simt-dev 0.7.0 → 0.8.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +191 -870
- package/README.md +188 -213
- package/bin/simt.mjs +19 -55
- package/docs/decisions/ADR-014-workspace-is-configuration.md +2 -2
- package/docs/decisions/ADR-025-a-baseline-is-a-region-in-a-file-the-repo-owns.md +1 -1
- package/docs/decisions/ADR-026-a-config-without-a-region-is-a-file-the-repo-owns.md +1 -1
- package/docs/decisions/ADR-027-the-one-gitattributes-line-that-is-neither-dangerous-nor-empty.md +1 -1
- package/docs/decisions/ADR-028-a-base-file-is-a-floor-so-the-disagreement-it-cannot-repair-becomes-a-check.md +1 -1
- package/docs/decisions/ADR-029-the-pins-a-repository-declares-are-its-own.md +1 -1
- package/docs/decisions/ADR-030-what-a-plan-does-not-ship-is-a-decision-with-a-record.md +1 -1
- package/docs/decisions/ADR-048-a-baseline-carries-only-keys-a-reader-honours.md +1 -1
- package/docs/decisions/ADR-082-the-tracker-override-is-a-manifest-key.md +1 -1
- package/docs/decisions/ADR-099-the-release-verifies-served-bytes-and-the-formula-mirrors-them.md +1 -1
- package/docs/decisions/ADR-117-the-darwin-release-builds-on-supported-macos-15-runners-and-a-re-run-is-idempotent.md +81 -0
- package/docs/decisions/ADR-118-the-bench-corpus-is-keyed-on-history-is-append-only-and-is-portable-as-a-sealed-document.md +91 -0
- package/docs/decisions/ADR-119-the-environment-variable-points-into-a-workspace-the-repo-declared.md +90 -0
- package/docs/decisions/ADR-120-a-pre-push-whose-tree-is-already-proven-green-skips-the-test-gate-on-that-evidence.md +96 -0
- package/docs/decisions/ADR-122-the-shims-move-into-the-state-directory-and-the-legacy-directory-removes-itself.md +94 -0
- package/docs/decisions/ADR-123-a-surplus-positional-is-not-refused-because-arity-is-not-in-the-source.md +57 -0
- package/docs/decisions/ADR-124-the-manifest-has-a-schema-in-the-tool-and-its-unknown-keys-stay-the-repositorys.md +64 -0
- package/docs/decisions/ADR-125-a-shared-context-belongs-to-a-read-and-a-writer-reads-directly.md +65 -0
- package/docs/decisions/ADR-126-the-mcp-surface-stays-a-reader-so-there-is-no-write-path-to-build.md +68 -0
- package/docs/decisions/ADR-127-the-mcp-tool-list-is-written-by-hand-and-roots-is-not-asked-for.md +65 -0
- package/docs/decisions/ADR-128-a-research-plan-is-a-plan-and-the-tracker-reads-it.md +42 -0
- package/ecosystems/bun.json +6 -0
- package/ecosystems/cargo.json +25 -0
- package/ecosystems/composer.json +6 -0
- package/ecosystems/dart.json +24 -0
- package/ecosystems/deno.json +21 -0
- package/ecosystems/devcontainers.json +6 -0
- package/ecosystems/docker-compose.json +6 -0
- package/ecosystems/docker.json +6 -0
- package/ecosystems/dotnet.json +25 -0
- package/ecosystems/elixir.json +23 -0
- package/ecosystems/gitsubmodule.json +6 -0
- package/ecosystems/go.json +25 -0
- package/ecosystems/gradle.json +13 -0
- package/ecosystems/maven.json +23 -0
- package/ecosystems/node.json +25 -0
- package/ecosystems/python.json +20 -0
- package/ecosystems/ruby.json +23 -0
