test(issue-21): h25 pins the revised env contract - with env flags the idle pane is skipped and the env rides on the pane-creation call

Review N1 (planner-reviewer-claude-01 50ae9fb0, planner-reviewer-codex-01
8779f4b4): af8a54c (R1) stopped reusing an idle pane when env flags are
present, because the old path put `env K=V ...` after `herdr agent start ...
--`, where herdr passes it to the agent executable as arguments. h25 still
required that old behaviour (idle pane reused, env in the agent command) and
failed. It now asserts the new contract instead: a pane split / workspace
create carries MY_TEST_FLAG=active and HERDR_WORKSPACE_ID as --env, the agent
does not land on the idle pane, and nothing env-like follows `--` in agent
start. Finding A's intent (env must not be silently lost) is kept; reuse
without env flags stays pinned by h24. No product code changes.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017R3Eg7MEpSWnm1oB9ZPP6G

tests/test_herdr_shim_contract.py

@@ -516,10 +516,13 @@ def test_h24_new_session_reuses_idle_pane_without_split(mam_sandbox, mock_herdr,
     assert not split_calls, f"Expected no pane split call when an idle pane was available: {split_calls}"
 
 
-def test_h25_new_session_idle_pane_preserves_env_and_ws_id(mam_sandbox, mock_herdr, mock_agents):
-    """Finding A: when an idle pane is reused, caller-provided KEY=VAL environment
-    flags (and HERDR_WORKSPACE_ID) must be prepended via env to final_cmd so they
-    are not silently lost when pane split / workspace create is bypassed."""
+def test_h25_new_session_with_env_flags_skips_the_idle_pane_and_uses_env_on_split(mam_sandbox, mock_herdr, mock_agents):
+    """Finding A, revised for Issue #21 R1: caller-provided KEY=VAL environment
+    flags (and HERDR_WORKSPACE_ID) must not be silently lost - and must not be
+    put after `agent start --` either, because herdr passes those tokens to the
+    agent executable (--kind) as arguments. With env flags an idle pane is not
+    reused; the env rides on the pane-creation call (pane split / workspace
+    create --env). Reuse without env flags stays covered by h24."""
     tmp_path = mam_sandbox
     state = _load_mock_state(mock_herdr)
     state["panes"] = [{
@@ -538,17 +541,22 @@ def test_h25_new_session_idle_pane_preserves_env_and_ws_id(mam_sandbox, mock_her
     assert res.returncode == 0, f"Stderr: {res.stderr}\nStdout: {res.stdout}"
 
     final_state = _load_mock_state(mock_herdr)
-    agents = final_state.get("agents", {})
-    matched = [d for n, d in agents.items() if "test-creator-claude" in n]
-    assert matched, agents
-    assert matched[0].get("pane_id") == "w1:p_idle"
-    cmd = matched[0].get("command", "")
-    assert "MY_TEST_FLAG=active" in cmd, f"Expected MY_TEST_FLAG=active in agent command: {cmd}"
-    assert "HERDR_WORKSPACE_ID=w1" in cmd, f"Expected HERDR_WORKSPACE_ID=w1 in agent command: {cmd}"
+    # the shim may prefix `--session <name>`; compare the subcommands themselves
+    new_calls = [c[2:] if c[:1] == ["--session"] else c for c in final_state.get("calls", [])[n_calls:]]
+    creates = [c for c in new_calls if c[:2] in (["pane", "split"], ["workspace", "create"])]
+    assert creates, f"expected a pane split / workspace create carrying the env: {new_calls}"
+    env_vals = [c[i + 1] for c in creates for i, t in enumerate(c[:-1]) if t == "--env"]
+    assert "MY_TEST_FLAG=active" in env_vals and "HERDR_WORKSPACE_ID=w1" in env_vals, env_vals
 
-    new_calls = final_state.get("calls", [])[n_calls:]
-    split_calls = [c for c in new_calls if len(c) >= 2 and c[0] == "pane" and c[1] == "split"]
-    assert not split_calls, f"Expected no pane split call when an idle pane was available: {split_calls}"
+    matched = [d for n, d in final_state.get("agents", {}).items() if "test-creator-claude" in n]
+    assert matched and matched[0].get("pane_id") != "w1:p_idle", matched
+
+    starts = [c for c in new_calls if c[:2] == ["agent", "start"]]
+    assert starts, new_calls
+    for c in starts:
+        args = c[c.index("--") + 1:] if "--" in c else []
+        assert "env" not in args, args
+        assert not any(a.startswith(("MY_TEST_FLAG=", "HERDR_WORKSPACE_ID=")) for a in args), args
 
 
 def test_h26_daemon_spawn_uses_process_group_detachment(mam_sandbox, mock_herdr, mock_agents):