO 4.18.2) Checking Ulw-Loop Steering"
 					}
 				]
 			}
@@ -20,7 +20,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook pre-tool-use",
 						"timeout": 5,
-						"statusMessage": "(OmO 4.18.1) Enforcing Unlimited Ulw-Loop Budget"
+						"statusMessage": "(OmO 4.18.2) Enforcing Unlimited Ulw-Loop Budget"
 					}
 				]
 			},
@@ -31,7 +31,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook pre-tool-use-spawn",
 						"timeout": 5,
-						"statusMessage": "(OmO 4.18.1) Guarding Ulw-Loop Spawns"
+						"statusMessage": "(OmO 4.18.2) Guarding Ulw-Loop Spawns"
 					}
 				]
 			}
@@ -43,7 +43,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook stop",
 						"timeout": 10,
-						"statusMessage": "(OmO 4.18.1) Checking Ulw-Loop Resume"
+						"statusMessage": "(OmO 4.18.2) Checking Ulw-Loop Resume"
 					}
 				]
 			}

package/packages/omo-codex/plugin/components/ulw-loop/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@code-yeongyu/codex-ulw-loop",
-	"version": "4.18.1",
+	"version": "4.18.2",
 	"description": "Codex plugin: durable repo-native multi-goal orchestration with embedded success criteria and observable evidence audit.",
 	"type": "module",
 	"packageManager": "npm@11.12.1",

package/packages/omo-codex/plugin/components/ulw-loop/skills/ulw-loop/references/full-workflow.md

@@ -187,7 +187,7 @@ Trigger only for the final aggregate goal after every criterion in every goal is
 2. FREEZE first — no more edits or rebases. At the frozen HEAD, re-run Manual-QA for any PASS criterion whose stamped tree differs from `git rev-parse --short "HEAD^{tree}"`, so every criterion is proven on the frozen tree; each artifact exists and is non-empty.
 3a. Spawn lazycodex-code-reviewer and lazycodex-qa-executor in parallel (`fork_context: false` on v1; `fork_turns: "none"` on v2) with brief, goals, desired outcome, diff, evidence; wait for BOTH and confirm their report artifacts exist on disk.
 3b. Only then spawn lazycodex-gate-reviewer with those artifact paths.
-3c. The gate's approval binds to the frozen tree and covers its three lanes — code quality, hands-on QA, and goal verification. A later rebase or amend that keeps the tree identical keeps the approval; changed content needs fresh review of the delta.
+3c. The gate's approval binds to the frozen tree and full commit SHA and covers its three lanes — code quality, hands-on QA, and goal verification. Immediately append one durable `.omo/ulw-loop/ledger.jsonl` record per passing lane with the lane name, full SHA, verdict, and report artifact/source. Before reuse after continuation or compaction, re-read the ledger and require the exact lane/SHA pair; memory or an unstamped report is not coverage. A later rebase or amend that keeps the tree identical still has a new SHA and needs fresh lane stamps; changed content needs fresh review of the delta.
 4. Treat timeout, missing deliverable, ack-only, `BLOCKED:`, or inconclusive review as a blocker. Any fix restarts the freeze at the new HEAD: re-run ONLY the proofs it invalidated and stamp the fresh output — never regenerate all evidence or relabel stale output to HEAD — re-review the delta at most TWICE; then record-review-blockers (step 5) and surface to the user.
 5. If review remains blocked, run `omo ulw-loop record-review-blockers --goal-id <id> --title "<...>" --objective "<...>" --evidence "<review findings>" --codex-goal-json <snapshot> --json`.
 6. If clean, checkpoint final completion:

package/packages/omo-codex/plugin/components/ulw-loop/src/stop-resume-hook.ts

@@ -142,7 +142,7 @@ function boulderContinuationWillFire(cwd: string, sessionId: string): boolean {
 			const entry = work as Record<string, unknown>;
 			const sessionIds = Array.isArray(entry["session_ids"]) ? entry["session_ids"] : [];
 			const continuable = entry["status"] === "active" || entry["status"] === "paused";
-			return continuable && sessionIds.includes(`codex:${sessionId}`) && boulderPlanHasRemainingTask(cwd, entry);
+			return continuable && sessionIds.includes(`codex:${sessionId}`) && boulderPlanHasChecklist(cwd, entry);
 		});
 	} catch (error) {
 		if (error instanceof Error) return false;
@@ -160,10 +160,9 @@ function transcriptShowsContextPressure(transcriptPath: string): boolean {
 	}
 }
 
-// start-work-continuation only fires while its plan checklist has remaining
-// items; a boulder work whose plan is exhausted (or unreadable) leaves the
-// Stop event to this hook.
-function boulderPlanHasRemainingTask(cwd: string, entry: Record<string, unknown>): boolean {
+// start-work-continuation owns an active Boulder plan until its final gate marks
+// the work complete, including the zero-remaining checklist state.
+function boulderPlanHasChecklist(cwd: string, entry: Record<string, unknown>): boolean {
 	const activePlan = entry["active_plan"];
 	if (typeof activePlan !== "string" || activePlan.trim().length === 0) return false;
 	const planPath = isAbsolute(activePlan) ? activePlan : join(cwd, activePlan);
@@ -176,7 +175,7 @@ function boulderPlanHasRemainingTask(cwd: string, entry: Record<string, unknown>
 		try {
 			return readFileSync(candidate, "utf8")
 				.split(/\r?\n/)
-				.some((line) => line.startsWith("- [ ] "));
+				.some((line) => line.startsWith("- [ ] ") || line.startsWith("- [x] ") || line.startsWith("- [X] "));
 		} catch (error) {
 			if (!(error instanceof Error)) throw error;
 		}

package/packages/omo-codex/plugin/components/ulw-loop/test/stop-resume-hook.test.ts