- package/ecosystems/swift.json +25 -0
- package/ecosystems/terraform.json +6 -0
- package/ecosystems/uv.json +6 -0
- package/harnesses/antigravity.json +162 -0
- package/harnesses/claude.json +206 -0
- package/harnesses/codex.json +136 -0
- package/harnesses/copilot.json +88 -0
- package/harnesses/cursor.json +140 -0
- package/harnesses/deepseek.json +99 -0
- package/harnesses/gemini.json +122 -0
- package/harnesses/opencode.json +173 -0
- package/package.json +12 -2
- package/rules/core.md +7 -0
- package/rules/mdc/intake-questions.mdc +8 -0
- package/rules/mdc/slice-commit.mdc +57 -4
- package/src/advice/advice.mjs +3 -2
- package/src/agenthooks/prompt.mjs +5 -2
- package/src/agenthooks/render.mjs +86 -180
- package/src/agenthooks/shim.mjs +1 -1
- package/src/agents/render.mjs +15 -18
- package/src/api.mjs +31 -0
- package/src/argv.mjs +48 -3
- package/src/bench/ablate.mjs +3 -4
- package/src/bench/adapters.json +163 -105
- package/src/bench/adapters.mjs +466 -0
- package/src/bench/arms.mjs +333 -0
- package/src/bench/grade.mjs +33 -73
- package/src/bench/graders.mjs +42 -0
- package/src/bench/mine.mjs +121 -475
- package/src/bench/probe-ledger.mjs +149 -0
- package/src/bench/probes.catalog.mjs +918 -0
- package/src/bench/probes.mjs +79 -1064
- package/src/bench/render.mjs +111 -0
- package/src/bench/report.mjs +120 -962
- package/src/bench/run.mjs +185 -802
- package/src/bench/variants.mjs +4 -5
- package/src/bench/workspace.mjs +160 -0
- package/src/brief/assemble.mjs +48 -15
- package/src/ci/dependabot.mjs +25 -55
- package/src/ci/workflow.mjs +30 -7
- package/src/cli.mjs +45 -0
- package/src/commands/agent.mjs +4 -13
- package/src/commands/agenthook.mjs +70 -40
- package/src/commands/bench.mjs +191 -18
- package/src/commands/brief.mjs +5 -4
- package/src/commands/ci.mjs +13 -14
- package/src/commands/compare.mjs +42 -42
- package/src/commands/completions.mjs +2 -6
- package/src/commands/decide.mjs +4 -4
- package/src/commands/distill.mjs +4 -3
- package/src/commands/docs.mjs +88 -0
- package/src/commands/doctor.mjs +11 -7
- package/src/commands/evidence.mjs +6 -9
- package/src/commands/explain.mjs +0 -1
- package/src/commands/gate.mjs +26 -25
- package/src/commands/graph.mjs +2 -3
- package/src/commands/harness.mjs +6 -5
- package/src/commands/help.mjs +168 -19
- package/src/commands/hooks.mjs +119 -49
- package/src/commands/ignore.mjs +13 -8
- package/src/commands/impact.mjs +8 -15
- package/src/commands/index.mjs +318 -193
- package/src/commands/init-scan.mjs +90 -0
- package/src/commands/init.mjs +124 -105
- package/src/commands/lease.mjs +73 -25
- package/src/commands/lessons.mjs +10 -9
- package/src/commands/local.mjs +3 -3
- package/src/commands/map.mjs +24 -14
- package/src/commands/mcp.mjs +2 -18
- package/src/commands/pack.mjs +9 -6
- package/src/commands/plan.mjs +6 -5
- package/src/commands/plugin.mjs +2 -2
- package/src/commands/prbody.mjs +3 -3
- package/src/commands/repoindex.mjs +12 -11
- package/src/commands/review.mjs +2 -2
- package/src/commands/rules.mjs +37 -16
