fix(missions): a caller's own task does not inherit the recipe's done_when

A recipe's completion condition is a condition on the recipe's own task.
phases_for_create merged the recipe config under the caller's, so a phase
that supplied a different task and no condition inherited a condition
about work it was never given: research_and_code's coding phase carries
"an implementation for each INT-XX item in IMPLEMENTATION_BRIEF", and a
phase asked to write CHAIN.md failed on it, honestly, every time
(01a0c20d, 01a0c493). Decided from the caller's config before the merge
(afterwards a recipe task and a caller task look the same): caller task
+ no caller condition → the recipe's done_when/done_when_check are not
inherited. A caller condition is kept; a phase with neither keeps the
recipe's pair. Test fixture now carries a recipe task+condition.

Harness: the triage agreement line dedupes per skill and excludes skills
whose Trigger is not observable (always_inject is inlined). First live
datapoint, 01a0c493: for 'create CHAIN.md and commit' Jev's top picks
were workspace-repo-commit-protocol 0.63 / small-focused-commits 0.57;
the agent read code-review-checklist (~0) and nothing else.

Co-Authored-By: Claude Opus 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01WZb5A2kfVfjpdwSochkuHz

crates/cm-api/src/routes/missions.rs

@@ -206,7 +206,21 @@ fn phases_for_create(
                 })
                 .map(|rp| rp.config.clone())
                 .unwrap_or(Value::Null);
+            // Decided from the caller's config BEFORE the merge: afterwards a
+            // recipe task and a caller task are indistinguishable.
+            let caller_task = p
+                .config
+                .get("task")
+                .and_then(|t| t.as_str())
+                .is_some_and(|s| !s.trim().is_empty());
+            let caller_condition =
+                p.config.get("done_when").is_some() || p.config.get("done_when_check").is_some();
             let config = merge_config(base, p.config);
+            let config = if caller_task && !caller_condition {
+                drop_orphaned_condition(config, &p.kind, p.order_idx)
+            } else {
+                config
+            };
             // Say what this phase asked for that will not happen. A config key
             // nothing reads is silent by construction — `task` sat unread
             // through every mission until two phases with different tasks
@@ -221,6 +235,36 @@ fn phases_for_create(
         .collect()
 }
 
+/// A recipe's completion condition is a condition on the recipe's own task.
+/// When the caller supplied a different `task` and no condition of its own,
+/// keeping the recipe's `done_when` judges the phase against work it was
+/// never asked to do — `research_and_code`'s coding phase inherits "an
+/// implementation for each INT-XX item in IMPLEMENTATION_BRIEF", and a
+/// phase asked to write CHAIN.md fails on it, honestly, every time (missions
+/// 01a0c20d, 01a0c493). The condition and the check travel with the task
+/// they were written for; a phase with its own task gets its own, or none.
+///
+/// Called only when the caller supplied a task and no condition; the
+/// decision is made before the merge, where the two are still telling apart.
+fn drop_orphaned_condition(config: Value, kind: &str, order_idx: i32) -> Value {
+    let Value::Object(mut c) = config else { return config };
+    let dropped: Vec<&str> = ["done_when", "done_when_check"]
+        .into_iter()
+        .filter(|k| c.contains_key(*k))
+        .collect();
+    if !dropped.is_empty() {
+        eprintln!(
+            "phase {kind}[{order_idx}]: caller supplied its own task and no completion \
+             condition — the recipe's {} is NOT inherited (it describes the recipe's task)",
+            dropped.join("/")
+        );
+        for k in dropped {
+            c.remove(k);
+        }
+    }
+    Value::Object(c)
+}
+
 /// Shallow-merge `over` onto `base`, key by key.
 ///
 /// Shallow is deliberate: phase config is a flat settings bag, and a caller
@@ -1755,6 +1799,44 @@ mod tests {
         );
     }
 
