@evolvingmachines/evolve 0.0.65 → 0.0.67

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.
Files changed (152) hide show
  1. package/dist/{chunk-DK2MGUPB.js → chunk-RFLMRPGK.js} +5 -5
  2. package/dist/cli/index.cjs +39 -39
  3. package/dist/cli/index.d.cts +3 -3
  4. package/dist/cli/index.d.ts +3 -3
  5. package/dist/cli/index.js +30 -30
  6. package/dist/index.cjs +1 -1
  7. package/dist/index.d.cts +4 -4
  8. package/dist/index.d.ts +4 -4
  9. package/dist/index.js +1 -1
  10. package/dist/{types-B_qmzlMk.d.cts → types-84M4J_Vm.d.cts} +11 -44
  11. package/dist/{types-B_qmzlMk.d.ts → types-84M4J_Vm.d.ts} +11 -44
  12. package/package.json +4 -4
  13. package/skills/create-adapter/SKILL.md +71 -26
  14. package/skills/create-task/SKILL.md +124 -66
  15. package/skills/evolve/SKILL.md +37 -20
  16. package/skills/evolve-evals/SKILL.md +142 -69
  17. package/skills/evolve-evals/references/cli-reference/agent.md +76 -0
  18. package/skills/evolve-evals/references/cli-reference/analysis.md +78 -0
  19. package/skills/evolve-evals/references/cli-reference/analyze.md +95 -0
  20. package/skills/evolve-evals/references/cli-reference/auth.md +96 -0
  21. package/skills/evolve-evals/references/cli-reference/check.md +156 -0
  22. package/skills/evolve-evals/references/cli-reference/dataset.md +154 -0
  23. package/skills/evolve-evals/references/cli-reference/filesystem.md +168 -0
  24. package/skills/evolve-evals/references/cli-reference/index.md +149 -0
  25. package/skills/evolve-evals/references/cli-reference/job.md +198 -0
  26. package/skills/evolve-evals/references/cli-reference/run.md +187 -0
  27. package/skills/evolve-evals/references/cli-reference/secrets.md +77 -0
  28. package/skills/evolve-evals/references/cli-reference/session.md +56 -0
  29. package/skills/evolve-evals/references/cli-reference/skill.md +52 -0
  30. package/skills/evolve-evals/references/cli-reference/skills.md +85 -0
  31. package/skills/evolve-evals/references/cli-reference/trial.md +115 -0
  32. package/skills/evolve-evals/references/cli-reference/upload.md +72 -0
  33. package/skills/evolve-evals/references/core-concepts/agents.md +96 -0
  34. package/skills/evolve-evals/references/core-concepts/analyze.md +143 -0
  35. package/skills/evolve-evals/references/core-concepts/check.md +116 -0
  36. package/skills/evolve-evals/references/core-concepts/compatibility.md +39 -0
  37. package/skills/evolve-evals/references/core-concepts/compose.md +103 -0
  38. package/skills/evolve-evals/references/core-concepts/datasets.md +234 -0
  39. package/skills/evolve-evals/references/core-concepts/index.md +52 -0
  40. package/skills/evolve-evals/references/core-concepts/jobs.md +223 -0
  41. package/skills/evolve-evals/references/core-concepts/models.md +73 -0
  42. package/skills/evolve-evals/references/core-concepts/multi-step.md +93 -0
  43. package/skills/evolve-evals/references/core-concepts/rewardkit.md +341 -0
  44. package/skills/evolve-evals/references/core-concepts/sandboxes.md +73 -0
  45. package/skills/evolve-evals/references/core-concepts/secrets.md +86 -0
  46. package/skills/evolve-evals/references/core-concepts/sharing.md +81 -0
  47. package/skills/evolve-evals/references/core-concepts/skills.md +100 -0
  48. package/skills/evolve-evals/references/core-concepts/task-config.md +169 -0
  49. package/skills/evolve-evals/references/core-concepts/task-environment.md +127 -0
  50. package/skills/evolve-evals/references/core-concepts/task-reference.md +191 -0
  51. package/skills/evolve-evals/references/core-concepts/task-verifiers.md +209 -0
  52. package/skills/evolve-evals/references/core-concepts/tasks.md +90 -0
  53. package/skills/evolve-evals/references/core-concepts/teams.md +128 -0
  54. package/skills/evolve-evals/references/core-concepts/trial-outputs.md +225 -0
