From 7c7a171c8d8a5af7d3cccb186614830d214dd85f Mon Sep 17 00:00:00 2001
From: Story Crater Bot <19826264+Riotpiaole@users.noreply.github.com>
Date: Wed, 19 Aug 2026 13:16:03 -0700
Subject: [PATCH] fix(agent-pod): committed progress ledger so resume skips
 done tasks

Resuming the phase branch alone only recovers the code -- the task loop
still walked from the first task, re-verifying every already-done one
through a full planner call before reaching the first task that actually
needed work. .agent-progress is committed (not gitignored) and appended
per completed task, so a resumed run reads it once and skips straight
past known-done tasks with zero LLM calls. Validated locally against a
throwaway repo: second run skipped both tasks instantly (resumed: true)
instead of re-running planner on them.
---
 k8s/apps/agent-pod/coordinator-configmap.yaml | 42 +++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/k8s/apps/agent-pod/coordinator-configmap.yaml b/k8s/apps/agent-pod/coordinator-configmap.yaml
index 2eb5069..04324da 100644
--- a/k8s/apps/agent-pod/coordinator-configmap.yaml
+++ b/k8s/apps/agent-pod/coordinator-configmap.yaml
@@ -469,6 +469,36 @@ data:
       }
     }
     
+    // Committed (never gitignored) so it survives a resumed phase branch --
+    // one task id per line, appended as each task resolves. This is what lets
+    // a resumed run skip straight past already-resolved tasks instead of
+    // re-running planner's judgeOnly decision on every one of them again:
+    // resuming the git branch alone only recovers the CODE, not "which tasks
+    // are already settled," and re-deciding that from scratch for every task
+    // burns a full LLM call per already-done task before ever reaching the
+    // first one that actually needs work.
+    function progressLedgerPath(cwd) {
+      return path.join(cwd, ".agent-progress");
+    }
+    
+    function readCompletedTasks(cwd) {
+      const file = progressLedgerPath(cwd);
+      if (!fs.existsSync(file)) return new Set();
+      return new Set(
+        fs
+          .readFileSync(file, "utf8")
+          .split("\n")
+          .map((line) => line.trim())
+          .filter(Boolean)
+      );
+    }
+    
+    async function recordTaskComplete(cwd, task) {
+      fs.appendFileSync(progressLedgerPath(cwd), `${task}\n`);
+      await runGit(cwd, ["add", path.basename(progressLedgerPath(cwd))]);
+      await runGit(cwd, ["commit", "-m", `chore: mark ${task} complete in progress ledger`]);
+    }
+    
     // Runs every task in a phase (no declared dependency between them) strictly
     // one at a time against the repo's shared role pool -- only one implementer/
     // judge/etc. exists per repo, so there is no per-task concurrency to have
@@ -485,9 +515,21 @@ data:
     // from a clone that never saw any of that work.
     async function runPhase(cwd, baseBranch, phaseBranch, phaseTasks, pool, repoId, pipelineSession) {
       const entries = phaseTasks.map((t) => (typeof t === "string" ? { id: t, judgeOnly: false } : t));
+      const completed = readCompletedTasks(cwd);
+    
       for (const entry of entries) {
+        if (completed.has(entry.id)) {
+          const result = { task: entry.id, status: "done", resumed: true };
+          pipelineSession.taskResults.push(result);
+          logProgress(pipelineSession);
+          continue;
+        }
+    
         const result = await runTaskOnPool(cwd, baseBranch, entry.id, pool, repoId, pipelineSession, entry.judgeOnly);
         pipelineSession.taskResults.push(result);
+        if (result.status === "done" || result.status === "done-with-concerns") {
+          await recordTaskComplete(cwd, entry.id);
+        }
         await runGit(cwd, ["push", "-u", "origin", phaseBranch]);
         logProgress(pipelineSession);
       }