{% extends "base.html" %} {% from "_macros.html" import badge, counts_line, legend %} {% set fam_name = family_names.get(cell.family, cell.family) %} {% block title %}{{ fam_name }} on {{ cell.engine }} {{ cell.engine_version }} ยท CanIToolCall{% endblock %} {% block main %}

{{ fam_name }} on {{ cell.engine }} {{ cell.engine_version }}

{{ badge(cell.status) }} {% if cell.pass_rate is not none %}{{ cell.pass_rate|pct }} strict pass{% endif %} {{ counts_line(cell.counts) }}

Run

Engine
{{ run.engine.name }} {{ run.engine.version }}{% if run.engine.commit %} ({{ run.engine.commit }}){% endif %}
Run
to
Platform
{{ run.run.platform }}, Python {{ run.run.python }}, canitoolcall {{ run.canitoolcall_version }}
Strategies
{{ run.run.strategies|join(", ") }} (normalization {{ run.run.normalization }}){% if run.run.synthetic_strategies %}; not counted for this engine: {{ run.run.synthetic_strategies|join(", ") }}{% endif %}
Fixtures digest
{{ run.run.fixtures_digest }} {% if have_corpus %} {% if digest_matches %}the fixture corpus used for this site matches the run {% else %}the fixture corpus has changed since this run; raw outputs below are the current versions{% endif %} {% endif %}
{% if run.engine.details %}
Engine details
{{ run.engine.details|pretty }}
{% endif %} {% if data_file %}
Results file
{{ data_file }}
{% endif %}
{% if corpus_note %}

{{ corpus_note }}

{% endif %}

Checks

{% if cell.checks %}
{% for k in cell.checks %} {% endfor %}
Per fixture, the worst result of each check over the non-streaming parse and every realistic chunking strategy.
CheckPassSoft FailErrorStrict pass rate
{{ k.check }} {{ k.counts["pass"] }} {{ k.counts["soft_pass"] }} {{ k.counts["fail"] }} {{ k.counts["error"] }} {{ k.pass_rate|pct }}
{% else %}

No checks applied (no supported fixtures).

{% endif %} {% if skipped %}

Strategies the worker could not run (not counted):

{% endif %} {% if cell.stress_failures %}

{{ cell.stress_failures }} fixture(s) failed only a synthetic strategy: char:* (which can split special tokens){% if cell.multi_token_synthetic %}, or a multi-token strategy this engine never produces because its server streams one token per event ({% for s in cell.multi_token_synthetic %}{{ s }}{% if not loop.last %}, {% endif %}{% endfor %}){% endif %}. These are listed below but never count toward the status.

{% endif %}

Fixtures needing attention

{% set attention = views|rejectattr("status", "equalto", "unsupported")|list %} {% set unsupported = views|selectattr("status", "equalto", "unsupported")|list %} {% if not attention %}

Every supported fixture passed strictly on every realistic strategy.

{% endif %} {% for v in attention %}
{{ badge(v.status) }} {{ v.fixture_id }} {% set names = v.failing|map(attribute="check")|unique|list %} {% if names %}{{ names|join(", ") }}{% endif %}
{% if v.failing %} {% for c in v.failing %} {% endfor %}
Checks that did not pass for {{ v.fixture_id }}
CheckStrategyResultDetail
{{ c.check }}{{ c.strategy }}{{ badge(c.status) }}{{ c.detail or "" }}
{% endif %} {% if v.stress %}

Synthetic strategies (not counted): {% for c in v.stress %}{{ c.check }}@{{ c.strategy }} {{ c.status|label }}{% if not loop.last %}, {% endif %}{% endfor %}

{% endif %} {% if v.skipped %}

Skipped strategies: {% for s, r in v.skipped.items() %}{{ s }} ({{ r }}){% if not loop.last %}, {% endif %}{% endfor %}

{% endif %} {% if v.harness_error %}

Harness error

{{ v.harness_error }}
{% endif %}

Minimal repro

{{ v.repro }}

Set up the engine first with scripts/engines/{{ cell.engine }}.sh; this run used {{ run.engine.name }} {{ run.engine.version }}. {% if v.fixture and v.fixture.source %}The fixture is line {{ v.fixture.line }} of {{ v.fixture.source }}.{% endif %}

{% if v.outcomes %}

Observed {% if v.fixture and v.fixture.expected_json %}vs expected{% endif %}

Identical parses are grouped. Empty strings are shown as null, as in strict comparison.

{% for o in v.outcomes %}

Strategies: {% for s in o.strategies %}{{ s }}{% if not loop.last %}, {% endif %}{% endfor %}

{% if o.diff %}
{% for cls, line in o.diff %}{{ line }}
{% endfor %}
{% else %} {% if o.matches_expected %}

Matches the expected parse.

{% endif %}
{{ o.observed_json }}
{% endif %}
{% endfor %} {% else %}

The results file does not include the observed parses for this fixture.

{% endif %} {% if v.fixture %}

Fixture

Provenance: {{ v.fixture.provenance_kind }}, {% if v.fixture.provenance_url %}{{ v.fixture.provenance_url }}{% else %}{{ v.fixture.provenance_text }}{% endif %}. Tags: {% for t in v.fixture.tags %}{{ t }}{% if not loop.last %}, {% endif %}{% else %}none{% endfor %}.

{% if v.fixture.expected_error %}

Expected graceful failure: {{ v.fixture.expected_error }}.

{% endif %}

Raw output

{{ v.fixture.raw_output }}
{% if v.fixture.expected_json %}

Expected parse

{{ v.fixture.expected_json }}
{% endif %}
Fixture record (JSONL, ready to vendor into an engine's tests)
{{ v.fixture.record_jsonl }}
{% endif %} {% if v.parser_config_json %}
Parser configuration
{{ v.parser_config_json }}
{% endif %}
{% endfor %} {% if unsupported %}

Unsupported fixtures

The adapter declined these fixtures because this engine version has no parser for the family or model.

{% endif %}
{{ legend() }} {% endblock %}