Files
optimclaw/tests/support/assertions.rs
T
b4b19738a8 Trajectory benchmarks and e2e trace test rig (#553)
* refactor: extract shared assertion helpers to support/assertions.rs

Move 5 assertion helpers from e2e_spot_checks.rs to a shared module.
Add assert_all_tools_succeeded and assert_tool_succeeded for eliminating
false positives in E2E tests.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat: add tool output capture via tool_results() accessor

Extract (name, preview) from ToolResult status events in TestChannel
and TestRig, enabling content assertions on tool outputs.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: correct tool parameters in 3 broken trace fixtures

- tool_time.json: add missing "operation": "now" for time tool
- robust_correct_tool.json: same fix
- memory_full_cycle.json: change "path" to "target" for memory_write

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: add tool success and output assertions to eliminate false positives

Every E2E test that exercises tools now calls assert_all_tools_succeeded.
Added tool output content assertions where tool results are predictable
(time year, read_file content, memory_read content).

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat: capture per-tool timing from ToolStarted/ToolCompleted events

Record Instant on ToolStarted and compute elapsed duration on
ToolCompleted, wiring real timing data into collect_metrics() instead
of hardcoded zeros.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* refactor: add RAII CleanupGuard for temp file/dir cleanup in tests

Replace manual cleanup_test_dir() calls and inline remove_file() with
Drop-based CleanupGuard that ensures cleanup even if a test panics.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: add Drop impl and graceful shutdown for TestRig

Wrap agent_handle in Option so Drop can abort leaked tasks. Signal
the channel shutdown before aborting for future cooperative shutdown.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: replace agent startup sleep with oneshot ready signal

Use a oneshot channel fired in Channel::start() instead of a fixed
100ms sleep, eliminating the race condition on slow systems.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: replace fragile string-matching iteration limit with count-based detection

Use tool completion count vs max_tool_iterations instead of scanning
status messages for "iteration"/"limit" substrings.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: use assert_all_tools_succeeded for memory_full_cycle test

Remove incorrect comment about memory_tree failing with empty path
(it actually succeeds). Omit empty path from fixture and use the
standard assert_all_tools_succeeded instead of per-tool assertions.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* refactor: promote benchmark metrics types to library code

Move TraceMetrics, ScenarioResult, RunResult, MetricDelta, and
compare_runs() from tests/support/metrics.rs to src/benchmark/metrics.rs.
Existing tests use re-export for backward compatibility.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat: add Scenario and Criterion types for agent benchmarking

Scenario defines a task with input, success criteria, and resource
limits. Criterion is an enum of programmatic checks (tool_used,
response_contains, etc.) evaluated without LLM judgment.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat: add initial benchmark scenario suite (12 scenarios across 5 categories)

Scenarios cover tool_selection, tool_chaining, error_recovery,
efficiency, and memory_operations. All loaded from JSON with
deserialization validation test.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat: add benchmark runner with BenchChannel and InstrumentedLlm

BenchChannel is a minimal Channel implementation for benchmarks.
InstrumentedLlm wraps any LlmProvider to capture per-call metrics.
Runner creates a fresh agent per scenario, evaluates success criteria,
and produces RunResult with timing, token, and cost metrics.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat: add baseline management, reports, and benchmark entry point

- baseline.rs: load/save/promote benchmark results
- report.rs: format comparison reports with regression detection
- benchmark_runner.rs: integration test with real LLM (feature-gated)
- Add benchmark feature flag to Cargo.toml

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* style: apply cargo fmt to benchmark module

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat(benchmark): add multi-turn scenario types with setup, judge, ResponseNotContains

Add BenchScenario, Turn, TurnAssertions, JudgeConfig, ScenarioSetup,
WorkspaceSetup, SeedDocument types for multi-turn benchmark scenarios.
Add ResponseNotContains criterion variant. Add TurnAssertions::to_criteria()
converter for backward compat with existing evaluation engine.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat(benchmark): add JSON scenario loader with recursive discovery and tag filter