  55. package/skills/evolve-evals/references/core-concepts/trials.md +129 -0
  56. package/skills/evolve-evals/references/core-concepts/upload-sdk-session.md +240 -0
  57. package/skills/evolve-evals/references/core-concepts/upload.md +166 -0
  58. package/skills/evolve-evals/references/dashboard/checks.md +54 -0
  59. package/skills/evolve-evals/references/dashboard/datasets.md +65 -0
  60. package/skills/evolve-evals/references/dashboard/jobs.md +106 -0
  61. package/skills/evolve-evals/references/dashboard/traces.md +54 -0
  62. package/skills/evolve-evals/references/dashboard/trial-viewer.md +77 -0
  63. package/skills/evolve-evals/references/getting-started/first-task.md +228 -0
  64. package/skills/evolve-evals/references/getting-started/installation.md +79 -0
  65. package/skills/evolve-evals/references/getting-started/quick-start.md +100 -0
  66. package/skills/evolve-evals/references/index.md +58 -0
  67. package/skills/evolve-evals/references/sdk/http.md +110 -0
  68. package/skills/evolve-evals/references/sdk/python.md +108 -0
  69. package/skills/evolve-evals/references/sdk/typescript.md +104 -0
  70. package/skills/evolve-evals/references/sdk-reference/agents.md +75 -0
  71. package/skills/evolve-evals/references/sdk-reference/analyses.md +124 -0
  72. package/skills/evolve-evals/references/sdk-reference/auth.md +171 -0
  73. package/skills/evolve-evals/references/sdk-reference/checks.md +145 -0
  74. package/skills/evolve-evals/references/sdk-reference/datasets.md +170 -0
  75. package/skills/evolve-evals/references/sdk-reference/error-codes.md +231 -0
  76. package/skills/evolve-evals/references/sdk-reference/errors.md +98 -0
  77. package/skills/evolve-evals/references/sdk-reference/filesystem.md +166 -0
  78. package/skills/evolve-evals/references/sdk-reference/index.md +161 -0
  79. package/skills/evolve-evals/references/sdk-reference/jobs.md +250 -0
  80. package/skills/evolve-evals/references/sdk-reference/meta.md +54 -0
  81. package/skills/evolve-evals/references/sdk-reference/methods/agents.md +154 -0
  82. package/skills/evolve-evals/references/sdk-reference/methods/analyses.md +211 -0
  83. package/skills/evolve-evals/references/sdk-reference/methods/auth.md +257 -0
  84. package/skills/evolve-evals/references/sdk-reference/methods/checks.md +460 -0
  85. package/skills/evolve-evals/references/sdk-reference/methods/datasets.md +687 -0
  86. package/skills/evolve-evals/references/sdk-reference/methods/filesystem.md +527 -0
  87. package/skills/evolve-evals/references/sdk-reference/methods/jobs.md +1021 -0
  88. package/skills/evolve-evals/references/sdk-reference/methods/meta.md +209 -0
  89. package/skills/evolve-evals/references/sdk-reference/methods/secrets.md +157 -0
  90. package/skills/evolve-evals/references/sdk-reference/methods/skills.md +125 -0
  91. package/skills/evolve-evals/references/sdk-reference/methods/trials.md +371 -0
  92. package/skills/evolve-evals/references/sdk-reference/secrets.md +104 -0
  93. package/skills/evolve-evals/references/sdk-reference/skills.md +66 -0
  94. package/skills/evolve-evals/references/sdk-reference/trials.md +164 -0
  95. package/skills/evolve-evals/references/sdk-reference/types.md +1249 -0
  96. package/skills/publish/SKILL.md +103 -79
  97. package/skills/rewardkit/SKILL.md +78 -23
  98. package/spec/openapi.yaml +19 -74
  99. package/skills/evolve-evals/references/cli-reference/agent.mdx +0 -79
  100. package/skills/evolve-evals/references/cli-reference/analysis.mdx +0 -160
  101. package/skills/evolve-evals/references/cli-reference/analyze.mdx +0 -84
  102. package/skills/evolve-evals/references/cli-reference/auth.mdx +0 -133
  103. package/skills/evolve-evals/references/cli-reference/check.mdx +0 -263
  104. package/skills/evolve-evals/references/cli-reference/dataset.mdx +0 -151