- package/src/commands/shared.mjs +14 -19
- package/src/commands/skills.mjs +33 -32
- package/src/commands/skillscompile.mjs +7 -8
- package/src/commands/skillsinstall.mjs +7 -6
- package/src/commands/slice.mjs +220 -74
- package/src/commands/spec.mjs +167 -0
- package/src/commands/status.mjs +27 -18
- package/src/commands/sync.mjs +27 -25
- package/src/commands/tests.mjs +18 -21
- package/src/commands/tokens.mjs +21 -26
- package/src/commands/undo.mjs +5 -15
- package/src/commands/upgrade.mjs +15 -7
- package/src/commands/why.mjs +15 -21
- package/src/compare/hooksstate.mjs +2 -6
- package/src/compare/learn.mjs +3 -1
- package/src/compare/row.mjs +0 -2
- package/src/context.mjs +64 -0
- package/src/decisions/index-doc.mjs +46 -0
- package/src/decisions/index.mjs +3 -2
- package/src/diff.mjs +1 -1
- package/src/distill/distill.mjs +14 -1
- package/src/distill/engine.mjs +5 -1
- package/src/docs/commands.mjs +65 -0
- package/src/ecosystem/records.mjs +219 -0
- package/src/explain.mjs +31 -0
- package/src/gates/index.mjs +385 -0
- package/src/graph/compile.mjs +8 -4
- package/src/graph/load.mjs +6 -2
- package/src/graph/spec.mjs +10 -8
- package/src/harness/records.mjs +143 -0
- package/src/hooks/capability.mjs +7 -5
- package/src/hooks/dispatcher.mjs +209 -60
- package/src/hooks/gates.mjs +10 -43
- package/src/hooks/resolve.mjs +4 -14
- package/src/hooks/shim.mjs +5 -2
- package/src/hooks/where.mjs +2 -7
- package/src/identity.mjs +31 -12
- package/src/index/coverage.mjs +58 -0
- package/src/index/extract.mjs +6 -16
- package/src/index/gate.mjs +1 -1
- package/src/index/govern.mjs +26 -9
- package/src/index/impact.mjs +4 -8
- package/src/index/map.mjs +14 -15
- package/src/index/open.mjs +173 -0
- package/src/index/persist.mjs +224 -57
- package/src/index/store.mjs +82 -39
- package/src/index/tests.mjs +2 -6
- package/src/journal.mjs +94 -20
- package/src/kernel/card.mjs +37 -63
- package/src/kernel/checks.mjs +4 -10
- package/src/lease.mjs +102 -7
- package/src/ledger/index.mjs +150 -14
- package/src/local/client.mjs +4 -6
- package/src/locate.mjs +33 -9
- package/src/manifest/schema.mjs +213 -0
- package/src/mcp/paginate.mjs +33 -0
- package/src/mcp/resources.mjs +7 -10
- package/src/mcp/schemas.mjs +512 -0
- package/src/mcp/server.mjs +119 -25
- package/src/mcp/tools-facts.mjs +326 -0
- package/src/mcp/tools-read.mjs +221 -0
- package/src/mcp/tools.mjs +4 -967
- package/src/measure/corpus.mjs +150 -0
- package/src/measure/metrics.mjs +236 -0
- package/src/measure/records.mjs +211 -0
- package/src/measure/session.mjs +3 -2
- package/src/measure/stats.mjs +538 -0
- package/src/measure/task-schema.mjs +125 -0
- package/src/measure/tasks.mjs +69 -0
- package/src/memory/decide.mjs +6 -15
- package/src/memory/lesson-text.mjs +61 -0
- package/src/memory/lessons.mjs +29 -82
- package/src/name.mjs +7 -0
- package/src/node-version.mjs +37 -0
- package/src/output/index.mjs +209 -10
- package/src/packs/manage.mjs +32 -12
- package/src/packs.mjs +20 -2
- package/src/plan/index.mjs +1 -1
