forked from HAL9000/cleveragents-core
e4c01492d5
Aligned the `agents actor run` command signature with the specification by introducing positional NAME and PROMPT arguments. The --config/-c option is preserved as an optional fallback for direct YAML invocation. When NAME is provided without --config, the actor is resolved from the Actor Registry. Updated both actor_run.py and actor.py run commands. Added backward compatibility: if --config is provided, it takes precedence over name-based resolution. Review fixes applied (code review round 1): - P1-1: Narrowed bare `except Exception` to `except NotFoundError` in _resolve_config_files to avoid masking infrastructure errors. - P1-2: Moved _resolve_config_files call inside the try block in run() so container/registry init errors get user-friendly messages. Added `except click.exceptions.Exit: raise` to let typer.Exit propagate through the broadened try scope. - P1-3: Added atexit.register cleanup for temp files created by _resolve_config_files (resource leak fix). - P1-4: Added CHANGELOG.md entry for the breaking CLI change. - P2-1: Extracted duplicated _resolve_config_files to shared module `_resolve_actor.py`; both actor.py and actor_run.py now import it. - P2-2: Added guard for actors with no configuration data (config_blob=None) to produce a clear error instead of invalid YAML. - P2-3/P2-4: Added 5 BDD scenarios exercising the real resolve_config_files function (registry path, yaml_text path, config_blob fallback, no-config-data error, not-found error). - P2-5: Added @coverage tags to all new BDD scenarios. - P3-1: Added timeout=120s and on_timeout=kill to Robot tests. - Fixed rxpy_route_validation.robot tests that used the removed --prompt/-p option (replaced with positional NAME + PROMPT args). Review fixes applied (code review round 2): - P2-1: Aligned actor_run.py exception handler from `CleverAgentsException` to `CleverAgentsError`, matching actor.py so infrastructure errors from registry resolution get user-friendly messages instead of falling through to the generic handler. - P2-2: Changed `yaml.dump` to `yaml.safe_dump` in _resolve_actor.py for fail-fast behavior on unexpected types, consistent with the codebase's dominant pattern. - P3-6: Replaced defensive `getattr(actor, ...)` calls with direct Pydantic model attribute access (`actor.yaml_text`, `actor.config_blob`) for type-checker coverage. - P3-1: Switched BDD temp file cleanup from post-assertion `unlink()` to `context.add_cleanup()` for leak-proof teardown. - P2-3/P3-2/P3-3/P3-4: Added 3 BDD edge-case scenarios (empty config_blob dict, infrastructure error propagation, empty string name) and 1 Robot test case (actor_app registry resolution). Review fixes applied (code review round 3): - P1-1: Migrated 48 remaining `-p` invocations across 9 Robot test files to the new positional `NAME PROMPT` pattern (context_delete_all_yes, load_context_test, scientific_paper_e2e_test, routing_prefix_stripping, scientific_paper_basic, scientific_paper_writer_test, context_management_test, initial_next_command_test, system_prompt_template_rendering). - P2-1: Documented `--config/-c` as a spec deviation in `_resolve_actor.py` module docstring (spec lines 4562-4566 define `actor run` with no --config option; issue #901 AC accepts keeping it as optional). - P2-2: Corrected `--config` help text from "fallback" to "overrides registry-based name resolution" — the option takes precedence, not the other way around. - P3-1: Added `.strip()` to `yaml_text` emptiness check in `_resolve_actor.py` to handle whitespace-only values that would otherwise bypass the `config_blob` fallback. - P3-2: Added `from None` to the no-configuration-data `typer.Exit(code=2)` for consistency with the not-found path. - P3-3: Added BDD scenario testing `--config` precedence for `actor_run_app` (was only tested for `actor_app`). - P3-4: Strengthened config_blob BDD scenario to verify generated YAML is parseable via `yaml.safe_load` round-trip. - P3-7: Replaced hardcoded `/tmp/dummy.yaml` with `tempfile.gettempdir()` for portability. - P3-8: Moved 5 inline imports to module level per CONTRIBUTING.md §1292-1294 (3x `import click`, 1x InfrastructureError in steps; 1x `import