  105. package/skills/evolve-evals/references/cli-reference/index.mdx +0 -108
  106. package/skills/evolve-evals/references/cli-reference/job.mdx +0 -278
  107. package/skills/evolve-evals/references/cli-reference/run.mdx +0 -204
  108. package/skills/evolve-evals/references/cli-reference/secrets.mdx +0 -95
  109. package/skills/evolve-evals/references/cli-reference/skill.mdx +0 -61
  110. package/skills/evolve-evals/references/cli-reference/skills.mdx +0 -81
  111. package/skills/evolve-evals/references/cli-reference/trial.mdx +0 -181
  112. package/skills/evolve-evals/references/cli-reference/upload.mdx +0 -36
  113. package/skills/evolve-evals/references/core-concepts/agents.mdx +0 -106
  114. package/skills/evolve-evals/references/core-concepts/analyze.mdx +0 -86
  115. package/skills/evolve-evals/references/core-concepts/check.mdx +0 -64
  116. package/skills/evolve-evals/references/core-concepts/datasets.mdx +0 -138
  117. package/skills/evolve-evals/references/core-concepts/index.mdx +0 -42
  118. package/skills/evolve-evals/references/core-concepts/jobs.mdx +0 -151
  119. package/skills/evolve-evals/references/core-concepts/models.mdx +0 -68
  120. package/skills/evolve-evals/references/core-concepts/sandboxes.mdx +0 -52
  121. package/skills/evolve-evals/references/core-concepts/secrets.mdx +0 -41
  122. package/skills/evolve-evals/references/core-concepts/sharing.mdx +0 -35
  123. package/skills/evolve-evals/references/core-concepts/skills.mdx +0 -42
  124. package/skills/evolve-evals/references/core-concepts/tasks.mdx +0 -216
  125. package/skills/evolve-evals/references/core-concepts/teams.mdx +0 -36
  126. package/skills/evolve-evals/references/core-concepts/trial-outputs.mdx +0 -117
  127. package/skills/evolve-evals/references/core-concepts/trials.mdx +0 -103
  128. package/skills/evolve-evals/references/core-concepts/upload.mdx +0 -93
  129. package/skills/evolve-evals/references/dashboard/checks.mdx +0 -21
  130. package/skills/evolve-evals/references/dashboard/datasets.mdx +0 -24
  131. package/skills/evolve-evals/references/dashboard/jobs.mdx +0 -65
  132. package/skills/evolve-evals/references/dashboard/traces.mdx +0 -17
  133. package/skills/evolve-evals/references/dashboard/trial-viewer.mdx +0 -30
  134. package/skills/evolve-evals/references/getting-started/installation.mdx +0 -56
  135. package/skills/evolve-evals/references/getting-started/quick-start.mdx +0 -94
  136. package/skills/evolve-evals/references/index.mdx +0 -48
  137. package/skills/evolve-evals/references/sdk/python.mdx +0 -161
  138. package/skills/evolve-evals/references/sdk/typescript.mdx +0 -163
  139. package/skills/evolve-evals/references/sdk-reference/agents.mdx +0 -108
  140. package/skills/evolve-evals/references/sdk-reference/analyses.mdx +0 -222
  141. package/skills/evolve-evals/references/sdk-reference/auth.mdx +0 -116
  142. package/skills/evolve-evals/references/sdk-reference/checks.mdx +0 -300
  143. package/skills/evolve-evals/references/sdk-reference/datasets.mdx +0 -346
  144. package/skills/evolve-evals/references/sdk-reference/errors.mdx +0 -210
  145. package/skills/evolve-evals/references/sdk-reference/index.mdx +0 -60
  146. package/skills/evolve-evals/references/sdk-reference/jobs.mdx +0 -822
  147. package/skills/evolve-evals/references/sdk-reference/meta.mdx +0 -52
  148. package/skills/evolve-evals/references/sdk-reference/skills.mdx +0 -69
  149. package/skills/evolve-evals/references/sdk-reference/trials.mdx +0 -302
  150. package/skills/evolve-evals/references/sdk-reference/types.mdx +0 -274
  151. package/skills/evolve-evals/references/snippets/global-options.mdx +0 -13
  152. package/skills/evolve-evals/references/snippets/list-flags.mdx +0 -23
@@ -1,79 +0,0 @@
1
- ---
2
- title: "evolve agent"
3
- description: "Register and manage your own agents."
