@evolvingmachines/evolve 0.0.67 → 0.0.68

package/skills/evolve-evals/references/cli-reference/agent.md

@@ -58,7 +58,7 @@ evolve agent show my-agent
 ```bash
 evolve run \
   -d harbor-examples@1.0 -i hello-world \
-  -a my-agent -m gpt-5.6-luna \
+  -a my-agent -m gpt-6-luna \
   --max-trial-spend 0.30 --max-retries 0 \
   --watch
 ```

package/skills/evolve-evals/references/cli-reference/analyze.md

@@ -15,10 +15,11 @@ Each selected trial gets its own analysis run. Read those runs with [`evolve ana
 
 ```bash
 evolve analyze --show-defaults
+evolve analyze --show-defaults -a codex
 evolve analyze --show-defaults --json
 ```
 
-This returns the current model, reasoning effort, sandbox provider, prompt, and rubric. Defaults mode takes no job ID or other analysis options.
+This returns the agent, model, reasoning effort, sandbox provider, prompt, and rubric an analysis runs under when you name none of them. With `-a`, it returns what that agent runs under: its default model and the effort that model takes. Defaults mode takes no job ID and no other analysis options.
 
 ## Select trials
 
@@ -51,6 +52,7 @@ Cancelled trials are excluded. `--passing` and `--failing` cannot be combined. T
 
 ```bash
 evolve analyze "$JOB_ID" \
+  --agent codex --model gpt-6-sol \
   --rubric rubric.toml \
   --prompt prompt.txt \
   --watch
@@ -58,12 +60,13 @@ evolve analyze "$JOB_ID" \
 
 | Option | Meaning |
 | --- | --- |
-| `-m`, `--model <name>` | Analyzer model. |
+| `-a`, `--agent <name>` | Agent the analyzer runs on. Default `claude`. |
+| `-m`, `--model <name>` | Analyzer model, from that agent's models. Default: the agent's default model. |
 | `--effort <value>` | Reasoning effort. |
 | `-r`, `--rubric <path>` | TOML, YAML, or JSON rubric. |
 | `-p`, `--prompt <path>` | Text file replacing the default prompt. |
 | `-e`, `--env <provider>` | Sandbox provider for analysis. |
-| `--show-defaults` | Print the default policy and exit. |
+| `--show-defaults` | Print the default policy and exit. `-a` picks the agent. |
 
 A rubric contains a `criteria` list. Every criterion needs `name`, `description`, and `guidance`.
 

package/skills/evolve-evals/references/cli-reference/check.md

@@ -44,16 +44,17 @@ evolve check --show-defaults
 | Option | Meaning |
 | --- | --- |
 | `--name <name>` | Check label. Defaults to the acceptance timestamp. |
-| `-m`, `--model <name>` | Checker model. |
+| `-a`, `--agent <name>` | Agent the checker runs on. Default `claude`. |
+| `-m`, `--model <name>` | Checker model, from that agent's models. Default: the agent's default model. |
 | `--effort <value>` | Reasoning effort. |
 | `-r`, `--rubric <path>` | TOML, YAML, or JSON rubric. |
 | `-p`, `--prompt <path>` | Replacement prompt text file. |
 | `-e`, `--env <provider>` | Checker sandbox provider. |
-| `--show-defaults` | Print the prompt, rubric, model, effort, and provider, then exit. |
+| `--show-defaults` | Print the agent, model, effort, provider, prompt, and rubric, then exit. `-a` picks the agent. |
 | `--watch` | Wait until every task check settles. |
 | `-q`, `--quiet` | With watch, suppress intermediate progress. |
 
-`--show-defaults` accepts only [global options](/cli-reference/index#global-options). It cannot be combined with a path, dataset, or checker options.
+`--show-defaults` accepts only `-a` and the [global options](/cli-reference/index#global-options). It cannot be combined with a path, dataset, or other checker options.
 
 For rubric format and interpretation, see [Check](/core-concepts/check).
 

package/skills/evolve-evals/references/cli-reference/index.md

@@ -109,7 +109,7 @@ A trial prefix may require reading the trials of every job in scope. On large ac
 Repeat a repeatable flag once per value. Do not combine short flags.
 