typer` in robot helper). - P3-9: Added `encoding="utf-8"` to `_write_yaml` in Robot helper for consistency with production code. Review fixes applied (code review round 4): - P2-1: Wrapped `yaml.safe_dump` in `_resolve_actor.py` with `try/except yaml.YAMLError` so non-serialisable config_blob values produce a user-friendly error message instead of a raw traceback. - P2-2: Moved remaining inline `import yaml` to module level in `actor_run_signature_steps.py` per CONTRIBUTING.md §1292-1294. - P2-3: Replaced 3 bare `assert` statements in Robot helper `helper_actor_run_signature.py` with diagnostic `if/print/sys.exit` pattern matching the rest of the file, improving failure diagnostics. Review fixes applied (code review round 5): - P3-4: Replaced per-call `atexit.register(lambda)` in `_resolve_actor.py` with a module-level `_temp_files` set and a single `atexit` handler (`_cleanup_temp_files`) to prevent unbounded handler accumulation in same-process usage (e.g. test suites running multiple CliRunner invocations). - P3-1/P3-2/P3-3: Added 4 BDD scenarios: whitespace-only `yaml_text` fallback to config_blob, config-precedence registry-not-consulted assertion for both `actor_app` and `actor_run_app`, multiple `--config` files with positional NAME. - P4-1: Strengthened error-path BDD assertions to verify error message content (not-found, no-config-data, serialisation-error) alongside exit codes via captured stderr. - P4-2: Added Robot test case for `actor_app` unknown-name error path and corresponding helper function. ISSUES CLOSED: #901
262 lines
10 KiB
Plaintext
262 lines
10 KiB
Plaintext
*** Settings ***
|
|
Documentation End-to-end integration test for Scientific Paper Writer
|
|
Library Process
|
|
Library OperatingSystem
|
|
Library String
|
|
Resource ${CURDIR}/v2_paths.resource
|
|
Suite Setup Setup Test Environment
|
|
Suite Teardown Cleanup Test Environment
|
|
|
|
*** Variables ***
|
|
${PYTHON} python
|
|
${CONFIG_FILE} ${CURDIR}/../examples/scientific_paper_writer.yaml
|
|
${CONTEXT_DIR} ${TEMPDIR}/paper_e2e_contexts
|
|
${CONTEXT_NAME} paper_e2e_${TEST_ID}
|
|
${TEST_ID} ${EMPTY}
|
|
|
|
|
|
*** Test Cases ***
|
|
Scientific Paper Writer Full Workflow
|
|
[Documentation] Test the complete workflow from intro through multiple stages
|
|
[Tags] integration e2e slow
|
|
[Timeout] 10 minutes
|
|
|
|
# Test 1: Intro stage
|
|
Log Testing intro stage...
|
|
${result}= Run Paper Command Hello
|
|
Should Contain ${result.stdout} Paper Writer
|
|
|
|
# Test 2: Advance to discovery
|
|
Log Advancing to discovery stage...
|
|
${result}= Run Paper Command !next discovery
|
|
Should Be Equal As Integers ${result.rc} 0
|
|
# Verify we're now in discovery stage
|
|
${stage_check}= Run Paper Command !stage
|
|
Should Contain ${stage_check.stdout} discovery
|
|
|
|
# Test 3: Commands work
|
|
Log Testing commands...
|
|
${result}= Run Paper Command !stages
|
|
Should Contain ${result.stdout} discovery
|
|
Should Contain ${result.stdout} brainstorming
|
|
|
|
# Test 4: Test help command
|
|
Log Testing help command...
|
|
${result}= Run Paper Command !help
|
|
Should Contain ${result.stdout} Available Commands
|
|
Should Contain ${result.stdout} !next
|
|
Should Contain ${result.stdout} !accept
|
|
|
|
# Test 5: Skip to brainstorming with mock data
|
|
Log Setting up mock paper details and advancing to brainstorming...
|
|
${result}= Run Paper Command !next brainstorming
|
|
Should Be Equal As Integers ${result.rc} 0
|
|
# Verify we're now in brainstorming stage
|
|
${stage_check}= Run Paper Command !stage
|
|
Should Contain ${stage_check.stdout} brainstorming
|
|
|
|
# Test 6: Test brainstorming stage
|
|
Log Testing brainstorming stage...
|
|
${result}= Run Paper Command I want to write about the impact of machine learning on healthcare, focusing on diagnostic imaging and patient outcomes timeout=90s
|
|
Length Should Be Greater Than ${result.stdout} 50
|
|
|
|
# Test 7: Verify stage may have advanced (brainstorming stage might auto-advance after LLM response)
|
|
# So we don't check for specific stage here anymore
|
|
|
|
# Test 8: Advance toward later stages (using structure or latex_generation as targets)
|
|
Log Advancing toward later stages...