4
- ---
5
-
6
- import GlobalOptions from '/snippets/global-options.mdx';
7
- import ListFlags from '/snippets/list-flags.mdx';
8
-
9
- ```bash
10
- evolve agent <command> [options]
11
- ```
12
-
13
- ## agent list
14
-
15
- ```bash
16
- evolve agent list [options]
17
- ```
18
-
19
- List registered agents.
20
-
21
- <ParamField path="--scope" type="my | shared | org">
22
- Visibility scope: `my`, your own registrations (the default); `shared`, your organizations' other members'; or `org`, every registration in your organizations.
23
- </ParamField>
24
-
25
- <ListFlags />
26
-
27
- ## agent show
28
-
29
- ```bash
30
- evolve agent show <name>
31
- ```
32
-
33
- Show a registered agent: your own of that name first, else the oldest of that name across the organizations you belong to. A name outside your organizations answers `agent_not_found`.
34
-
35
- ## agent add
36
-
37
- ```bash
38
- evolve agent add <name> [options]
39
- ```
40
-
41
- Register an agent from an install script or a local directory.
42
-
43
- The registration belongs to you and to an organization: its members may name the agent in their own jobs, and only you can change or delete it. A name stays unique per person, so two teammates may each register their own `acme-cli`.
44
-
45
- A registration that cannot be built — the script exits non-zero, or installs nothing executable (see [Registered agents](/core-concepts/agents)) — fails its trials as the agent's own error (`failure_phase` `agent_source`; the trial's stderr stream holds the install's output), never retried: `agent remove` it, `agent add` it again, and resume the job.
46
-
47
- <ParamField path="--org" type="name">
48
- Organization the registration belongs to. Default: the organization from `evolve auth org use`, else your personal one. It is fixed once set.
49
- </ParamField>
50
-
51
- <ParamField path="--install-script" type="path">
52
- Install script file. Its contents are uploaded.
53
- </ParamField>
54
-
55
- <ParamField path="--dir" type="path">
56
- Local agent directory, tarred and uploaded.
57
- </ParamField>
58
-
59
- <ParamField path="--run" type="command" required>
60
- Run command, executed with `sh -c`.
61
- </ParamField>
62
-
63
- <ParamField path="--ae, --agent-env" type="KEY=VALUE">
64
- Environment injected at run time. Repeatable. It may not override the six run-contract keys, and a credential-shaped key is refused, both with `agent_invalid_env`; see [the run contract](/core-concepts/agents#the-run-contract).
65
- </ParamField>
66
-
67
- ```bash
68
- evolve agent add acme-cli --install-script ./install.sh --run "acme-cli --headless"
69
- ```
70
-
71
- ## agent remove
72
-
73
- ```bash
74
- evolve agent remove <name>
75
- ```
76
-
77
- Delete a registered agent. Past jobs keep their record.
78
-
79
- <GlobalOptions />
@@ -1,160 +0,0 @@
1
- ---
2
- title: "evolve analysis"
3
- description: "List, inspect, and download trace-analysis runs."
