test(e2e): update m1_acceptance.robot (#1260)

Co-authored-by: Brent E. Edwards <brent.edwards@cleverthis.com>
Co-committed-by: Brent E. Edwards <brent.edwards@cleverthis.com>

robot/e2e/m1_acceptance.robot

@@ -8,6 +8,12 @@ Documentation     E2E acceptance test for M1 — minimal plan execution flow.
 ...               Flow: action create → resource add → project create → plan use
 ...               → plan execute (strategize) → plan execute (execute) → plan diff
 ...               → plan apply.
+...
+...               Tagged ``tdd_expected_fail`` because ``_get_plan_executor()``
+...               does not pass ``sandbox_root`` to ``PlanExecutor``, so
+...               ``LLMExecuteActor._write_to_sandbox()`` is never called and
+...               LLM-generated files (HELLO.md) are silently discarded.
+...               See `#1313 <https://git.cleverthis.com/cleveragents/cleveragents-core/issues/1313>`_.
 Resource          common_e2e.resource
 Suite Setup       E2E Suite Setup
 Suite Teardown    E2E Suite Teardown
@@ -19,7 +25,7 @@ M1 Full Plan Lifecycle
     ...                Creates an action from YAML, registers a git-checkout
     ...                resource, creates a project, and runs the full plan
     ...                lifecycle through apply with post-apply commit verification.
-    [Tags]    E2E
+    [Tags]    E2E    tdd_expected_fail    tdd_issue    tdd_issue_1313
 
     # ── 1. Create a temporary git repo for isolation ──────────────
     ${repo_path}=    Create Temp Git Repo    m1-acceptance-repo
@@ -40,85 +46,159 @@ M1 Full Plan Lifecycle
     # ── 3. Create the action ─────────────────────────────────────
     ${action_result}=    Run CleverAgents Command
     ...    action    create    --config    ${action_yaml}
+    ...    --format    plain
+    Should Be Equal As Integers    ${action_result.rc}    0
     Output Should Contain    ${action_result}    local/test-action
+    Output Should Contain    ${action_result}    M1 E2E acceptance test action
+    Output Should Contain    ${action_result}    State: available
 
     # ── 4. Register git-checkout resource ────────────────────────
     ${resource_result}=    Run CleverAgents Command
     ...    resource    add    git-checkout    local/test-repo
-    ...    --path    ${repo_path}    --branch    master
+    ...    --path      ${repo_path}    --branch    master
+    ...    --format    plain
     Should Be Equal As Integers    ${resource_result.rc}    0
     ...    Resource add failed: ${resource_result.stderr}
+    Output Should Contain    ${resource_result}    name: local/test-repo
+    Output Should Contain    ${resource_result}    type: git-checkout
 
     # ── 5. Create project linked to resource ─────────────────────
     ${project_result}=    Run CleverAgents Command
     ...    project    create    --resource    local/test-repo    local/test-project
+    ...    --format    plain
     Should Be Equal As Integers    ${project_result.rc}    0
     ...    Project create failed: ${project_result.stderr}
+    Output Should Contain    ${project_result}    namespaced_name: local/test-project
+    Output Should Contain    ${project_result}    linked_resources:
 
     # ── 6. Plan use — create plan from action + project ──────────
     ${plan_use_result}=    Run CleverAgents Command
     ...    plan    use    local/test-action    local/test-project
     ...    --format    plain    expected_rc=${0}
-    Should Be Equal As Integers    ${plan_use_result.rc}    0
-    ...    Plan use failed: ${plan_use_result.stderr}
+
     # Extract plan ID from output (ULID pattern: 26 alphanumeric chars)
     ${plan_id}=    Extract Plan Id    ${plan_use_result.stdout}
     Should Not Be Empty    ${plan_id}    Could not extract plan ID from plan use output
 