- package/src/plugins.mjs +22 -16
- package/src/prbody.mjs +7 -11
- package/src/projection/loaders.mjs +7 -692
- package/src/projection/lock.mjs +11 -1
- package/src/projection/manifest.mjs +29 -468
- package/src/projection/mdc.mjs +7 -8
- package/src/projection/project.mjs +126 -221
- package/src/projection/region.mjs +561 -0
- package/src/projection/rules.mjs +20 -550
- package/src/projection/surfaces.mjs +43 -210
- package/src/projection/targets.mjs +5 -5
- package/src/repo-root.mjs +31 -0
- package/src/resolve/eval.mjs +2 -1
- package/src/resolve/fingerprint.mjs +19 -22
- package/src/resolve/resolve.mjs +1 -41
- package/src/review/critic.mjs +10 -13
- package/src/run.mjs +98 -0
- package/src/secrets.mjs +14 -22
- package/src/state/events.mjs +129 -0
- package/src/status-snapshot.mjs +233 -0
- package/src/status.mjs +2 -6
- package/src/sys/git.mjs +82 -0
- package/src/sys/proc.mjs +151 -0
- package/src/testing/parsers.mjs +265 -0
- package/src/testing/patches.mjs +23 -0
- package/src/testing/paths.mjs +49 -0
- package/src/testing/runners.mjs +186 -0
- package/src/testing/vault.mjs +68 -0
- package/src/text/frontmatter.mjs +49 -0
- package/src/text/tokens.mjs +52 -0
- package/src/toolwords.mjs +3 -0
- package/src/util/fs.mjs +20 -0
- package/src/util/sort.mjs +12 -0
- package/src/workspace.mjs +58 -11
- package/src/write/plan.mjs +82 -0
- package/templates/plan/tracker.json +1 -0
- package/docs/decisions/ADR-033-three-plan-rows-closed-by-decision-not-by-authoring.md +0 -82
- package/docs/decisions/ADR-102-the-two-queued-review-rows-are-closed-by-ruling.md +0 -49
- package/docs/decisions/README.md +0 -600
- package/src/bench/tasks.mjs +0 -36
package/src/bench/adapters.json
CHANGED
|
@@ -1,149 +1,207 @@
|
|
|
1
1
|
{
|
|
2
|
-
"schemaVersion":
|
|
2
|
+
"schemaVersion": 2,
|
|
3
3
|
"adapters": {
|
|
4
4
|
"claude": {
|
|
5
5
|
"id": "claude",
|
|
6
6
|
"label": "Claude Code",
|
|
7
|
-
"kind": "
|
|
7
|
+
"kind": "agent",
|
|
8
8
|
"bin": "claude",
|
|
9
|
-
"
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
|
|
13
|
-
|
|
14
|
-
"
|
|
15
|
-
|
|
16
|
-
|
|
17
|
-
|
|
18
|
-
"
|
|
19
|
-
"
|
|
20
|
-
|
|
21
|
-
|
|
22
|
-
|
|
9
|
+
"prompt": {
|
|
10
|
+
"delivery": "argv",
|
|
11
|
+
"args": ["-p", "{prompt}", "--output-format", "json", "--max-turns", "{turns}"],
|
|
12
|
+
"modelArgs": ["--model", "{model}"]
|
|
13
|
+
},
|
|
14
|
+
"env": { "allow": ["ANTHROPIC_API_KEY"] },
|
|
15
|
+
"isolation": "env",
|
|
16
|
+
"timeoutMs": 120000,
|
|
17
|
+
"usage": {
|
|
18
|
+
"format": "json",
|
|
19
|
+
"fields": {
|
|
20
|
+
"input": ["usage.input_tokens", "usage.input"],
|
|
21
|
+
"cacheWrite": ["usage.cache_creation_input_tokens", "usage.cacheWrite"],
|
|
22
|
+
"cacheRead": ["usage.cache_read_input_tokens", "usage.cacheRead"],
|
|
23
|
+
"output": ["usage.output_tokens", "usage.output"],
|
|
24
|
+
"turns": ["num_turns", "usage.turns"],
|
|
25
|
+
"toolCalls": ["num_tool_calls", "tool_calls", "usage.toolCalls"],
|
|
26
|
+
"costUsd": ["total_cost_usd", "cost_usd", "costUsd"]