+    /// A caller's own task does not inherit the recipe's condition; a
+    /// caller's own condition is kept; a phase with neither keeps the
+    /// recipe's pair as before.
+    #[test]
+    fn a_custom_task_does_not_inherit_the_recipes_done_when() {
+        let recipe = test_recipe();
+        let coding_has_condition = recipe
+            .phases
+            .iter()
+            .any(|p| p.kind == "coding" && p.config.get("done_when").is_some());
+        assert!(coding_has_condition, "the fixture must carry a recipe condition");
+        let phases = phases_for_create(
+            Some(&recipe),
+            vec![
+                PhaseSpec {
+                    kind: "coding".into(),
+                    order_idx: 1,
+                    config: serde_json::json!({"task": "write CHAIN.md"}),
+                },
+                PhaseSpec {
+                    kind: "coding".into(),
+                    order_idx: 2,
+                    config: serde_json::json!({"task": "write X", "done_when": "X exists"}),
+                },
+                PhaseSpec {
+                    kind: "coding".into(),
+                    order_idx: 3,
+                    config: Value::Null,
+                },
+            ],
+        );
+        assert!(phases[0].config.get("done_when").is_none(), "{:?}", phases[0].config);
+        assert_eq!(phases[1].config["done_when"], "X exists");
+        assert!(phases[2].config.get("done_when").is_some(), "{:?}", phases[2].config);
+        // The rest of the recipe's config still backfills the custom-task phase.
+        assert!(phases[0].config.get("loop").is_some());
+    }
+
     /// Omitting phases entirely takes the recipe's list wholesale.
     #[test]
     fn phases_default_to_the_recipe() {
@@ -1853,7 +1935,10 @@ mod tests {
                     order_idx: 1,
                     config: serde_json::json!({
                         "loop": "until_no_more_int_items",
-                        "commit_policy": "on_green_tests"
+                        "commit_policy": "on_green_tests",
+                        // The recipe's own task and the condition written for it.
+                        "task": "implement every INT-XX item",
+                        "done_when": "an implementation exists for each INT-XX item"
                     }),
                 },
             ],

scripts/verify-mission-delivery.sh

@@ -1246,12 +1246,21 @@ assert_skill_triage() { # <token> <mission> <label>
   # not expect. Only meaningful when the arm is a retrieval arm.
   agree=$(api "$token" GET "/api/missions/$mission/skill-use" | python3 -c '
 import json,sys
-d=json.load(sys.stdin); sk=d.get("skills") or []
+d=json.load(sys.stdin); rows=d.get("skills") or []
-if not sk or all(s.get("triage_p") is None for s in sk): print("n/a"); sys.exit()
+if not rows or all(s.get("triage_p") is None for s in rows): print("n/a"); sys.exit()
-def read(s): return s["trigger"].get("verdict") in ("pass",) if isinstance(s.get("trigger"),dict) else str(s.get("trigger")).startswith("pass")
+# One row per skill per phase: collapse to the skill, keeping any pass. Skills
-applies=[s for s in sk if (s.get("triage_p") or 0)>=0.5]
+# whose Trigger is not observable (always_inject, inlined) cannot be "not read".
-hit=sum(1 for s in applies if read(s)); read_unexpected=sum(1 for s in sk if read(s) and (s.get("triage_p") or 0)<0.5)
+by={}
-print(f"oracle says {len(applies)} of {len(sk)} delivered skills apply; agent read {hit} of those and {read_unexpected} it did not expect")' 2>/dev/null)
+for s in rows:
+    v=s["trigger"].get("verdict") if isinstance(s.get("trigger"),dict) else str(s.get("trigger"))
+    e=by.setdefault(s["skill"],{"p":s.get("triage_p") or 0,"read":False,"obs":False})
+    e["p"]=max(e["p"],s.get("triage_p") or 0)
+    if v=="pass": e["read"]=True
+    if v in ("pass","fail","not_applicable"): e["obs"]=True
+obs={k:v for k,v in by.items() if v["obs"]}
+applies=[k for k,v in obs.items() if v["p"]>=0.5]
+hit=[k for k in applies if obs[k]["read"]]; unexpected=[k for k,v in obs.items() if v["read"] and v["p"]<0.5]
+print(f"of {len(obs)} observable skills the oracle says {len(applies)} apply ({", ".join(applies) or "-"}); agent read {len(hit)} of those and {len(unexpected)} it did not expect ({", ".join(unexpected) or "-"})")' 2>/dev/null)
   case "$agree" in
     ""|n/a) pass "$label-triage: agreement n/a on this arm (no retrieval to compare against)" ;;
     *)      pass "$label-triage: $agree" ;;