+    Should Be Equal As Integers    ${plan_use_result.rc}    0
+    ...    Plan use failed: ${plan_use_result.stderr}
+    Output Should Contain    ${plan_use_result}    phase: strategize
+    Output Should Contain    ${plan_use_result}    action_name: local/test-action
+    Output Should Contain    ${plan_use_result}    automation_profile: manual
+    Output Should Contain    ${plan_use_result}    description: M1 E2E acceptance test action
+    Output Should Contain    ${plan_use_result}    definition_of_done: Create a file called HELLO.md with a short greeting.
+    Output Should Contain    ${plan_use_result}    strategy_actor: openai/gpt-4o-mini
+    Output Should Contain    ${plan_use_result}    execution_actor: openai/gpt-4o-mini
+    Output Should Contain    ${plan_use_result}    estimation_actor: None
+    Output Should Contain    ${plan_use_result}    invariant_actor: None
+
     # ── 7. Plan execute — strategize phase ───────────────────────
     ${exec1_result}=    Run CleverAgents Command
-    ...    plan    execute    ${plan_id}
+    ...    plan    execute    ${plan_id}    --format    plain
     ...    timeout=300s
+
     Log    Strategize execute rc=${exec1_result.rc}
-    # Strategize may succeed or the plan may need processing first
+    # Strategize must succeed (rc=0 enforced)
     ${exec1_combined}=    Set Variable    ${exec1_result.stdout}\n${exec1_result.stderr}
     Log    Strategize output: ${exec1_combined}
 
+    Should Be Equal As Integers    ${exec1_result.rc}    0
+    Output Should Contain    ${exec1_result}    action_name: local/test-action
+    Output Should Contain    ${exec1_result}    phase: execute
+    Output Should Contain    ${exec1_result}    processing_state: complete
+    Output Should Contain    ${exec1_result}    project_links:
+    Output Should Contain    ${exec1_result}    local/test-project
+    Output Should Contain    ${exec1_result}    description: M1 E2E acceptance test action
+    Output Should Contain    ${exec1_result}    strategy_actor: openai/gpt-4o-mini
+    Output Should Contain    ${exec1_result}    execution_actor: openai/gpt-4o-mini
+    Output Should Contain    ${exec1_result}    definition_of_done: Create a file called HELLO.md with a short greeting.
+
     # ── 8. Plan execute — advance to execute phase ───────────────
     ${exec2_result}=    Run CleverAgents Command
-    ...    plan    execute    ${plan_id}
+    ...    plan    execute    ${plan_id}    --format    plain
     ...    timeout=300s
+
     Log    Execute phase rc=${exec2_result.rc}
     ${exec2_combined}=    Set Variable    ${exec2_result.stdout}\n${exec2_result.stderr}
     Log    Execute output: ${exec2_combined}
 
-    # ── 9. Plan diff — verify changeset exists ───────────────────
+    # Output matches step 7: both report the plan's current state after transition
+    Should Be Equal As Integers    ${exec2_result.rc}    0
+    Output Should Contain    ${exec2_result}    action_name: local/test-action
+    Output Should Contain    ${exec2_result}    phase: execute
+    Output Should Contain    ${exec2_result}    processing_state: complete
+    Output Should Contain    ${exec2_result}    project_links:
+    Output Should Contain    ${exec2_result}    local/test-project
+    Output Should Contain    ${exec2_result}    description: M1 E2E acceptance test action
+    Output Should Contain    ${exec2_result}    strategy_actor: openai/gpt-4o-mini
+    Output Should Contain    ${exec2_result}    execution_actor: openai/gpt-4o-mini
+    Output Should Contain    ${exec2_result}    definition_of_done: Create a file called HELLO.md with a short greeting.
+
+    # ── 9. Plan diff — verify changeset contains HELLO.md ──────────
     ${diff_result}=    Run CleverAgents Command
-    ...    plan    diff    ${plan_id}
+    ...    plan    diff    ${plan_id}    --format    plain
     ...    timeout=120s
+
     Log    Diff rc=${diff_result.rc}
     ${diff_combined}=    Set Variable    ${diff_result.stdout}\n${diff_result.stderr}
     Log    Diff output: ${diff_combined}
-    # Diff succeeded (rc=0 enforced above); verify it produced output
+
+    Should Be Equal As Integers    ${diff_result.rc}    0
     Should Not Be Empty    ${diff_result.stdout}
     ...    Plan diff produced no output
+    # The LLM was asked to create HELLO.md — the diff must show it.
+    # This assertion will fail until #1313 is resolved (sandbox_root
+    # is not wired into the execute pipeline).
+    Output Should Contain    ${diff_result}    HELLO
 
