@evolvingmachines/evolve 0.0.56 → 0.0.58

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@evolvingmachines/evolve",
-  "version": "0.0.56",
+  "version": "0.0.58",
   "keywords": [
     "ai",
     "agents",
@@ -129,9 +129,9 @@
   },
   "dependencies": {
     "@agentclientprotocol/sdk": "^0.5.1",
-    "@evolvingmachines/daytona": "0.0.56",
-    "@evolvingmachines/e2b": "0.0.56",
-    "@evolvingmachines/modal": "0.0.56",
+    "@evolvingmachines/daytona": "0.0.58",
+    "@evolvingmachines/e2b": "0.0.58",
+    "@evolvingmachines/modal": "0.0.58",
     "ajv": "^8.17.1",
     "p-map": "^7.0.2",
     "smol-toml": "^1.7.0",

package/skills/evolve/SKILL.md

@@ -14,7 +14,7 @@ Python SDK: `pip install evolvingmachines-evolve` (`import evolve`). The manual
 
 ## Start here
 
-This file is a pointer, not the manual. The manual ships inside the CLI and always matches the installed version. Before running any `evolve` command, load it:
+This file is a pointer, not the manual. The manual ships inside the CLI and always matches the installed version. Keep it current: `npm i -g @evolvingmachines/evolve@latest`, then `evolve skills install --force` refreshes this file. Before running any `evolve` command, load it:
 
 ```bash
 evolve skills get evals                        # the index of the documentation: every page, one line each

package/skills/evolve-evals/SKILL.md

@@ -18,7 +18,6 @@ The pages under `references/` are the documentation site's pages, byte for byte,
 2. Every CLI verb is documented from its own `--help`; run `evolve <verb> --help` to confirm the flags of the installed version.
 3. Every command and every SDK client reads `EVOLVE_API_KEY`; the Installation page says where the key comes from.
 
-## Topic index
 
 ## Docs
 

package/skills/evolve-evals/references/cli-reference/run.mdx

@@ -83,10 +83,6 @@ Each of these applies to every arm of the job.
   Skill for every agent arm. Repeatable. Accepts `skills.sh/<owner>/<repo>[/<skill>]`, `org/repo[@ref]`, an https git URL, `upload:<id>`, `name:<skill-name>` (your moving name pointer, resolved server-side), or a local folder, which is uploaded first and then referenced; `--print-config` still shows the path you typed.
 </ParamField>
 
-<ParamField path="--ae, --agent-env" type="KEY=VALUE">
-  Sent as the job's `agent_env`, which the server refuses on this deployment: the create fails naming the two `--ve` keys it honors instead. Agent environment comes from the task's `[environment.env]` table or an attached `--secret`.
-</ParamField>
-
 <ParamField path="--ve, --verifier-env" type="KEY=VALUE">
   Environment for every verifier run. Repeatable. The server honors exactly `REWARDKIT_JUDGE` and `REWARDKIT_MODEL`, rewardkit's judge override, and refuses any other key.
 </ParamField>

package/skills/evolve-evals/references/core-concepts/agents.mdx

@@ -45,7 +45,7 @@ evolve run \
 
 Only `claude` and `codex` take a config or a preset; the [capability document](/sdk-reference/meta) publishes `supports_config` and `presets` per harness. An effort, preset or config a harness cannot honor is refused when the job is created, never silently skipped, and so is a config key that touches billing, base URLs, routing or environment.
 
-Environment for the agent comes from two places, a task's own `[environment.env]` table and a secret attached with `--secret`; a job cannot add a third, and the server refuses `agent_env` (the `--ae` flag). See [secrets](/core-concepts/secrets) and [tasks](/core-concepts/tasks#environment-variables).
+Environment for the agent comes from two places, a task's own `[environment.env]` table and a secret attached with `--secret`; a job cannot add a third. See [secrets](/core-concepts/secrets) and [tasks](/core-concepts/tasks#environment-variables).
 