4
- ---
5
-
6
- import GlobalOptions from '/snippets/global-options.mdx';
7
- import ListFlags from '/snippets/list-flags.mdx';
8
-
9
- ```bash
10
- evolve analysis <command> [options]
11
- ```
12
-
13
- `show`, `trace` and `download` take an analysis id, or a trial id. An analysis id (or its unambiguous prefix) names that run. A trial id (or prefix) names the trial's latest analysis, the one `trial show` prints on its analysis row. A prefix matching both an analysis and a trial is refused as ambiguous, naming both.
14
-
15
- A trial nobody analyzed is refused with the remedy, `evolve analyze <job>`, and so is a regrade result's id. An id you cannot read answers `analysis_not_found`; `download` on a run still queued or running answers `analysis_not_terminal`.
16
-
17
- ## analysis list
18
-
19
- ```bash
20
- evolve analysis list [options]
21
- ```
22
-
23
- List analysis runs, newest first, with the trial, job and task each one judged.
24
-
25
- <ListFlags />
26
-
27
- <ParamField path="--scope" type="my | shared">
28
- Visibility scope: `my`, what you created (the default), or `shared`, your organizations' rows that teammates created.
29
- </ParamField>
30
-
31
- <ParamField path="--job" type="job-id">
32
- Only analyses of this job's trials. An id, or an unambiguous prefix.
33
- </ParamField>
34
-
35
- <ParamField path="--status" type="s1,s2,...">
36
- Filter by analysis status: `queued`, `running`, `completed`, `failed`.
37
- </ParamField>
38
-
39
- ```bash
40
- evolve analysis list --job 3e1f9a2c-… --status failed
41
- ```
42
-
43
- ## analysis show
44
-
45
- ```bash
46
- evolve analysis show <analysis-id | trial-id>
47
- ```
48
-
49
- Show one analysis run in full: the verdict document.
50
-
51
- ## analysis trace
52
-
53
- ```bash
54
- evolve analysis trace <analysis-id | trial-id> [options]
55
- ```
56
-
57
- Print the analyzer's own parsed transcript.
58
-
59
- <ParamField path="--since" type="n">
60
- Skip the first N events. To resume, pass the count you already hold; sequence numbers are dense from 0, so N is also the next one.
61
- </ParamField>
62
-
63
- ## analysis download
64
-
65
- ```bash
66
- evolve analysis download <analysis-id | trial-id> [options]
67
- ```
68
-
69
- Save an analysis run as a trial folder plus `evolve.json`, or stream one artifact.
70
-
71
- <ParamField path="-o, --output-dir" type="dir" default="analyses/">
72
- Directory to save under. The run lands in `<dir>/analyze-<analyzed trial>__<7 chars>/`, the run's own folder name, read from the archive.
73
- </ParamField>
74
-
75
- <ParamField path="--overwrite">
76
- Replace an existing folder of the same name.
77
- </ParamField>
78
-
79
- <ParamField path="--stream" type="artifact">
80
- Print one artifact to stdout instead of saving: `analysis` (the verdict document), `trace-parsed`, `trace-stdout`, `trace-stderr` or `agent-home`.
81
- </ParamField>
82
-
83
- <ParamField path="--since" type="n">
84
- With `--stream trace-parsed`: skip the first N events.
85
- </ParamField>
86
-
87
- ```bash
88
- evolve analysis download a0a1b2c3-… --stream trace-stdout
89
- ```
90
-
91
- ## analysis files
92
-
93
- ```bash
94
- evolve analysis files <status|ls|cat|search|changes|archive> <analysis-id> [path] [options]
95
- ```
96
-
97
- The run's file system: while the box runs, `files` reads it as it changes; after the run, the same commands read the kept tree. `files status` says which you get.
98
-
99
- - `files status <analysis-id>` — `live`, `captured`, `capturing` (the kept tree is still being written) or `none`; the box, how change events arrive (`watcher`), and the capture record (`ready`, `incomplete` with what was left out, or `failed`).