 ```bash
-evolve run -d harbor-examples@1.0 -a codex -m gpt-5.6-luna \
+evolve run -d harbor-examples@1.0 -a codex -m gpt-6-luna \
   -i 'hello-*' -x '*-slow' --max-trial-spend 0.30 --max-retries 0
 ```
 

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

@@ -9,7 +9,7 @@ Start a hosted job. `evolve job start` accepts exactly the same options.
 evolve run \
   -d harbor-examples@1.0 \
   -i hello-world \
-  -a codex -m gpt-5.6-luna \
+  -a codex -m gpt-6-luna \
   --max-trial-spend 0.30 \
   --max-retries 0 \
   --watch
@@ -51,7 +51,7 @@ datasets:
     task_names: [hello-world]
 agents:
   - name: codex
-    model_name: gpt-5.6-luna
+    model_name: gpt-6-luna
 n_attempts: 1
 n_concurrent_trials: 4
 max_trial_spend_usd: 0.30
@@ -148,7 +148,8 @@ See [Jobs](/core-concepts/jobs) for the retry and spend rules.
 | Option | Meaning |
 | --- | --- |
 | `--analyze` | Enable analysis with the platform defaults. |
-| `--analyze-model <name>` | Analyzer model. |
+| `--analyze-agent <name>` | Agent the analyzer runs on. Default `claude`. |
+| `--analyze-model <name>` | Analyzer model, from that agent's models. |
 | `--analyze-rubric <path>` | TOML, YAML, or JSON rubric. |
 | `--analyze-prompt <path>` | Replacement prompt file. |
 | `--analyze-provider <provider>` | Analyzer sandbox provider. |

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

@@ -8,7 +8,7 @@ An evaluation arm pairs an **agent harness** with a **model**. The harness reads
 ```text
 One arm
 ├── Harness: -a codex
-└── Model: -m gpt-5.6-luna
+└── Model: -m gpt-6-luna
 ```
 
 ## Built-in harnesses
@@ -17,15 +17,19 @@ One arm
 | --- | --- |
 | `claude` | Claude Code |
 | `codex` | Codex |
-| `gemini` | Gemini CLI |
 | `qwen` | Qwen Code |
 | `kimi` | Kimi Code |
 | `opencode` | OpenCode |
 | `droid` | Droid |
+| `pi` | pi |
+| `prime-agent` | Prime Agent |
+| `dsh` | DeepSeek Harness |
+| `zcode` | Z Code |
+| `antigravity` | Antigravity CLI |
 
 ```bash
 evolve run -d harbor-examples@1.0 -i hello-world \
-  -a codex -m gpt-5.6-luna \
+  -a codex -m gpt-6-luna \
   --max-trial-spend 1 --max-retries 0 --watch
 ```
 

package/skills/evolve-evals/references/core-concepts/analyze.md

@@ -41,7 +41,7 @@ Repeat `-t` with full trial IDs to select specific trials; selection happens bef
 ```bash
 evolve run \
   -d harbor-examples@1.0 -i hello-world \
-  -a codex -m gpt-5.6-luna \
+  -a codex -m gpt-6-luna \
   --max-trial-spend 1 -r 0 --analyze --watch
 ```
 
@@ -104,7 +104,7 @@ evolve analyze "$JOB_ID" -r rubric.toml -p prompt.txt --watch
 
 An analyzer prompt can use `{trial_path}`, `{task_section}`, and `{criteria_guidance}`. Evolve appends the required output format.
 
-Use `-m`, `--effort`, `-e`, and `-n` for model, effort, provider, and concurrency. On job creation, use the corresponding `--analyze-*` flags. See the [full reference](/cli-reference/analyze).
+Use `-a`, `-m`, `--effort`, `-e`, and `-n` for agent, model, effort, provider, and concurrency. The analyzer runs on `claude` unless `-a` names another agent; the model must be one of that agent's [models](/core-concepts/models#analysis-and-check-models). On job creation, use the corresponding `--analyze-*` flags. See the [full reference](/cli-reference/analyze).
 
 ## The result
 

package/skills/evolve-evals/references/core-concepts/check.md

@@ -52,13 +52,13 @@ A check is a hosted model run and incurs cost. `evolve dataset check` is a separ
 | Execution | Valid reference solution; rejection of non-solutions; environment works; stable verification; sufficient limits. |
 | Feasibility | The task is solvable. |
 
-Inspect the default rubric's criteria and their complete guidance, and the current model, effort, provider, and prompt:
+Inspect the default rubric's criteria and their complete guidance, and the current agent, model, effort, provider, and prompt:
 