 ## Register your own agent
 

package/skills/evolve-evals/references/getting-started/quick-start.mdx

@@ -16,6 +16,14 @@ This page takes you from an empty terminal to a downloaded trial: one API key, a
     Create a key on the dashboard's [API keys page](https://dashboard.evolvingmachines.ai/api-keys), then export it. See [installation](/getting-started/installation) for the SDKs.
   </Step>
 
+  <Step title="Give your coding agent the manual">
+    ```bash
+    evolve skills install
+    ```
+
+    Your agent then reads these docs with `evolve skills get evals`, and the `create-task`, `rewardkit`, `create-adapter` and `publish` skills by name. [The five skills](/cli-reference/skills).
+  </Step>
+
   <Step title="Pick a dataset">
     The catalog lists every dataset you can run, with its versions.
 
@@ -28,7 +36,7 @@ This page takes you from an empty terminal to a downloaded trial: one API key, a
   </Step>
 
   <Step title="Start a job and watch it">
-    Name a dataset, an agent, and a model. `--watch` streams the job's events until it finishes; `-l 5` caps the run at five tasks so the first job is small.
+    Name a dataset, an agent, and a model. `--watch` streams the job's events until it finishes; `-l 5` caps the run at five tasks and `--max-trial-spend 1` caps what each trial may spend on the model, so the first job is small.
 
     ```bash
     evolve run \
@@ -36,6 +44,7 @@ This page takes you from an empty terminal to a downloaded trial: one API key, a
       -a codex \
       -m gpt-6-astra \
       -l 5 \
+      --max-trial-spend 1 \
       --watch
     ```
 
@@ -67,19 +76,19 @@ This page takes you from an empty terminal to a downloaded trial: one API key, a
   </Step>
 </Steps>
 
-## Next
+## Next, by what you want to do
 
 <Columns cols={2}>
-  <Card title="Jobs" icon="list-checks" href="/core-concepts/jobs">
-    Attempts, concurrency, retries, spend caps, and what to do with a finished job.
+  <Card title="Port a benchmark" icon="arrow-right-left" href="/core-concepts/tasks">
+    `evolve skills get create-adapter` turns it into Harbor-format tasks.
   </Card>
-  <Card title="Analyze" icon="search" href="/core-concepts/analyze">
-    Judge every trial's trace against a rubric with `--analyze`.
+  <Card title="Write a task" icon="file-plus" href="/core-concepts/tasks">
+    `evolve skills get create-task`, and `rewardkit` for its verifier.
   </Card>
-  <Card title="Agents" icon="bot" href="/core-concepts/agents">
-    The seven built-in harnesses, and how to bring your own.
+  <Card title="Publish a dataset" icon="upload" href="/core-concepts/datasets">
+    `evolve skills get publish`, then `evolve dataset publish`.
   </Card>
-  <Card title="CLI reference" icon="terminal" href="/cli-reference/run">
-    Every flag of `evolve run`.
+  <Card title="Upload a job you ran elsewhere" icon="folder-up" href="/core-concepts/upload">
+    `evolve upload <job dir>` brings a Harbor job into the dashboard.
   </Card>
 </Columns>

package/skills/evolve-evals/references/index.mdx

@@ -20,6 +20,18 @@ evolve run \
   --watch
 ```
 
+New here? The [quick start](/getting-started/quick-start) takes five minutes.
+
+## The whole process
+
+1. [Get tasks](/core-concepts/tasks): a public dataset, your own, or a converted benchmark.
+2. [Check](/core-concepts/check) each task against a rubric before you run it.
+3. [Publish](/core-concepts/datasets) the tasks as a versioned dataset.
+4. [Run](/core-concepts/jobs) any agent and model on it; every trial streams live.
+5. [Read](/core-concepts/trial-outputs) every trial's tree and [analyze](/core-concepts/analyze) its trace.
+
+A coding agent does all five from the same CLI with the [skills](/cli-reference/skills).
+
 <Columns cols={2}>
   <Card title="Quick start" icon="play" href="/getting-started/quick-start">
     Install the CLI, start a job, read its result.