100
- - `files ls <analysis-id> [path]` — one folder, sorted by name (default `/`). Each row shows the type, mode, size, mtime and name; `created (agent)` or `modified (verifier)` marks what the run changed and when, `image only` marks a file the run never touched (it lists but does not open on the kept tree).
101
- - `files cat <analysis-id> <path>` — the raw bytes of one file, to stdout. `--range bytes=a-b` (or `bytes=a-`, `bytes=-n`) reads a slice.
102
- - `files search <analysis-id> <text>` — every line matching the text, as `path:line: snippet`. `--path` narrows the search to one folder (the whole box takes seconds); `--regex` treats the text as a pattern; a `(truncated)` note means there was more.
103
- - `files changes <analysis-id>` — the files the run created, modified or removed, with the phase (`--phase agent|verifier`).
104
- - `files archive <analysis-id>` — a `.tar.gz` of one subtree (`--path`, default the whole tree) to stdout, or saved under `-o <dir>`. The kept tree's archive lists the files it does not carry in `MANIFEST.tsv`; while the box runs, a subtree too large to read out in time is refused (`feature_unsupported`).
105
-
106
- <ParamField path="--source" type="live|capture">
107
- Force the source. Without it, whichever the run has. A source that is not there is refused with `filesystem_state`.
108
- </ParamField>
109
-
110
- <ParamField path="-l, --limit" type="n">
111
- Page size on `ls`, `search` and `changes` (`ls`, `changes` default 500; `search` default 200; max 1000).
112
- </ParamField>
113
-
114
- <ParamField path="--cursor" type="c">
115
- Resume a paged `ls` or `changes` after the previous page's `next_cursor`.
116
- </ParamField>
117
-
118
- ```bash
119
- evolve analysis files ls a0a1b2c3-… /app/work
120
- evolve analysis files search a0a1b2c3-… 'permission denied' --path /app/work
121
- evolve analysis files archive a0a1b2c3-… --path /app/work -o archives/
122
- ```
123
-
124
- ## analysis logs
125
-
126
- ```bash
127
- evolve analysis logs <analysis-id> --stream <name> [--follow] [options]
128
- ```
129
-
130
- The box's own streams: `agent` (the harness's stdout and stderr), `verifier` and `system` (the box's system log, only when the job asked for it with `--system-log`); `setup` and `metrics` are named but not recorded today, so their pages are empty and say why. One page by default; `--follow` keeps printing lines as they arrive while the box lives, and returns once it is gone.
131
-
132
- <ParamField path="--stream" type="name" required>
133
- `agent`, `verifier`, `system`, `setup` or `metrics`.
134
- </ParamField>
135
-
136
- <ParamField path="-f, --follow">
137
- Keep printing new lines while the box lives.
138
- </ParamField>
139
-
140
- <ParamField path="-l, --limit" type="n" default="1000">
141
- Lines per page, max 1000.
142
- </ParamField>
143
-
144
- <ParamField path="--cursor" type="seq">
145
- Resume after this line.
146
- </ParamField>
147
-
148
- ```bash
149
- evolve analysis logs a0a1b2c3-… --stream agent --follow
150
- ```
151
-
152
- ## analysis procs
153
-
154
- ```bash
155
- evolve analysis procs <analysis-id>
156
- ```
157
-
158
- The processes running in the box right now. Live only: once the box is gone the command is refused with `filesystem_state`.
159
-
160
- <GlobalOptions />
@@ -1,84 +0,0 @@
1
- ---
2
- title: "evolve analyze"
3
- description: "Analyze a finished job's trial traces against a rubric, on the platform."
4
- ---
5
-
6
- import GlobalOptions from '/snippets/global-options.mdx';
7
-
8
- ```bash
9
- evolve analyze <job-id> [options]
10
- evolve analyze --show-defaults
11
- ```
12
-
13
- Analyze a terminal job's trial traces against a rubric, server-side. Without `--watch` the command returns at once with the job block and the hint `Follow it with: evolve job show <id>`; `--json` prints the accepted job body. Exit 0 on an accepted wave; with `--watch`, exit 1 when any analysis failed.