|
|
27
|
+
}
|
|
28
|
+
},
|
|
29
|
+
"transcript": { "sources": ["stdout"] }
|
|
23
30
|
},
|
|
24
31
|
"codex": {
|
|
25
32
|
"id": "codex",
|
|
26
33
|
"label": "Codex",
|
|
27
|
-
"kind": "
|
|
34
|
+
"kind": "agent",
|
|
28
35
|
"bin": "codex",
|
|
29
|
-
"
|
|
30
|
-
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
"
|
|
35
|
-
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
"
|
|
39
|
-
"
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
|
|
36
|
+
"prompt": {
|
|
37
|
+
"delivery": "argv",
|
|
38
|
+
"args": ["exec", "--json", "{prompt}"],
|
|
39
|
+
"modelArgs": ["--model", "{model}"]
|
|
40
|
+
},
|
|
41
|
+
"env": { "allow": ["OPENAI_API_KEY"] },
|
|
42
|
+
"isolation": "env",
|
|
43
|
+
"timeoutMs": 120000,
|
|
44
|
+
"usage": {
|
|
45
|
+
"format": "jsonl",
|
|
46
|
+
"fields": {
|
|
47
|
+
"input": ["usage.input_tokens", "input_tokens", "usage.input"],
|
|
48
|
+
"cacheWrite": ["usage.cache_creation_input_tokens", "usage.cache_write_input_tokens", "cache_write_input_tokens"],
|
|
49
|
+
"cacheRead": ["usage.cached_input_tokens", "usage.cache_read_input_tokens", "cached_input_tokens"],
|
|
50
|
+
"output": ["usage.output_tokens", "output_tokens", "usage.output"],
|
|
51
|
+
"turns": ["turns", "num_turns"],
|
|
52
|
+
"toolCalls": ["tool_calls", "num_tool_calls"],
|
|
53
|
+
"costUsd": ["total_cost_usd", "cost_usd", "cost"]
|
|
54
|
+
},
|
|
55
|
+
"events": {
|
|
56
|
+
"turns": [{ "type": "turn.completed" }],
|
|
57
|
+
"toolCalls": [
|
|
58
|
+
{ "type": "item.completed", "item.type": ["command_execution", "tool_call", "mcp_tool_call"] }
|
|
59
|
+
]
|
|
60
|
+
}
|
|
61
|
+
},
|
|
62
|
+
"transcript": { "sources": ["stdout"] }
|
|
43
63
|
},
|
|
44
64
|
"gemini": {
|
|
45
65
|
"id": "gemini",
|
|
46
66
|
"label": "Gemini CLI",
|
|
47
|
-
"kind": "
|
|
67
|
+
"kind": "agent",
|
|
48
68
|
"bin": "gemini",
|
|
49
|
-
"
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
"
|
|
55
|
-
|
|
56
|
-
|
|
57
|
-
|
|
58
|
-
"
|
|
59
|
-
"
|
|
60
|
-
|
|
61
|
-
|
|
62
|
-
|
|
69
|
+
"prompt": {
|
|
70
|
+
"delivery": "argv",
|
|
71
|
+
"args": ["-p", "{prompt}", "--output-format", "json"],
|
|
72
|
+
"modelArgs": ["--model", "{model}"]
|
|
73
|
+
},
|
|
74
|
+
"env": { "allow": ["GEMINI_API_KEY", "GOOGLE_API_KEY"] },
|
|
75
|
+
"isolation": "env",
|
|
76
|
+
"timeoutMs": 120000,
|
|
77
|
+
"usage": {
|
|
78
|
+
"format": "json",
|
|
79
|
+
"fields": {
|
|
80
|
+
"input": ["stats.inputTokens", "stats.tokens.prompt", "stats.prompt_tokens", "usage.input_tokens"],
|
|
81
|
+
"cacheWrite": ["stats.cacheWriteTokens", "stats.tokens.cacheWrite", "usage.cache_creation_input_tokens"],
|
|
82
|
+
"cacheRead": ["stats.cachedTokens", "stats.tokens.cached", "usage.cache_read_input_tokens"],
|
|
83
|
+
"output": ["stats.outputTokens", "stats.tokens.candidates", "stats.completion_tokens", "usage.output_tokens"],
|
|
84
|
+
"turns": ["stats.turns", "stats.totalTurns", "num_turns"],
|
|
85
|
+
"toolCalls": ["stats.toolCalls", "stats.tools.totalCalls", "num_tool_calls"],
