d8add7e8cb
Replace freeform prompt_template output with validated AgentConfig JSON: - agent_setup.py: new system prompt (journey_system_v2), AGENT_CONFIG_START/END markers, _extract_agent_config() with Pydantic validation, updated handlers returning agent_config key; import AgentConfig from schemas - tests/test_journey_v2.py: 6 unit tests + 5 parametrized LLM eval cases following test_agent_runner_v2.py pattern; _run_journey uses set_client_executor/clear_client_executor mirroring device_ws - tests/fixtures/journey_v2/: cases.yaml + email_action.html + email_info.html - tests/conftest.py: add --journey-dir CLI option; remove S3/plugin fixtures (cleanup from microservices migration, already present in working tree) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
88 lines
3.4 KiB
YAML
88 lines
3.4 KiB
YAML
# Journey V2 eval test cases — Step 4
|
|
#
|
|
# Each case simulates a complete journey session:
|
|
# 1. handle_journey_start is called with directory + data_types
|
|
# 2. handle_journey_message is called for each entry in user_messages
|
|
# 3. Assertions are evaluated on the final reply
|
|
#
|
|
# directory_files: list of {path, content_file} — content_file is relative to data/
|
|
#
|
|
# Assertion keys:
|
|
# expect_question: true → first reply must contain "?"
|
|
# expect_done: true → final reply must have done=True
|
|
# expect_valid_config: true → agent_config must be parseable as AgentConfig with content_types > 0
|
|
# expect_content_type_id: <str> → AgentConfig.content_types must contain an entry with this id
|
|
# expect_extraction_contains: <str> → first content_type extraction_prompt must contain this word
|
|
# expect_global_rules: true → AgentConfig.global_rules must be non-empty
|
|
|
|
- id: "4.1"
|
|
description: "Journey start explores directory, first reply contains a question"
|
|
directory: "/test/emails"
|
|
data_types: ["tasks", "notes", "timelines"]
|
|
directory_files:
|
|
- path: "/test/emails/outlook_export_2024.html"
|
|
content_file: "email_action.html"
|
|
user_messages: []
|
|
score_name: "journey.start"
|
|
expect_question: true
|
|
|
|
- id: "4.2"
|
|
description: "Full 3-turn conversation produces a valid AgentConfig JSON"
|
|
directory: "/test/emails"
|
|
data_types: ["tasks", "notes", "timelines"]
|
|
directory_files:
|
|
- path: "/test/emails/email_backup.html"
|
|
content_file: "email_action.html"
|
|
user_messages:
|
|
- "These are email exports from Outlook in HTML format"
|
|
- "Create tasks for emails with direct action requests, notes for informational emails"
|
|
- "Yes, that looks correct. No other rules."
|
|
score_name: "journey.valid_json"
|
|
expect_done: true
|
|
expect_valid_config: true
|
|
|
|
- id: "4.3"
|
|
description: "Journey detects email_html content type from directory exploration"
|
|
directory: "/test/emails"
|
|
data_types: ["tasks", "notes"]
|
|
directory_files:
|
|
- path: "/test/emails/message.html"
|
|
content_file: "email_action.html"
|
|
user_messages:
|
|
- "HTML email backups from my mail client, exported from Outlook"
|
|
- "Create tasks from emails that contain assignments or direct action items"
|
|
- "Correct, no other rules needed"
|
|
score_name: "journey.detect_email"
|
|
expect_done: true
|
|
expect_content_type_id: "email_html"
|
|
|
|
- id: "4.4"
|
|
description: "Custom user rule (only notes, no tasks) reflected in extraction_prompt"
|
|
directory: "/test/emails"
|
|
data_types: ["notes"]
|
|
directory_files:
|
|
- path: "/test/emails/email.html"
|
|
content_file: "email_info.html"
|
|
user_messages:
|
|
- "HTML emails from my work inbox"
|
|
- "Create only notes from all emails — I do not want tasks or timelines to be created"
|
|
- "Yes, exactly"
|
|
score_name: "journey.custom_rules"
|
|
expect_done: true
|
|
expect_extraction_contains: "note"
|
|
|
|
- id: "4.5"
|
|
description: "Global rule (no project = no entity) appears in AgentConfig.global_rules"
|
|
directory: "/test/emails"
|
|
data_types: ["tasks", "notes"]
|
|
directory_files:
|
|
- path: "/test/emails/email.html"
|
|
content_file: "email_action.html"
|
|
user_messages:
|
|
- "Email backups from Outlook"
|
|
- "Create tasks from action request emails, notes from informational emails"
|
|
- "If the email cannot be matched to any project, do not create any entity at all"
|
|
score_name: "journey.global_rules"
|
|
expect_done: true
|
|
expect_global_rules: true
|