Add load_bench_scenarios() for the new BenchScenario format with recursive
directory traversal and tag-based filtering. Create 4 initial trajectory
scenarios across tool-selection, multi-turn, and efficiency categories.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat(benchmark): multi-turn runner with workspace seeding and per-turn metrics

Add run_bench_scenario() that loops over BenchScenario turns, seeds workspace
documents, collects per-turn metrics (tokens, tool calls, wall time), and
evaluates per-turn assertions. Add TurnMetrics to metrics.rs and
clear_for_next_turn() to BenchChannel.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat(benchmark): add LLM-as-judge scoring with prompt formatting and score parsing

Create judge.rs with format_judge_prompt, parse_judge_score, and judge_turn.
Wire into run_bench_scenario for turns with judge config -- scores below
min_score fail the turn.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat(benchmark): add CLI subcommand (ironclaw benchmark)

Add BenchmarkCommand with --tags, --scenario, --no-judge, --timeout,
--update-baseline flags. Wire into Command enum and main.rs dispatch.
Feature-gated behind benchmark flag.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat(benchmark): per-scenario JSON output with full trajectory

Add save_scenario_results() that writes per-scenario JSON files alongside
the run summary. Each scenario gets its own file with turn_metrics trajectory.
Update CLI to use new output format.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat(benchmark): add ToolRegistry::retain_only and wire tool filtering in scenarios

Add a retain_only() method to ToolRegistry that filters tools down to a
given allowlist. Wire this into run_bench_scenario() so that when a
scenario specifies a tools list in its setup, only those tools are
available during the benchmark run. Includes two tests for the new
method: one verifying filtering works and one verifying empty input
is a no-op.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat(benchmark): wire identity overrides into workspace before agent start

Add seed_identity() helper that writes identity files (IDENTITY.md,
USER.md, etc.) into the workspace before the agent starts, so that
workspace.system_prompt() picks them up. Wire it into
run_bench_scenario() after workspace seeding. Include a test that
verifies identity files are written and readable.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat(benchmark): add --parallel and --max-cost CLI flags

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix(benchmark): use feature-conditional snapshot names for CLI help tests

Prevents snapshot conflicts between default (no benchmark) and
all-features (with benchmark) builds by using separate snapshot names
per feature set.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat(benchmark): parallel execution with JoinSet and budget cap enforcement

Replace sequential loop in run_all_bench() with parallel execution using
JoinSet + semaphore when config.parallel > 1. Add budget cap enforcement
that skips remaining scenarios when max_total_cost_usd is exceeded.
Track skipped count in RunResult.skipped_scenarios and display it in
format_report().

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat(benchmark): add tool restriction and identity override test scenarios

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* chore: fix formatting for Phase 3

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat(benchmark): add SkillRegistry::retain_only and wire skill filtering in scenarios

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat(benchmark): add --json flag for machine-readable output

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* ci: add GitHub Actions benchmark workflow (manual trigger)

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* refactor(benchmark): remove in-tree benchmark harness, keep retain_only utilities

Move benchmark-specific code out of ironclaw in preparation for the
nearai/benchmarks trajectory adapter. This removes:

- src/benchmark/ (runner, scenarios, metrics, judge, report, etc.)
- src/cli/benchmark.rs and the Benchmark CLI subcommand
- benchmarks/ data directory (scenarios + trajectories)
- .github/workflows/benchmark.yml
- The "benchmark" Cargo feature flag

What remains:
- ToolRegistry::retain_only() and SkillRegistry::retain_only()
- Test support types (TraceMetrics, InstrumentedLlm) inlined into
  tests/support/ instead of re-exporting from the deleted module

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* docs: add README for LLM trace fixture format

Documents the trajectory JSON format, response types, request hints,
directory structure, and how to write new traces.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat(test): unify trace format around turns, add multi-turn support

Introduce TraceTurn type that groups user_input with LLM response steps,
making traces self-contained conversation trajectories. Add run_trace()
to TestRig for automatic multi-turn replay. Backward-compatible: flat
"steps" JSON is deserialized as a single turn transparently.