14
-
15
- ```bash
16
- evolve analyze 3e1f9a2c-… \
17
- -r rubric.toml \
18
- -p prompt.txt \
19
- --failing \
20
- -l 20 \
21
- -n 2 \
22
- --watch
23
- evolve analyze 3e1f9a2c-… -t d1a10c4e-… -t d1a10f72-…
24
- ```
25
-
26
- ## Options
27
-
28
- <ParamField path="-m, --model" type="name" default="openrouter/deepseek/deepseek-v4.1-flash">
29
- Model the analyzer runs. `glm-5.3-flash` and `haiku` are alternatives, `glm-5.3` escalates, and `fireworks/deepseek-v4.1-flash` is the same model on its Fireworks route. Must be on the `claude` roster.
30
- </ParamField>
31
-
32
- <ParamField path="--effort" type="value">
33
- Reasoning effort the analyzer runs at. Defaults to the per-model default: `high` on `openrouter/deepseek/deepseek-v4.1-flash`, `max` on `glm-5.3-flash`.
34
- </ParamField>
35
-
36
- <ParamField path="-r, --rubric" type="path">
37
- Rubric file: TOML (one `[[criteria]]` table per criterion), YAML or JSON in the `{criteria: [{name, description, guidance}]}` shape, parsed at the keyboard with unknown fields refused by name; the server owns the bounds. Defaults to the platform's analyze rubric, seven criteria with `score_is_earned` first.
38
- </ParamField>
39
-
40
- <ParamField path="-p, --prompt" type="path">
41
- Prompt file for the evaluator agent; its text replaces the built-in prompt, with `{trial_path}`, `{task_section}` and `{criteria_guidance}` rendered, `{{` and `}}` writing a literal brace, and an unknown `{token}` rendering empty. The instructions for writing the result are appended after it. An empty file is refused; there is no length bound. Defaults to the built-in prompt.
42
- </ParamField>
43
-
44
- <ParamField path="-e, --env" type="provider">
45
- Sandbox provider the analyzer runs on. Defaults to `daytona`.
46
- </ParamField>
47
-
48
- <ParamField path="--show-defaults">
49
- Print the defaults an analysis runs under when you name none: model, effort, provider, the rubric's criteria and the built-in prompt template, then exit. With `--json`, one object. Takes no job id and no other analyze flag.
50
- </ParamField>
51
-
52
- <ParamField path="-n, --n-concurrent" type="n">
53
- Max concurrent trial analyses, 1 to 150, beneath the organization's `max_concurrent_analyses` (fleet default 60). Defaults to the ceiling.
54
- </ParamField>
55
-
56
- <ParamField path="--passing">
57
- Only analyze passing trials (reward 1.0).
58
- </ParamField>
59
-
60
- <ParamField path="--failing">
61
- Only analyze failing trials (reward below 1.0, or an exception).
62
- </ParamField>
63
-
64
- <ParamField path="-t, --trial" type="trial-id">
65
- Analyze only this trial; repeatable. Combines with `--passing` or `--failing` (a named trial on the other side is skipped) and comes before `-l`. An id that is not a trial of this job is refused, with the unknown ids named.
66
- </ParamField>
67
-
68
- <ParamField path="-l, --n-trials" type="n">
69
- Max trials to analyze, after `--passing`, `--failing` or `--trial`, in the job's trial order.
70
- </ParamField>
71
-
72
- <ParamField path="--watch">
73
- Poll until every analysis settles, then print one row per analyzed trial: the label (`custom rubric` when there is none), the criterion outcomes, the analyzer's cost and a summary excerpt, with failed analyses listed below. With `--json`, NDJSON envelopes: `analysis.accepted`, `analysis.stats` per change, `analysis.final` with the job and the analyzed trials.
74
- </ParamField>
75
-
76
- <ParamField path="-q, --quiet">
77
- With `--watch`: suppress the progress lines and print the final block only.