|
|
86
|
+
"costUsd": ["stats.totalCostUsd", "stats.costUsd", "total_cost_usd"]
|
|
87
|
+
},
|
|
88
|
+
"totals": [
|
|
89
|
+
{
|
|
90
|
+
"root": "stats.models",
|
|
91
|
+
"keys": { "input": "tokens.prompt", "cacheRead": "tokens.cached", "output": "tokens.candidates" }
|
|
92
|
+
}
|
|
93
|
+
]
|
|
94
|
+
},
|
|
95
|
+
"transcript": { "sources": ["stdout"] }
|
|
63
96
|
},
|
|
64
97
|
"opencode": {
|
|
65
98
|
"id": "opencode",
|
|
66
99
|
"label": "opencode",
|
|
67
|
-
"kind": "
|
|
100
|
+
"kind": "agent",
|
|
68
101
|
"bin": "opencode",
|
|
69
|
-
"
|
|
70
|
-
|
|
71
|
-
|
|
72
|
-
|
|
73
|
-
|
|
74
|
-
"
|
|
75
|
-
|
|
76
|
-
|
|
77
|
-
|
|
78
|
-
"
|
|
79
|
-
"
|
|
80
|
-
|
|
81
|
-
|
|
82
|
-
|
|
102
|
+
"prompt": {
|
|
103
|
+
"delivery": "argv",
|
|
104
|
+
"args": ["run", "--format", "json", "{prompt}"],
|
|
105
|
+
"modelArgs": ["--model", "{model}"]
|
|
106
|
+
},
|
|
107
|
+
"env": { "allow": ["OPENAI_API_KEY", "ANTHROPIC_API_KEY"] },
|
|
108
|
+
"isolation": "env",
|
|
109
|
+
"timeoutMs": 120000,
|
|
110
|
+
"usage": {
|
|
111
|
+
"format": "jsonl",
|
|
112
|
+
"fields": {
|
|
113
|
+
"input": ["tokens.input", "usage.input_tokens", "part.tokens.input"],
|
|
114
|
+
"cacheWrite": ["tokens.cache.write", "usage.cache_creation_input_tokens", "part.tokens.cache.write"],
|
|
115
|
+
"cacheRead": ["tokens.cache.read", "usage.cache_read_input_tokens", "part.tokens.cache.read"],
|
|
116
|
+
"output": ["tokens.output", "usage.output_tokens", "part.tokens.output"],
|
|
117
|
+
"turns": ["turns", "num_turns"],
|
|
118
|
+
"toolCalls": ["toolCalls", "num_tool_calls"],
|
|
119
|
+
"costUsd": ["cost", "part.cost", "total_cost_usd"]
|
|
120
|
+
},
|
|
121
|
+
"events": {
|
|
122
|
+
"turns": [{ "type": "step_finish" }, { "event": "message_send" }],
|
|
123
|
+
"toolCalls": [{ "type": "tool_use" }]
|
|
124
|
+
}
|
|
125
|
+
},
|
|
126
|
+
"transcript": { "sources": ["stdout"] }
|
|
83
127
|
},
|
|
84
128
|
"cursor": {
|
|
85
129
|
"id": "cursor",
|
|
86
130
|
"label": "Cursor CLI",
|
|
87
|
-
"kind": "
|
|
131
|
+
"kind": "agent",
|
|
88
132
|
"bin": "cursor-agent",
|
|
89
|
-
"
|
|
90
|
-
|
|
91
|
-
|
|
92
|
-
|
|
93
|
-
|
|
94
|
-
"
|
|
95
|
-
|
|
96
|
-
|
|
97
|
-
|
|
98
|
-
"
|
|
99
|
-
"
|
|
100
|
-
|
|
101
|
-
|
|
102
|
-
|
|
133
|
+
"prompt": {
|
|
134
|
+
"delivery": "argv",
|
|
135
|
+
"args": ["-p", "{prompt}", "--output-format", "json"],
|
|
136
|
+
"modelArgs": ["--model", "{model}"]
|
|
137
|
+
},
|
|
138
|
+
"env": { "allow": ["CURSOR_API_KEY"] },
|
|
139
|
+
"isolation": "env",
|
|
140
|
+
"timeoutMs": 120000,
|
|
141
|
+
"usage": {
|
|
142
|
+
"format": "json",
|
|
143
|
+
"fields": {
|
|
144
|
+
"input": ["usage.input_tokens", "usage.input", "stats.inputTokens"],
|
|
145
|
+
"cacheWrite": ["usage.cache_creation_input_tokens", "usage.cacheWrite", "stats.cacheWriteTokens"],
|
|
146
|
+
"cacheRead": ["usage.cache_read_input_tokens", "usage.cacheRead", "stats.cachedTokens"],
|
|
147
|
+
"output": ["usage.output_tokens", "usage.output", "stats.outputTokens"],