Includes all trace fixtures (spot, coverage, advanced), plan docs, and
new e2e tests for steering, error recovery, long chains, memory, and
prompt injection resilience.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix(test): fix CI failures after merging main

- Fix tool_json fixture: use "data" parameter (not "input") to match
  JsonTool schema
- Fix status_events test: remove assertion for "time" tool that isn't
  in the fixture (only "echo" calls are used)
- Allow dead_code in test support metrics/instrumented_llm modules
  (utilities for future benchmark tests)

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* Working on recording traces and testing them

* feat(test): add declarative expects to trace fixtures, split infra tests

Add TraceExpects struct with 9 optional assertion fields (response_contains,
tools_used, all_tools_succeeded, etc.) that can be declared in fixture JSON
instead of hand-written Rust. Add verify_expects() and run_recorded_trace()
so recorded trace tests become one-liners.

Split trace infra tests (deserialization, backward compat) into
tests/trace_format.rs which doesn't require the libsql feature gate.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* refactor(test): add expects to all trace fixtures, simplify e2e tests

Add declarative expects blocks to all 19 trace fixture JSONs across
spot/, coverage/, advanced/, and root directories. Update all 8 e2e
test files to use verify_trace_expects() / run_and_verify_trace(),
replacing ~270 lines of hand-written assertions with fixture-driven
verification.

Tests that check things beyond expects (file content on disk, metrics,
event ordering) keep those extra assertions alongside the declarative
ones.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix(test): adapt tests to AppBuilder refactor, fix formatting

Update test files to work with refactored TestRigBuilder that uses
AppBuilder::build_all() (removing with_tools/with_workspace methods).
Update telegram_check fixture to use tool_list instead of echo.
Fix cargo fmt issues in src/llm/mod.rs and src/llm/recording.rs.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* refactor(test): deduplicate support unit tests into single binary

Support modules (assertions, cleanup, test_channel, test_rig, trace_llm)
had #[cfg(test)] mod tests blocks that were compiled and run 12 times —
once per e2e test binary that declares `mod support;`. Extracted all 29
support unit tests into a dedicated `tests/support_unit_tests.rs` so they
run exactly once.

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* style: fix trailing newlines in support files

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* refactor(test): unify trace types and fix recorded multi-turn replay

Import shared types (TraceStep, TraceResponse, TraceToolCall, RequestHint,
ExpectedToolResult, MemorySnapshotEntry, HttpExchange*) from
ironclaw::llm::recording instead of redefining them in trace_llm.rs.

Fix the flat-steps deserializer to split at UserInput boundaries into
multiple turns, instead of filtering them out and wrapping everything
into a single turn. This enables recorded multi-turn traces to be
replayed as proper multi-turn conversations via run_trace().

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix(test): fix CI failures - unused imports and missing struct fields

- Add #[allow(unused_imports)] on pub use re-exports in trace_llm.rs
  (types are re-exported for downstream test files, not used locally)
- Add `..` to ToolCompleted pattern in test_channel.rs to match new
  `error` and `parameters` fields

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix(test): fix CI failures after merging main

- Add missing `error` and `parameters` fields to ToolCompleted
  constructors in support_unit_tests.rs
- Add `..` to ToolCompleted pattern match in support_unit_tests.rs
- Add #[allow(dead_code)] to CleanupGuard, LlmTrace impl, and
  TraceLlm impl (only used behind #[cfg(feature = "libsql")])

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* Adding coverage running script