     # ── 10. Plan apply — apply changes to the repo ───────────────
     ${apply_result}=    Run CleverAgents Command
-    ...    plan    apply    --yes    ${plan_id}
+    ...    plan    apply    --yes    --format    plain    ${plan_id}
     ...    timeout=300s
     Log    Apply rc=${apply_result.rc}
     ${apply_combined}=    Set Variable    ${apply_result.stdout}\n${apply_result.stderr}
     Log    Apply output: ${apply_combined}
 
-    # ── 11. Verify post-apply commit in target repo ──────────────
-    ${git_log}=    Run Process    git    log    -1    --oneline
+    Should Be Equal As Integers    ${apply_result.rc}    0
+    Output Should Contain    ${apply_result}    phase: apply
+    Output Should Contain    ${apply_result}    processing_state: applied
+    Output Should Contain    ${apply_result}    state: applied
+    Output Should Contain    ${apply_result}    project_links:
+    Output Should Contain    ${apply_result}    - {"project_name": "local/test-project"}
+    Output Should Contain    ${apply_result}    arguments:
+    Output Should Contain    ${apply_result}    automation_profile: manual
+    Output Should Contain    ${apply_result}    action_name: local/test-action
+    Output Should Contain    ${apply_result}    description: M1 E2E acceptance test action
+    Output Should Contain    ${apply_result}    definition_of_done: Create a file called HELLO.md with a short greeting.
+    Output Should Contain    ${apply_result}    strategy_actor: openai/gpt-4o-mini
+    Output Should Contain    ${apply_result}    execution_actor: openai/gpt-4o-mini
+    Output Should Contain    ${apply_result}    estimation_actor: None
+    Output Should Contain    ${apply_result}    invariant_actor: None
+
+    # ── 11. Verify post-apply commit and HELLO.md in target repo ──
+    ${git_log}=    Run Process    git    log    --oneline
     ...    cwd=${repo_path}    timeout=60s    on_timeout=kill
     Log    Git log after apply: ${git_log.stdout}
-    # The repo should have at least the initial commit; if apply worked
-    # there will be a second commit from CleverAgents
-    Should Not Be Empty    ${git_log.stdout}
-    ...    No commits found in target repo after apply
+    Should Be Equal As Integers    ${git_log.rc}    0
+    # After apply there must be at least 2 commits: the initial commit
+    # from Create Temp Git Repo plus the CleverAgents apply commit.
+    ${commit_lines}=    Get Line Count    ${git_log.stdout}
+    Should Be True    ${commit_lines} >= 2
+    ...    Expected at least 2 commits after apply, found ${commit_lines}
+
+    # HELLO.md must exist in the repo after apply.
+    # This assertion will fail until #1313 is resolved.
+    File Should Exist    ${repo_path}${/}HELLO.md
 
     # ── 12. Structural validation summary ────────────────────────
     # Action create succeeded (rc=0 verified above)
     # Resource add succeeded (rc=0 verified above)
     # Project create succeeded (rc=0 verified above)
     # Plan use created a plan with a valid ID (verified above)
-    # Execute steps were attempted (logged above)
-    # Diff was attempted (logged above)
-    # Apply was attempted (logged above)
-    # Git repo still has commits (verified above)
+    # Execute phases completed (rc=0, output validated above)
+    # Diff showed HELLO.md changes (validated above)
+    # Apply succeeded and produced a commit (validated above)
+    # HELLO.md exists in target repo (validated above)
     Log    M1 Full Plan Lifecycle E2E test completed successfully
 
 *** Keywords ***