|
|
${result}= Run Paper Command !next structure timeout=120s
|
|
Should Be Equal As Integers ${result.rc} 0
|
|
|
|
# Test 9: Verify stage list command works
|
|
Log Verifying stage list command...
|
|
${result}= Run Paper Command !stages
|
|
Should Contain ${result.stdout} structure
|
|
Should Contain ${result.stdout} latex_generation
|
|
|
|
Log End-to-end test completed successfully
|
|
|
|
Scientific Paper Writer LaTeX Generation
|
|
[Documentation] Test LaTeX generation using pre-populated context
|
|
[Tags] integration e2e latex code_blocks
|
|
[Timeout] 5 minutes
|
|
|
|
${ctx}= Set Variable latex_test_${TEST_ID}
|
|
|
|
# Import the brainstorming context fixture
|
|
Log Importing brainstorming context fixture...
|
|
${result}= Run Process ${PYTHON} -m cleveragents context import
|
|
... ${ctx}
|
|
... ${V2_PAPER_CONTEXTS_DIR}/03_brainstorming.json
|
|
... --context-dir ${CONTEXT_DIR}
|
|
... stderr=STDOUT
|
|
... timeout=30s
|
|
|
|
Should Be Equal As Integers ${result.rc} 0
|
|
Log Context imported: ${result.stdout}
|
|
|
|
# Advance to latex_generation stage
|
|
Log Advancing to latex_generation stage...
|
|
${result}= Run Process ${PYTHON} -m cleveragents actor run
|
|
... -c ${CONFIG_FILE}
|
|
... --context ${ctx}
|
|
... --context-dir ${CONTEXT_DIR}
|
|
... --unsafe
|
|
... --allow-rxpy-in-run-mode
|
|
... test-actor !next latex_generation
|
|
... stderr=STDOUT
|
|
... timeout=180s
|
|
Should Be Equal As Integers ${result.rc} 0
|
|
# Note: Stage may auto-advance after !next is called
|
|
|
|
# Generate LaTeX document (send message that should trigger LaTeX generation)
|
|
# The exact stage doesn't matter - the system should generate LaTeX when asked
|
|
Log Generating LaTeX document...
|
|
${result}= Run Process ${PYTHON} -m cleveragents actor run
|
|
... -c ${CONFIG_FILE}
|
|
... --context ${ctx}
|
|
... --context-dir ${CONTEXT_DIR}
|
|
... --unsafe
|
|
... --allow-rxpy-in-run-mode
|
|
... test-actor Generate the complete LaTeX document
|
|
... stderr=STDOUT
|
|
... timeout=180s
|
|
Should Be Equal As Integers ${result.rc} 0
|
|
# System should produce SOME output (not just echo the input)
|
|
Should Not Be Equal ${result.stdout} Generate the complete LaTeX document
|
|
|
|
# Verify LaTeX structure
|
|
Log Verifying LaTeX document structure...
|
|
Should Contain ${result.stdout} \\documentclass
|
|
Should Contain ${result.stdout} \\begin{document}
|
|
Should Contain ${result.stdout} \\end{document}
|
|
Should Contain ${result.stdout} \\section
|
|
|
|
# Verify context was updated
|
|
Log Verifying context is accessible...