* fix(test): address review feedback on E2E test infrastructure

- Increase wait_for_responses polling to exponential backoff (50ms-500ms)
  and raise default timeout from 15s to 30s to reduce CI flakiness (#1)
- Strengthen prompt_injection_resilience test with positive safety layer
  assertion via has_safety_warnings(), enable injection_check (#2)
- Add assert_tool_order() helper and tools_order field in TraceExpects
  for verifying tool execution ordering in multi-step traces (#3)
- Document TraceLlm sequential-call assumption for concurrency (#6)
- Clean up CleanupGuard with PathKind enum instead of shotgun
  remove_file + remove_dir_all on every path (#8)
- Fix coverage.sh: default to --lib only, fix multi-filter syntax,
  add COV_ALL_TARGETS option
- Add coverage/ to .gitignore
- Remove planning docs from PR

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: address PR review - use HashSet in retain_only, improve skill test

- Use HashSet for O(N+M) lookup in SkillRegistry::retain_only and
  ToolRegistry::retain_only instead of linear scan
- Strengthen test_retain_only_empty_is_noop in SkillRegistry to
  pre-populate with a skill before asserting the no-op behavior

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix(test): revert incorrect safety layer assertion in injection test

The safety layer sanitizes tool output, not user input. The injection
test sends a malicious user message with no tools called, so the safety
layer never fires. Reverted to the original test which correctly
validates the LLM refuses via trace expects. Also fixed case-sensitive
request hint ("ignore" -> "Ignore") to suppress noisy warning.

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: clean stale profdata before coverage run

Adds `cargo llvm-cov clean` before each run to prevent
"mismatched data" warnings from stale instrumentation profiles.

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* style: fix formatting in retain_only test

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 <[email protected]>

---------

Co-authored-by: Claude Opus 4.6 <[email protected]>
Co-authored-by: Illia Polosukhin <[email protected]>
2026-03-05 09:13:09 +00:00