 ```bash
 evolve check --show-defaults
 ```
 
-Use `-r rubric.toml` or `-p prompt.txt` to customize. Check prompt tokens are `{task_path}`, `{file_tree}`, and `{criteria_guidance}`. The required result format is appended automatically.
+Use `-r rubric.toml` or `-p prompt.txt` to customize. Check prompt tokens are `{task_path}`, `{file_tree}`, and `{criteria_guidance}`. The required result format is appended automatically. The checker runs on `claude` unless `-a` names another agent; pass a model from that agent's [models](/core-concepts/models#analysis-and-check-models) with `-m`, or omit `-m` for that agent's default model.
 
 ## The result
 

package/skills/evolve-evals/references/core-concepts/datasets.md

@@ -102,7 +102,7 @@ Configuration validation cannot prove that images build or tests are correct. Ru
 
 ```bash
 # Run an exact version.
-evolve run -d my-dataset@1.0 -a codex -m gpt-5.6-luna
+evolve run -d my-dataset@1.0 -a codex -m gpt-6-luna
 
 # Change what the bare name resolves to.
 evolve dataset activate my-dataset 1.0

package/skills/evolve-evals/references/core-concepts/index.md

@@ -20,7 +20,7 @@ flowchart TD
 | --- | --- | --- |
 | [Task](/core-concepts/tasks) | An instruction, environment, and grading logic. | Fix a bug and pass the tests. |
 | [Dataset](/core-concepts/datasets) | A named, versioned collection of tasks. | `harbor-examples@1.0`. |
-| [Agent](/core-concepts/agents) | A harness running a selected model. | Codex with `gpt-5.6-luna`. |
+| [Agent](/core-concepts/agents) | A harness running a selected model. | Codex with `gpt-6-luna`. |
 | [Sandbox](/core-concepts/sandboxes) | The isolated environment where a trial runs. | A task image on Daytona, E2B, or Modal. |
 | [Job](/core-concepts/jobs) | A group of trials with shared run settings. | 10 tasks × 2 configurations × 3 attempts = 60 trials. |
 | [Trial](/core-concepts/trials) | One attempt at one task. | One score and its supporting evidence. |

package/skills/evolve-evals/references/core-concepts/jobs.md

@@ -19,7 +19,7 @@ Each of the three tasks runs twice in Arm A and twice in Arm B.
 ```bash
 evolve run \
   -d harbor-examples@1.0 -i hello-world \
-  -a codex -m gpt-5.6-luna \
+  -a codex -m gpt-6-luna \
   --max-trial-spend 1 -r 0 \
   --watch
 ```
@@ -50,7 +50,7 @@ Use a [config file](#config-files) to compare different harnesses in one job.
 `-i` and `-x` accept task-name globs. Quote them so your shell does not expand them.
 
 ```bash
-evolve run -d my-dataset@1.0 -a codex -m gpt-5.6-luna \
+evolve run -d my-dataset@1.0 -a codex -m gpt-6-luna \
   -i 'auth-*' -x 'auth-legacy' -l 20 \
   --max-trial-spend 2 -r 0 --watch
 ```
@@ -198,7 +198,7 @@ datasets:
     task_names: [hello-world]
 agents:
   - name: codex
-    model_name: gpt-5.6-luna
+    model_name: gpt-6-luna
   - name: claude
     model_name: fable
 n_attempts: 2

package/skills/evolve-evals/references/core-concepts/models.md

@@ -8,7 +8,7 @@ description: "Select models, compare them, and control metered spend."
 ```bash
 evolve run -d harbor-examples@1.0 -i hello-world \
   -a codex \
-  -m gpt-5.6-luna -m gpt-5.6-terra \
+  -m gpt-6-luna -m gpt-5.6-terra \
   --max-trial-spend 1 --max-retries 0 --watch
 ```
 