78
- </ParamField>
79
-
80
- <GlobalOptions />
81
-
82
- ## Reading analyses back
83
-
84
- The [`analysis`](/cli-reference/analysis) group lists, shows, traces and downloads analysis runs.
@@ -1,133 +0,0 @@
1
- ---
2
- title: "evolve auth"
3
- description: "Identity, API keys, and your organizations."
4
- ---
5
-
6
- import GlobalOptions from '/snippets/global-options.mdx';
7
-
8
- ```bash
9
- evolve auth <command> [options]
10
- ```
11
-
12
- ## auth status
13
-
14
- ```bash
15
- evolve auth status
16
- ```
17
-
18
- Who am I: the caller and the API key in use.
19
-
20
- ## auth org list
21
-
22
- ```bash
23
- evolve auth org list [options]
24
- ```
25
-
26
- List the organizations you belong to.
27
-
28
- <ParamField path="--search" type="text">
29
- Free-text filter over slug, display name and role.
30
- </ParamField>
31
-
32
- <ParamField path="--columns" type="keys | all | help">
33
- Choose and order columns, comma-separated. `help` lists the keys.
34
- </ParamField>
35
-
36
- <ParamField path="-q, --quiet">
37
- Print only slugs, one per line, for piping.
38
- </ParamField>
39
-
40
- <ParamField path="--no-trunc">
41
- Full cell content instead of one-line truncation.
42
- </ParamField>
43
-
44
- <ParamField path="--no-headers">
45
- Omit the header row in piped (TSV) output.
46
- </ParamField>
47
-
48
- ## auth org show
49
-
50
- ```bash
51
- evolve auth org show <slug>
52
- ```
53
-
54
- Show one organization: your role, its members, its quota and live usage.
55
-
56
- ```bash
57
- evolve auth org show acme
58
- ```
59
-
60
- ## auth org create
61
-
62
- ```bash
63
- evolve auth org create <name> [--display-name <text>]
64
- ```
65
-
66
- Create an organization. You become its owner. The name is its slug: lowercase letters, digits and hyphens, starting and ending with a letter or digit, 48 characters at most; `personal` is reserved.
67
-
68
- ```bash
69
- evolve auth org create acme --display-name "Acme Corp"
70
- ```
71
-
72
- ```text
73
- Created organization acme
74
- slug acme
75
- display name Acme Corp
76
- role owner
77
-
78
- Invite a teammate with: evolve auth org invite acme
79
- ```
80
-
81
- ## auth org invite
82
-
83
- ```bash
84
- evolve auth org invite <org>
85
- ```
86
-
87
- Mint an invite token for an organization you own. The token is shown once; send your teammate the join command it prints.
88
-
89
- ```bash
90
- evolve auth org invite acme
91
- ```
92
-
93
- ```text
94
- token evi_...
95
- expires 2026-09-24T00:00:00.000Z
96
- uses unlimited
97
-
98
- Send the teammate this command: evolve auth org join evi_...
99
- ```
100
-
101
- ## auth org join
102
-
103
- ```bash
104
- evolve auth org join <token>
105
- ```
106
-
107
- Join the organization an invite token names, as a member. Running it again with the same token is harmless.
108
-
109
- ```bash
110
- evolve auth org join evi_...
111
- ```
112
-
113
- ```text
114
- Joined acme as member
115
- ```
116
-
117
- ## auth org use
118
-
119
- ```bash
120
- evolve auth org use [<name> | personal]
121
- ```
122
-
123
- Set the organization your jobs and datasets land in when a command names none. It is written to `$XDG_CONFIG_HOME/evolve/config.json`, else `~/.config/evolve/config.json`. `personal` clears it; with no argument it prints the current default. `--org` on `evolve run` or `evolve dataset publish` always wins over it.
124
-
125
- ```bash
126
- evolve auth org use acme
127
- ```
128
-
129
- ```text
130
- Default org: acme (/Users/you/.config/evolve/config.json)
131
- ```
132
-
133
- <GlobalOptions />