214 lines
6.9 KiB
Rust

//! Shared assertion helpers for E2E tests.
//!
//! Extracted from `e2e_spot_checks.rs` so they can be reused across all E2E
//! test files. Mirrors the assertion types from `nearai/benchmarks` SpotSuite.
#![allow(dead_code)]
use regex::Regex;
use crate::support::trace_llm::TraceExpects;
/// Assert the response contains all `needles` (case-insensitive).
pub fn assert_response_contains(response: &str, needles: &[&str]) {
let lower = response.to_lowercase();
for needle in needles {
assert!(
lower.contains(&needle.to_lowercase()),
"response_contains: missing \"{needle}\" in response: {response}"
);
}
}
/// Assert the response matches the given regex `pattern`.
pub fn assert_response_matches(response: &str, pattern: &str) {
let re = Regex::new(pattern).expect("invalid regex pattern");
assert!(
re.is_match(response),
"response_matches: /{pattern}/ did not match response: {response}"
);
}
/// Assert that all `expected` tool names appear in `started`.
pub fn assert_tools_used(started: &[String], expected: &[&str]) {
for tool in expected {
assert!(
started.iter().any(|s| s == tool),
"tools_used: \"{tool}\" not called, got: {started:?}"
);
}
}
/// Assert that none of the `forbidden` tool names appear in `started`.
pub fn assert_tools_not_used(started: &[String], forbidden: &[&str]) {
for tool in forbidden {
assert!(
!started.iter().any(|s| s == tool),
"tools_not_used: \"{tool}\" was called, got: {started:?}"
);
}
}
/// Assert at most `max` tool calls were started.
pub fn assert_max_tool_calls(started: &[String], max: usize) {
assert!(
started.len() <= max,
"max_tool_calls: expected <= {max}, got {}. Tools: {started:?}",
started.len()
);
}
/// Assert ALL completed tools succeeded. Panics listing failed tools.
pub fn assert_all_tools_succeeded(completed: &[(String, bool)]) {
let failed: Vec<&str> = completed
.iter()
.filter(|(_, success)| !*success)
.map(|(name, _)| name.as_str())
.collect();
assert!(
failed.is_empty(),
"Expected all tools to succeed, but these failed: {failed:?}. All: {completed:?}"
);
}
/// Assert a specific tool completed successfully at least once.
pub fn assert_tool_succeeded(completed: &[(String, bool)], tool_name: &str) {
let found = completed
.iter()
.any(|(name, success)| name == tool_name && *success);
assert!(
found,
"Expected '{tool_name}' to complete successfully, got: {completed:?}"
);
}
/// Assert the response does NOT contain any of `forbidden` (case-insensitive).
pub fn assert_response_not_contains(response: &str, forbidden: &[&str]) {
let lower = response.to_lowercase();
for needle in forbidden {
assert!(
!lower.contains(&needle.to_lowercase()),
"response_not_contains: found \"{needle}\" in response: {response}"
);
}
}
/// Assert that `expected` tools appear in `started` in the given order.
///
/// The tools need not be consecutive — only relative ordering is checked.
/// For example, `assert_tool_order(started, &["write_file", "read_file"])`
/// passes if `write_file` appears before `read_file`, even with other tools
/// in between.
pub fn assert_tool_order(started: &[String], expected: &[&str]) {
let mut search_from = 0;
for tool in expected {
let pos = started[search_from..]
.iter()
.position(|s| s == tool)
.map(|p| p + search_from);
match pos {
Some(idx) => search_from = idx + 1,
None => {
panic!(
"assert_tool_order: \"{tool}\" not found after position {search_from} \
in: {started:?}. Expected order: {expected:?}"
);
}
}
}
}
/// Verify all expectations from a `TraceExpects` against actual data.
///
/// `label` is used in assertion messages to identify context (e.g. "top-level" or "turn 0").
/// `responses` are the response content strings, `started` are tool names started,
/// `completed` are (name, success) pairs, `results` are (name, preview) pairs.
pub fn verify_expects(
expects: &TraceExpects,
responses: &[String],
started: &[String],
completed: &[(String, bool)],
results: &[(String, String)],
label: &str,
) {
if expects.is_empty() {
return;
}
// min_responses
if let Some(min) = expects.min_responses {
assert!(
responses.len() >= min,
"[{label}] min_responses: expected >= {min}, got {}",
responses.len()
);
}
// response_contains / response_not_contains / response_matches — checked against joined response
let joined = responses.join("\n");
if !expects.response_contains.is_empty() {
let needles: Vec<&str> = expects
.response_contains
.iter()
.map(|s| s.as_str())
.collect();
assert_response_contains(&joined, &needles);
}
if !expects.response_not_contains.is_empty() {
let forbidden: Vec<&str> = expects
.response_not_contains
.iter()
.map(|s| s.as_str())
.collect();
assert_response_not_contains(&joined, &forbidden);
}
if let Some(ref pattern) = expects.response_matches {
assert_response_matches(&joined, pattern);
}
// tools_used
if !expects.tools_used.is_empty() {
let expected: Vec<&str> = expects.tools_used.iter().map(|s| s.as_str()).collect();
assert_tools_used(started, &expected);
}
// tools_not_used
if !expects.tools_not_used.is_empty() {
let forbidden: Vec<&str> = expects.tools_not_used.iter().map(|s| s.as_str()).collect();
assert_tools_not_used(started, &forbidden);
}
// all_tools_succeeded
if expects.all_tools_succeeded == Some(true) {
assert_all_tools_succeeded(completed);
}
// max_tool_calls
if let Some(max) = expects.max_tool_calls {
assert_max_tool_calls(started, max);
}
// tools_order
if !expects.tools_order.is_empty() {
let expected: Vec<&str> = expects.tools_order.iter().map(|s| s.as_str()).collect();
assert_tool_order(started, &expected);
}
// tool_results_contain
for (tool_name, substring) in &expects.tool_results_contain {
let found = results.iter().find(|(name, _)| name == tool_name);
assert!(
found.is_some(),
"[{label}] tool_results_contain: no result for tool \"{tool_name}\", got: {results:?}"
);
let (_, preview) = found.unwrap();
assert!(
preview.to_lowercase().contains(&substring.to_lowercase()),
"[{label}] tool_results_contain: tool \"{tool_name}\" result does not contain \"{substring}\", got: \"{preview}\""
);
}
}