@@ -110,7 +110,7 @@ describe("runStopResumeHook", () => {
 		expect(runStopResumeHook(stopPayload())).toBe("");
 	});
 
-	it("#given an active boulder work whose plan is exhausted #when the hook runs #then resumes instead of deferring", () => {
+	it("#given an active boulder work whose plan is exhausted #when the hook runs #then defers to the final gate continuation", () => {
 		writeGoals([pendingGoal()]);
 		const plan = writeBoulderPlan(false);
 		writeFileSync(
@@ -118,7 +118,7 @@ describe("runStopResumeHook", () => {
 			JSON.stringify({ works: { w1: { session_ids: ["codex:s1"], status: "active", active_plan: plan } } }),
 		);
 
-		expect(JSON.parse(runStopResumeHook(stopPayload())).decision).toBe("block");
+		expect(runStopResumeHook(stopPayload())).toBe("");
 	});
 
 	it("#given a flat legacy boulder work with remaining plan tasks #when the hook runs #then still defers", () => {

package/packages/omo-codex/plugin/hooks/post-compact-resetting-git-bash-mcp-reminder.json

@@ -7,7 +7,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/components/git-bash/dist/cli.js\" hook post-compact",
 						"timeout": 5,
-						"statusMessage": "(OmO 4.18.1) Resetting Git Bash MCP Reminder",
+						"statusMessage": "(OmO 4.18.2) Resetting Git Bash MCP Reminder",
 						"commandWindows": "powershell -NoProfile -ExecutionPolicy Bypass -File \"${PLUGIN_ROOT}\\components\\bootstrap\\scripts\\node-dispatch.ps1\" \"${PLUGIN_ROOT}\\components\\git-bash\\dist\\cli.js\" hook post-compact"
 					}
 				],

package/packages/omo-codex/plugin/hooks/post-compact-resetting-lsp-diagnostics-cache.json

@@ -7,7 +7,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/components/lsp/dist/cli.js\" hook post-compact",
 						"timeout": 5,
-						"statusMessage": "(OmO 4.18.1) Resetting LSP Diagnostics Cache",
+						"statusMessage": "(OmO 4.18.2) Resetting LSP Diagnostics Cache",
 						"commandWindows": "powershell -NoProfile -ExecutionPolicy Bypass -File \"${PLUGIN_ROOT}\\components\\bootstrap\\scripts\\node-dispatch.ps1\" \"${PLUGIN_ROOT}\\components\\lsp\\dist\\cli.js\" hook post-compact"
 					}
 				],

package/packages/omo-codex/plugin/hooks/post-compact-resetting-project-rule-cache.json

@@ -7,7 +7,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/components/rules/dist/cli.js\" hook post-compact",
 						"timeout": 10,
-						"statusMessage": "(OmO 4.18.1) Resetting Project Rule Cache",
+						"statusMessage": "(OmO 4.18.2) Resetting Project Rule Cache",
 						"commandWindows": "powershell -NoProfile -ExecutionPolicy Bypass -File \"${PLUGIN_ROOT}\\components\\bootstrap\\scripts\\node-dispatch.ps1\" \"${PLUGIN_ROOT}\\components\\rules\\dist\\cli.js\" hook post-compact"
 					}
 				],

package/packages/omo-codex/plugin/hooks/post-tool-use-checking-codegraph-init-guidance.json

@@ -7,7 +7,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/components/codegraph/dist/cli.js\" hook post-tool-use",
 						"timeout": 5,
-						"statusMessage": "(OmO 4.18.1) Checking CodeGraph Init Guidance",
+						"statusMessage": "(OmO 4.18.2) Checking CodeGraph Init Guidance",
 						"commandWindows": "powershell -NoProfile -ExecutionPolicy Bypass -File \"${PLUGIN_ROOT}\\components\\bootstrap\\scripts\\node-dispatch.ps1\" \"${PLUGIN_ROOT}\\components\\codegraph\\dist\\cli.js\" hook post-tool-use"
 					}
 				],

package/packages/omo-codex/plugin/hooks/post-tool-use-checking-comments.json

@@ -7,7 +7,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/components/comment-checker/dist/cli.js\" hook post-tool-use",
 						"timeout": 30,
-						"statusMessage": "(OmO 4.18.1) Checking Comments",
+						"statusMessage": "(OmO 4.18.2) Checking Comments",
 						"commandWindows": "powershell -NoProfile -ExecutionPolicy Bypass -File \"${PLUGIN_ROOT}\\components\\bootstrap\\scripts\\node-dispatch.ps1\" \"${PLUGIN_ROOT}\\components\\comment-checker\\dist\\cli.js\" hook post-tool-use"
 					}
 				],

package/packages/omo-codex/plugin/hooks/post-tool-use-checking-lsp-diagnostics.json

@@ -7,7 +7,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/components/lsp/dist/cli.js\" hook post-tool-use",
 						"timeout": 60,
-						"statusMessage": "(OmO 4.18.1) Checking LSP Diagnostics",
+						"statusMessage": "(OmO 4.18.2) Checking LSP Diagnostics",
 						"commandWindows": "powershell -NoProfile -ExecutionPolicy Bypass -File \"${PLUGIN_ROOT}\\components\\bootstrap\\scripts\\node-dispatch.ps1\" \"${PLUGIN_ROOT}\\components\\lsp\\dist\\cli.js\" hook post-tool-use"
 					}
 				],