@@ -49,7 +49,6 @@ If you enable your own provider key, supported model requests bill that provider
 | --- | --- |
 | Supports effort levels | Use a value from `limits.job.reasoning_efforts` |
 | Qwen thinking mode | Use `off` or `minimal` to disable thinking; `medium` or `thinking` to enable it |
-| Gemini | Do not pass effort; it is unsupported |
 | Custom agent | Configure reasoning in its run command |
 
 When omitted, Evolve resolves the harness's default and records it in `agent_info.reasoning_effort`. The same harness and model at different efforts are distinct arms.
@@ -58,15 +57,15 @@ In `/api/meta`, `agents[].effort_support` identifies the mode: `level`, `binary`
 
 ## Analysis and check models
 
-Trace analysis and task checks use the Claude Code harness. Select their model separately:
+Trace analysis and task checks run on Claude Code unless you choose another agent. Select their agent and model separately from the evaluation arms:
 
-| Operation | Model option |
-| --- | --- |
-| `evolve analyze` | `-m` |
-| `evolve check` | `-m` |
-| Analysis attached to `evolve run` | `--analyze-model` |
+| Operation | Agent option | Model option |
+| --- | --- | --- |
+| `evolve analyze` | `-a` | `-m` |
+| `evolve check` | `-a` | `-m` |
+| Analysis attached to `evolve run` | `--analyze-agent` | `--analyze-model` |
 
-Their default is `openrouter/deepseek/deepseek-v4.1-flash`. Choose from the supported Claude Code roster.
+Omit the model and the agent runs its default: `openrouter/deepseek/deepseek-v4.1-flash` on every agent whose models include it, otherwise that agent's own default model. A model you name must be one of the chosen agent's models. In `/api/meta`, `analyze.agents` lists the agents these commands accept, each agent's default model and models, and the effort each model runs at when you pass none. `evolve analyze --show-defaults -a <agent>` prints what that agent runs under.
 
 **[Configure a run](/cli-reference/run)**
 

package/skills/evolve-evals/references/core-concepts/sandboxes.md

@@ -7,7 +7,7 @@ Each trial runs in its own cloud sandbox. Use `-e` to request E2B, Daytona, or M
 
 ```bash
 evolve run -d harbor-examples@1.0 -i hello-world \
-  -a codex -m gpt-5.6-luna -e modal \
+  -a codex -m gpt-6-luna -e modal \
   --max-trial-spend 1 --max-retries 0 --watch
 ```
 

package/skills/evolve-evals/references/core-concepts/secrets.md

@@ -29,7 +29,7 @@ Eval jobs support **direct** delivery: the value enters the agent sandbox. Broke
 ## Attach it to a job
 
 ```bash
-evolve run -d my-dataset@1.0 -a codex -m gpt-5.6-luna \
+evolve run -d my-dataset@1.0 -a codex -m gpt-6-luna \
   --secret GITHUB_TOKEN@staging \
   --max-trial-spend 1 --max-retries 0 --watch
 ```

package/skills/evolve-evals/references/core-concepts/skills.md

@@ -18,7 +18,7 @@ my-skill/
 
 ```bash
 evolve run -d harbor-examples@1.0 -i hello-world \
-  -a codex -m gpt-5.6-luna \
+  -a codex -m gpt-6-luna \
   --skills ./my-skill \
   --max-trial-spend 1 --max-retries 0 --watch
 ```

