007af498b8
CI / benchmark-publish (pull_request) Has been skipped
CI / build (pull_request) Successful in 17s
CI / helm (pull_request) Successful in 33s
CI / lint (pull_request) Successful in 3m42s
CI / security (pull_request) Successful in 4m8s
CI / quality (pull_request) Successful in 4m9s
CI / typecheck (pull_request) Successful in 4m20s
CI / integration_tests (pull_request) Successful in 7m2s
CI / unit_tests (pull_request) Successful in 7m55s
CI / docker (pull_request) Successful in 1m19s
CI / coverage (pull_request) Successful in 8m46s
CI / e2e_tests (pull_request) Successful in 16m1s
CI / status-check (pull_request) Successful in 1s
CI / build (push) Successful in 17s
CI / helm (push) Successful in 22s
CI / quality (push) Successful in 31s
CI / lint (push) Successful in 3m28s
CI / typecheck (push) Successful in 3m54s
CI / benchmark-regression (push) Has been skipped
CI / security (push) Successful in 4m5s
CI / integration_tests (push) Successful in 6m13s
CI / unit_tests (push) Successful in 6m28s
CI / docker (push) Successful in 1m34s
CI / coverage (push) Successful in 12m5s
CI / e2e_tests (push) Successful in 18m47s
CI / status-check (push) Successful in 1s
CI / benchmark-publish (push) Successful in 28m0s
CI / benchmark-regression (pull_request) Successful in 59m48s
Renamed all 11 task-type confidence threshold fields in AutomationProfile from phase-transition semantics to spec-defined task-type semantics. Updated all 8 built-in profiles, CLI formatting, YAML schema, services, and all Behave/Robot tests referencing the old field names. Post-review fixes: - Fixed 24 stale old field names in M6 fixture files (automation_profiles.json, autonomy_guardrails.json) - Added model_validator(mode='before') to detect legacy field names and raise actionable ValueError with rename mapping - Added semantic bridge comments in PlanLifecycleService mapping task-type thresholds to phase-transition gates - Added threshold_field to structured log messages for observability - Restored categorised CLI automation-profile show output to match spec (Phase Transitions / Decision Automation / Self-Repair / Execution Controls) instead of flat list - Added missing access_network field to spec show output examples (Rich, Plain, JSON, YAML variants) - Aligned ADR-017 profile fields table to all 11 fields with descriptions matching spec Automatable Tasks table - Aligned automation_profiles.md threshold descriptions with spec - Added spec section references in phase_reversion.md, error_recovery.md, and plan_execute.md for field naming context - Extended repository roundtrip test to assert all 11 threshold fields - Fixed benchmark _make_profile() passing safety fields as top-level kwargs instead of via SafetyProfile sub-model (incompatible with extra="forbid") - Aligned CLI JSON/YAML output structure for automation-profile show with the specification grouped format (phase_transitions, decision_automation, self_repair, execution_controls) - Moved safety boolean fields into the Execution Controls section of Rich output per spec examples - Reverted auto profile description to "Fully automatic except apply" per specification (line 16703, line 28406) - Improved bridge comments in test steps with semantic context for threshold-to-gate mappings ISSUES CLOSED: #902
73 lines
3.8 KiB
Plaintext
73 lines
3.8 KiB
Plaintext
*** Settings ***
|
||
Documentation Integration test for WF03 plan prompt and confidence-threshold
|
||
... pausing verification.
|
||
...
|
||
... Exercises:
|
||
... - plan prompt via the A2A facade (§15822)
|
||
... - confidence-threshold pausing with the cautious profile
|
||
... (§37262–37367) where confidence < 0.6 causes escalation
|
||
... - pause-and-resume flow: low-confidence decision triggers
|
||
... pause, then plan prompt guidance resumes execution
|
||
...
|
||
... References:
|
||
... - Issue #961 (AC1: plan prompt, AC2: confidence-threshold)
|
||
... - Spec §15822–15931 (plan prompt command)
|
||
... - Spec §37262–37367 (WF03 cautious profile flow)
|
||
Resource ${CURDIR}/common.resource
|
||
Suite Setup Setup Test Environment
|
||
Suite Teardown Cleanup Test Environment
|
||
Force Tags wf03 v3.4.0 integration plan-prompt confidence
|
||
|
||
*** Variables ***
|
||
${HELPER} ${CURDIR}/helper_wf03_plan_prompt_confidence.py
|
||
|
||
*** Test Cases ***
|
||
WF03 Plan Prompt Via Facade
|
||
[Documentation] Exercise ``plan prompt`` via the A2A facade dispatch
|
||
... path. Sends guidance for a plan and verifies the
|
||
... facade returns a stub ``guidance_injected`` response
|
||
... with the correct plan ID. (§15822)
|
||
[Tags] plan-prompt facade
|
||
${result}= Run Process ${PYTHON} ${HELPER} plan-prompt-facade cwd=${WORKSPACE} timeout=120s on_timeout=kill
|
||
Log ${result.stdout}
|
||
Log ${result.stderr}
|
||
Should Be Equal As Integers ${result.rc} 0
|
||
Should Contain ${result.stdout} wf03-plan-prompt-ok
|
||
|
||
WF03 Confidence Threshold Pausing
|
||
[Documentation] Verify that the cautious profile pauses execution when
|
||
... a strategy decision has confidence below the threshold
|
||
... (0.6 for ``edit_code``). Seeds factors
|
||
... producing confidence 0.55 and asserts ``proceed=False``.
|
||
[Tags] confidence cautious threshold
|
||
${result}= Run Process ${PYTHON} ${HELPER} confidence-threshold-pausing cwd=${WORKSPACE} timeout=120s on_timeout=kill
|
||
Log ${result.stdout}
|
||
Log ${result.stderr}
|
||
Should Be Equal As Integers ${result.rc} 0
|
||
Should Contain ${result.stdout} wf03-confidence-pause-ok
|
||
|
||
WF03 Confidence Threshold Proceeds
|
||
[Documentation] Verify that the cautious profile proceeds when a strategy
|
||
... decision has confidence above the threshold. Seeds factors
|
||
... producing confidence 0.85 and asserts ``proceed=True``.
|
||
[Tags] confidence cautious threshold
|
||
${result}= Run Process ${PYTHON} ${HELPER} confidence-threshold-proceeds cwd=${WORKSPACE} timeout=120s on_timeout=kill
|
||
Log ${result.stdout}
|
||
Log ${result.stderr}
|
||
Should Be Equal As Integers ${result.rc} 0
|
||
Should Contain ${result.stdout} wf03-confidence-proceed-ok
|
||
|
||
WF03 Pause And Resume Via Plan Prompt
|
||
[Documentation] End-to-end flow: seed a plan with a low-confidence
|
||
... decision, verify it pauses, then provide guidance via
|
||
... ``plan prompt`` and verify the system accepts the
|
||
... guidance (stub path). This covers the WF03 scenario
|
||
... from §37262–37367 where the user corrects a paused
|
||
... decision by providing guidance.
|
||
[Tags] plan-prompt confidence cautious pause-resume
|
||
${result}= Run Process ${PYTHON} ${HELPER} pause-and-resume cwd=${WORKSPACE} timeout=120s on_timeout=kill
|
||
Log ${result.stdout}
|
||
Log ${result.stderr}
|
||
Should Be Equal As Integers ${result.rc} 0
|
||
Should Contain ${result.stdout} wf03-pause-resume-ok
|