|
|
148
|
+
"turns": ["num_turns", "turns", "usage.turns"],
|
|
149
|
+
"toolCalls": ["num_tool_calls", "tool_calls", "usage.toolCalls", "toolCalls"],
|
|
150
|
+
"costUsd": ["total_cost_usd", "costUsd", "cost_usd"]
|
|
151
|
+
}
|
|
152
|
+
},
|
|
153
|
+
"transcript": { "sources": ["stdout"] }
|
|
103
154
|
},
|
|
104
155
|
"aider": {
|
|
105
156
|
"id": "aider",
|
|
106
157
|
"label": "Aider",
|
|
107
|
-
"kind": "
|
|
158
|
+
"kind": "agent",
|
|
108
159
|
"bin": "aider",
|
|
109
|
-
"
|
|
110
|
-
|
|
111
|
-
|
|
112
|
-
|
|
113
|
-
|
|
114
|
-
"
|
|
115
|
-
|
|
116
|
-
|
|
117
|
-
|
|
118
|
-
"
|
|
119
|
-
"
|
|
120
|
-
|
|
121
|
-
|
|
122
|
-
|
|
160
|
+
"prompt": {
|
|
161
|
+
"delivery": "argv",
|
|
162
|
+
"args": ["--message", "{prompt}", "--yes-always", "--analytics-log", "{analyticsLog}"],
|
|
163
|
+
"modelArgs": ["--model", "{model}"]
|
|
164
|
+
},
|
|
165
|
+
"env": { "allow": ["OPENAI_API_KEY", "ANTHROPIC_API_KEY"] },
|
|
166
|
+
"isolation": "env",
|
|
167
|
+
"timeoutMs": 120000,
|
|
168
|
+
"usage": {
|
|
169
|
+
"format": "analytics-log",
|
|
170
|
+
"fields": {
|
|
171
|
+
"input": ["prompt_tokens", "properties.prompt_tokens", "usage.input_tokens"],
|
|
172
|
+
"cacheWrite": ["cache_creation_input_tokens", "properties.cache_write_tokens"],
|
|
173
|
+
"cacheRead": ["cache_read_input_tokens", "properties.cache_read_tokens"],
|
|
174
|
+
"output": ["completion_tokens", "properties.completion_tokens", "usage.output_tokens"],
|
|
175
|
+
"turns": ["turns", "properties.turns"],
|
|
176
|
+
"toolCalls": ["tool_calls", "properties.tool_calls"],
|
|
177
|
+
"costUsd": ["cost", "total_cost", "properties.cost", "properties.total_cost"]
|
|
178
|
+
}
|
|
179
|
+
},
|
|
180
|
+
"transcript": { "sources": ["stdout", "analytics"] }
|
|
123
181
|
},
|
|
124
182
|
"gold": {
|
|
125
183
|
"id": "gold",
|
|
126
184
|
"label": "Gold Oracle",
|
|
127
|
-
"kind": "
|
|
185
|
+
"kind": "oracle",
|
|
186
|
+
"oracle": { "from": "vault" },
|
|
128
187
|
"bin": null,
|
|
129
|
-
"
|
|
130
|
-
"
|
|
131
|
-
"
|
|
132
|
-
"format": "
|
|
133
|
-
"
|
|
134
|
-
"fields": {}
|
|
188
|
+
"prompt": { "delivery": "argv", "args": [], "modelArgs": [] },
|
|
189
|
+
"env": { "allow": [] },
|
|
190
|
+
"isolation": "none",
|
|
191
|
+
"usage": { "format": "none", "fields": {}, "fixed": { "turns": 1, "toolCalls": 1 } },
|
|
192
|
+
"transcript": { "sources": [] }
|
|
135
193
|
},
|
|
136
194
|
"noop": {
|
|
137
195
|
"id": "noop",
|
|
138
196
|
"label": "No-op Baseline",
|
|
139
|
-
"kind": "
|
|
197
|
+
"kind": "oracle",
|
|
198
|
+
"oracle": { "from": "none" },
|
|
140
199
|
"bin": null,
|
|
141
|
-
"
|
|
142
|
-
"
|
|
143
|
-
"
|
|
144
|
-
"format": "
|
|
145
|
-
"
|
|
146
|
-
"fields": {}
|
|
200
|
+
"prompt": { "delivery": "argv", "args": [], "modelArgs": [] },
|
|
201
|
+
"env": { "allow": [] },
|
|
202
|
+
"isolation": "none",
|
|
203
|
+
"usage": { "format": "none", "fields": {} },
|
|
204
|
+
"transcript": { "sources": [] }
|
|
147
205
|
}
|
|
148
206
|
}
|
|
149
207
|
}
|