package/skills/evolve-evals/references/core-concepts/task-verifiers.md

@@ -197,7 +197,7 @@ Evolve supplies a gateway credential and the matching base URL. Recognized crede
 For a Reward Kit judge, override its agent and model for one job with:
 
 ```bash
-evolve run -d my-dataset@1.0 -a codex -m gpt-5.6-luna \
+evolve run -d my-dataset@1.0 -a codex -m gpt-6-luna \
   --ve REWARDKIT_JUDGE=claude \
   --ve REWARDKIT_MODEL=sonnet
 ```

package/skills/evolve-evals/references/core-concepts/teams.md

@@ -68,7 +68,7 @@ Personal organizations cannot be renamed, deleted, or have their membership chan
 ```bash
 evolve run \
   -d harbor-examples@1.0 -i hello-world \
-  -a codex -m gpt-5.6-luna \
+  -a codex -m gpt-6-luna \
   --max-trial-spend 1 -r 0 --org acme
 ```
 

package/skills/evolve-evals/references/core-concepts/upload.md

@@ -70,7 +70,7 @@ This is a minimal illustrative trial record with a reward. Replace the task, age
   "agent_info": {
     "name": "codex",
     "version": "",
-    "model_info": { "name": "gpt-5.6-luna" }
+    "model_info": { "name": "gpt-6-luna" }
   },
   "verifier_result": { "rewards": { "reward": 1.0 } }
 }

package/skills/evolve-evals/references/getting-started/first-task.md

@@ -170,7 +170,7 @@ evolve run \
   -d "$DATASET@$VERSION" \
   -i hello-world \
   -a codex \
-  -m gpt-5.6-luna \
+  -m gpt-6-luna \
   --max-trial-spend 1 \
   --max-retries 0 \
   --watch

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

@@ -32,7 +32,7 @@ evolve run \
   -d harbor-examples@1.0 \
   -i hello-world \
   -a codex \
-  -m gpt-5.6-luna \
+  -m gpt-6-luna \
   --max-trial-spend 1 \
   --max-retries 0 \
   --watch

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

@@ -39,7 +39,7 @@ After [installation and authentication](/getting-started/installation), run one
 ```bash
 evolve run \
   -d harbor-examples@1.0 -i hello-world \
-  -a codex -m gpt-5.6-luna \
+  -a codex -m gpt-6-luna \
   --max-trial-spend 1 --max-retries 0 --watch
 ```
 

package/skills/evolve-evals/references/sdk/http.md

@@ -29,7 +29,7 @@ Save the request as `job.json`:
   }],
   "agents": [{
     "name": "codex",
-    "model_name": "gpt-5.6-luna"
+    "model_name": "gpt-6-luna"
   }],
   "max_trial_spend_usd": 1,
   "retry": {"max_retries": 0}

package/skills/evolve-evals/references/sdk/python.md

@@ -27,7 +27,7 @@ async def main():
                 "version": "1.0",
                 "task_names": ["hello-world"],
             }],
-            agents=[{"name": "codex", "model_name": "gpt-5.6-luna"}],
+            agents=[{"name": "codex", "model_name": "gpt-6-luna"}],
             max_trial_spend_usd=0.50,
             retry={"max_retries": 0},
         )

package/skills/evolve-evals/references/sdk/typescript.md

@@ -25,7 +25,7 @@ const job = await evolve.jobs.start({
     version: "1.0",
     task_names: ["hello-world"],
   }],
-  agents: [{ name: "codex", model_name: "gpt-5.6-luna" }],
+  agents: [{ name: "codex", model_name: "gpt-6-luna" }],
   max_trial_spend_usd: 0.50,
   retry: { max_retries: 0 },
 });

package/skills/evolve-evals/references/sdk-reference/analyses.md

@@ -49,8 +49,9 @@ The field names are the same in both languages. TypeScript passes an object; Pyt
 