|
|
${result}= Run Process ${PYTHON} -m cleveragents actor run
|
|
... -c ${CONFIG_FILE}
|
|
... --context ${ctx}
|
|
... --context-dir ${CONTEXT_DIR}
|
|
... --unsafe
|
|
... --allow-rxpy-in-run-mode
|
|
... test-actor !context
|
|
... stderr=STDOUT
|
|
... timeout=30s
|
|
Should Contain ${result.stdout} latex_source
|
|
|
|
Log LaTeX generation test completed
|
|
|
|
Scientific Paper Writer Stage Navigation
|
|
[Documentation] Test stage navigation and command processing
|
|
[Tags] integration commands code_blocks
|
|
[Timeout] 3 minutes
|
|
|
|
${ctx}= Set Variable stage_nav_${TEST_ID}
|
|
|
|
# Start at intro
|
|
${result}= Run Process ${PYTHON} -m cleveragents actor run
|
|
... -c ${CONFIG_FILE}
|
|
... --context ${ctx}
|
|
... --context-dir ${CONTEXT_DIR}
|
|
... --unsafe
|
|
... --allow-rxpy-in-run-mode
|
|
... test-actor !stages
|
|
... stderr=STDOUT
|
|
... timeout=20s
|
|
Should Contain ${result.stdout} intro
|
|
|
|
# Test !next command
|
|
${result}= Run Process ${PYTHON} -m cleveragents actor run
|
|
... -c ${CONFIG_FILE}
|
|
... --context ${ctx}
|
|
... --context-dir ${CONTEXT_DIR}
|
|
... --unsafe
|
|
... --allow-rxpy-in-run-mode
|
|
... test-actor !next
|
|
... stderr=STDOUT
|
|
... timeout=20s
|
|
Should Be Equal As Integers ${result.rc} 0
|
|
# Verify we advanced from intro (stage may auto-advance past discovery to brainstorming)
|
|
${stage_check}= Run Process ${PYTHON} -m cleveragents actor run
|
|
... -c ${CONFIG_FILE}
|
|
... --context ${ctx}
|
|
... --context-dir ${CONTEXT_DIR}
|
|
... --unsafe
|
|
... --allow-rxpy-in-run-mode
|
|
... test-actor !stage
|
|
... stderr=STDOUT
|
|
... timeout=20s
|
|
Should Not Contain ${stage_check.stdout} intro
|
|
|
|
# Test !help command
|
|
${result}= Run Process ${PYTHON} -m cleveragents actor run
|
|
... -c ${CONFIG_FILE}
|
|
... --context ${ctx}
|
|
... --context-dir ${CONTEXT_DIR}
|
|
... --unsafe
|
|
... --allow-rxpy-in-run-mode
|
|
... test-actor !help
|
|
... stderr=STDOUT
|
|
... timeout=20s
|
|
Should Contain ${result.stdout} Available Commands
|
|
Should Contain ${result.stdout} !next
|
|
Should Contain ${result.stdout} !accept
|
|
|
|
# Test !stage command
|
|
${result}= Run Process ${PYTHON} -m cleveragents actor run
|
|
... -c ${CONFIG_FILE}
|
|
... --context ${ctx}
|
|
... --context-dir ${CONTEXT_DIR}
|
|
... --unsafe
|
|
... --allow-rxpy-in-run-mode
|
|
... test-actor !stage
|
|
... stderr=STDOUT
|
|
... timeout=20s
|
|
Should Contain ${result.stdout} Current Stage
|
|
Should Contain ${result.stdout} Purpose
|
|
|
|
*** Keywords ***
|
|
Setup Test Environment
|
|
${timestamp}= Get Time epoch
|
|
Set Suite Variable ${TEST_ID} ${timestamp}
|
|
Set Suite Variable ${CONTEXT_NAME} paper_e2e_${TEST_ID}
|
|
Create Directory ${CONTEXT_DIR}
|
|
Log Test environment setup complete with ID: ${TEST_ID}
|
|
|
|
Cleanup Test Environment
|
|
Run Keyword And Ignore Error Remove Directory ${CONTEXT_DIR} recursive=True
|
|
Log Test environment cleaned up
|
|
|
|
Run Paper Command
|
|
[Arguments] ${command} ${timeout}=30s
|
|
[Documentation] Run a command against the paper writer with the persistent context
|
|
${result}= Run Process ${PYTHON} -m cleveragents actor run
|
|
... -c ${CONFIG_FILE}
|
|
... --context ${CONTEXT_NAME}
|
|
... --context-dir ${CONTEXT_DIR}
|
|
... --unsafe
|
|
... --allow-rxpy-in-run-mode
|
|
... test-actor ${command}
|
|
... stderr=STDOUT
|
|
... timeout=${timeout}
|
|
Log Command: ${command}
|
|
Log Output: ${result.stdout}
|
|
RETURN ${result}
|
|
|
|
Should Contain Any
|
|
[Arguments] ${text} @{patterns}
|
|
[Documentation] Check if text contains at least one of the patterns
|
|
FOR ${pattern} IN @{patterns}
|
|
${status}= Run Keyword And Return Status Should Contain ${text} ${pattern} ignore_case=True
|
|
IF ${status} RETURN
|
|
END
|
|
Fail Text does not contain any of: @{patterns}
|
|
|
|
Length Should Be Greater Than
|
|
[Arguments] ${text} ${min_length}
|
|
[Documentation] Check if text length is greater than minimum
|
|
${length}= Get Length ${text}
|
|
Should Be True ${length} > ${min_length} Text length ${length} is not greater than ${min_length}
|
|
|