 | Field | Purpose |
 | --- | --- |
-| `model_name` | Analyzer model |
-| `reasoning_effort` | Effort supported by the analyzer |
+| `agent` | Agent the analyzer runs on; default `claude` |
+| `model_name` | Analyzer model, one of that agent's models |
+| `reasoning_effort` | Effort that agent accepts |
 | `sandbox_provider` | Analyzer's sandbox provider |
 | `rubric` | `{criteria: [{name, description, guidance}, ...]}` |
 | `prompt` | Replacement prompt template text |
@@ -77,14 +78,20 @@ Polling slows to at most 30 seconds while the tally stays unchanged. Call the wa
 ```ts TypeScript
 const defaults = await analyses().defaults();
 console.log(defaults.model_name, defaults.rubric, defaults.prompt);
+
+const codex = await analyses().defaults({ agent: "codex" });
+console.log(codex.model_name, codex.reasoning_effort);
 ```
 
 ```python Python
 defaults = await analyses().defaults()
 print(defaults["model_name"], defaults["rubric"], defaults["prompt"])
+
+codex = await analyses().defaults(agent="codex")
+print(codex["model_name"], codex["reasoning_effort"])
 ```
 
-The response includes `model_name`, `rubric`, `prompt`, `reasoning_effort`, and `sandbox_provider`. The prompt is the editable template text.
+The response includes `agent`, `model_name`, `rubric`, `prompt`, `reasoning_effort`, and `sandbox_provider`. The prompt is the editable template text. Pass an agent to read what that agent runs under when you name no model: its default model and the effort that model takes.
 
 A custom analyze prompt may use `{trial_path}`, `{task_section}`, and `{criteria_guidance}`. The required result schema is appended by the platform. See [analysis concepts](/core-concepts/analyze) for rubric design.
 
@@ -110,7 +117,7 @@ The latest analysis also appears on `trial.analysis`. Each criterion reports `pa
 | Method | TypeScript | Python |
 | --- | --- | --- |
 | List runs | `list(options)` | `list(...)` |
-| Read defaults | `defaults()` | `defaults()` |
+| Read defaults | `defaults({ agent })` | `defaults(agent=...)` |
 | Download run | `download(analysisId, { to })` | `download(analysis_id, to=...)` |
 | Browse sandbox files | `filesystem(analysisId)` | `filesystem(analysis_id)` |
 | Read one analysis directly | `get(analysisId)` | Use list results or `trial.analysis` |

package/skills/evolve-evals/references/sdk-reference/checks.md

@@ -55,8 +55,9 @@ Choose one source. A local check does not first publish a dataset.
 | Option | Purpose |
 | --- | --- |
 | `name` | Check label; defaults to an acceptance timestamp |
-| `model_name` | Checker model |
-| `reasoning_effort` | Supported reasoning effort |
+| `agent` | Agent the checker runs on; default `claude` |
+| `model_name` | Checker model, one of that agent's models |
+| `reasoning_effort` | Effort that agent accepts |
 | `sandbox_provider` | Checker sandbox provider |
 | `rubric` | `{criteria: [{name, description, guidance}, ...]}` |
 | `prompt` | Replacement prompt template |
@@ -73,14 +74,20 @@ TypeScript places these alongside `source` in the input object. Python takes key
 ```ts TypeScript
 const defaults = await client.defaults();
 console.log(defaults.rubric, defaults.prompt);
+
+const codex = await client.defaults({ agent: "codex" });
+console.log(codex.model_name, codex.reasoning_effort);
 ```
 
 ```python Python
 defaults = await client.defaults()
 print(defaults["rubric"], defaults["prompt"])
+
+codex = await client.defaults(agent="codex")
+print(codex["model_name"], codex["reasoning_effort"])
 ```
 
-Defaults include model, rubric, prompt, effort, and provider. Check prompt tokens are `{task_path}`, `{file_tree}`, and `{criteria_guidance}`. They differ from analysis prompt tokens.
+Defaults include agent, model, rubric, prompt, effort, and provider. Pass an agent to read what that agent runs under when you name no model: its default model and the effort that model takes. Check prompt tokens are `{task_path}`, `{file_tree}`, and `{criteria_guidance}`. They differ from analysis prompt tokens.
 
 ## Understand the result
 
@@ -116,7 +123,7 @@ Evolve derives no verdict from a result. Read the criterion outcomes and evidenc
 | `get(id)` | Full check and its task results |
 | `list(...)` | `scope`, `status` list, `dataset`, `limit`, `cursor`; paginated handle |
 | `watch(id, ...)` | Wait until completed; callback on changes |
-| `defaults()` | Current policy and editable prompt |
+| `defaults({ agent })` | Current policy and editable prompt; with an agent, what that agent runs under |
 
 Watch options are `onProgress`, `pollIntervalMs`, `signal` in TypeScript; `on_progress`, `poll_interval_s`, `timeout_s` in Python. Polling starts at 2 seconds and slows to 30 seconds while unchanged.
 

package/skills/evolve-evals/references/sdk-reference/error-codes.md

@@ -95,6 +95,7 @@ These codes apply to chunked dataset and job uploads. They describe the transfer
 | `agent_config_unsupported` | This harness does not support a native config. Omit it or choose a harness listed in `details.config_supporting_agents`. |
 | `agent_config_key_refused` | Native config contains settings that Evolve controls, such as routing or credentials. Remove the keys named in `details.refused_keys`. |
 | `agent_preset_unsupported` | This harness cannot apply the requested preset. Choose a supported harness or remove the preset. |
+| `agent_retired` | A new job, resume, retry, analysis or check named a retired harness. Use the harness in `details.retired_agents[].replaced_by`; its past runs stay readable. |
 
 ## Registered agents
 

package/skills/evolve-evals/references/sdk-reference/jobs.md

@@ -28,7 +28,7 @@ const job = await client.start({
     version: "1.0",
     task_names: ["hello-world"],
   }],
-  agents: [{ name: "codex", model_name: "gpt-5.6-luna" }],
+  agents: [{ name: "codex", model_name: "gpt-6-luna" }],
   max_trial_spend_usd: 0.50,
   retry: { max_retries: 0 },
 });
@@ -44,7 +44,7 @@ job = await client.start(
         "version": "1.0",
         "task_names": ["hello-world"],
     }],
-    agents=[{"name": "codex", "model_name": "gpt-5.6-luna"}],
+    agents=[{"name": "codex", "model_name": "gpt-6-luna"}],
     max_trial_spend_usd=0.50,
     retry={"max_retries": 0},
 )

package/skills/evolve-evals/references/sdk-reference/meta.md

@@ -31,10 +31,11 @@ Also available as `hosted().meta()` in both languages.
 | Field | Use it to answer |
 | --- | --- |
 | `agents` | Which harnesses run? Which models, efforts, versions, kwargs, and presets do they support? |
+| `retired_agents` | Which harnesses are retired, and which harness replaces each? |
 | `sandbox_providers` | Which providers support the task's resources and features? |
 | `platform_constraints` | Which requirements cannot run on this deployment? |
 | `network_modes` | Which network modes can a task declare? |
-| `analyze` | Which analyzer models and reasoning efforts are available? |
+| `analyze` | Which agents can analyses and checks run on, with which models and reasoning efforts? |
 | `limits` | What are the current defaults and bounds for jobs, pages, uploads, and comparisons? |
 | `statuses` | Which states exist, and which are terminal? |
 | `agent_registration` | Which names, environment keys, and upload sizes can a custom agent use? |

package/skills/evolve-evals/references/sdk-reference/methods/analyses.md

@@ -54,27 +54,29 @@ Python analysis rows are dictionaries: `row["id"]`, `row["checks"]`. [Analysis r
 
 ## defaults
 
-Read the current analysis defaults. Returns `AnalyzeDefaults`: model, effort, sandbox provider, rubric, and unrendered prompt template.
+Read the current analysis defaults. Returns `AnalyzeDefaults`: agent, model, effort, sandbox provider, rubric, and unrendered prompt template. Pass an agent to read what that agent runs under when you name no model.
 
 ### Signature
 
 ```ts TypeScript signature
-defaults(): Promise<AnalyzeDefaults>;
+defaults(options?: { agent?: string }): Promise<AnalyzeDefaults>;
 ```
 
 ```python Python signature
-async def defaults() -> AnalyzeDefaults: ...
+async def defaults(*, agent: Optional[str] = None) -> AnalyzeDefaults: ...
 ```
 
 ```ts TypeScript
 const defaults = await client.defaults();
+const codex = await client.defaults({ agent: "codex" });
 ```
 
 ```python Python
 defaults = await client.defaults()
+codex = await client.defaults(agent="codex")
 ```
 
-Python returns a dictionary. These are current defaults; an existing analysis records the policy it actually ran under.
+Python returns a dictionary. These are current defaults; an existing analysis records the policy it actually ran under. An agent the platform does not offer is refused with `invalid_input`.
 
 ## get
 

package/skills/evolve-evals/references/sdk-reference/methods/checks.md

@@ -37,6 +37,7 @@ async def create(
     *,
     dataset: Optional[str] = None,
     name: Optional[str] = None,
+    agent: Optional[str] = None,
     model_name: Optional[str] = None,
     rubric: Optional[Rubric] = None,
     prompt: Optional[str] = None,
@@ -80,6 +81,7 @@ Optional `onUploadProgress(sent, total)` / `on_upload_progress(sent, total)` rep
 ```ts
 interface CheckConfigInput {
   name?: string;
+  agent?: string;
   model_name?: string;
   rubric?: Rubric;
   prompt?: string;
@@ -160,27 +162,29 @@ Optional `scope`: `my` (default), `shared`, or `org`; `status`: a list of `queue
 
 ## defaults
 
-Read `CheckDefaults`: current model, reasoning effort, sandbox provider, rubric, and unrendered prompt template.
+Read `CheckDefaults`: current agent, model, reasoning effort, sandbox provider, rubric, and unrendered prompt template. Pass an agent to read what that agent runs under when you name no model.
 
 ### Signature
 
 ```ts TypeScript signature
-defaults(): Promise<CheckDefaults>;
+defaults(options?: { agent?: string }): Promise<CheckDefaults>;
 ```
 
 ```python Python signature
-async def defaults() -> CheckDefaults: ...
+async def defaults(*, agent: Optional[str] = None) -> CheckDefaults: ...
 ```
 
 ```ts TypeScript
 const defaults = await client.defaults();
+const codex = await client.defaults({ agent: "codex" });
 ```
 
 ```python Python
 defaults = await client.defaults()
+codex = await client.defaults(agent="codex")
 ```
 
-Python returns a dictionary. The check’s prompt uses `{task_path}`, `{file_tree}`, and `{criteria_guidance}`; the output contract is appended after your template.
+Python returns a dictionary. The check’s prompt uses `{task_path}`, `{file_tree}`, and `{criteria_guidance}`; the output contract is appended after your template. An agent the platform does not offer is refused with `invalid_input`.
 
 ## watch
 

package/skills/evolve-evals/references/sdk-reference/methods/jobs.md

@@ -67,7 +67,7 @@ const job = await client.start({
   agents: [
     {
       name: "codex",
-      model_name: "gpt-5.6-luna"
+      model_name: "gpt-6-luna"
     }
   ],
   max_trial_spend_usd: 1,
@@ -89,7 +89,7 @@ job = await client.start(
     agents=[
         {
             'name': 'codex',
-            'model_name': 'gpt-5.6-luna',
+            'model_name': 'gpt-6-luna',
         },
     ],
     max_trial_spend_usd=1,
@@ -528,6 +528,7 @@ analyze(
 async def analyze(
     id: str,
     *,
+    agent: Optional[str] = None,
     model_name: Optional[str] = None,
     rubric: Optional[Rubric] = None,
     prompt: Optional[str] = None,
@@ -556,7 +557,7 @@ job = await client.analyze(
 )
 ```
 
-All options are optional. `analyses().defaults()` reads the current model, effort, provider, rubric, and prompt defaults.
+All options are optional. `analyses().defaults()` reads the current agent, model, effort, provider, rubric, and prompt defaults.
 
 | Selection | Meaning |
 | --- | --- |
@@ -572,6 +573,7 @@ Cancelled trials are excluded. `trial_ids` is accepted here, but refused inside
 
 ```ts
 interface AnalyzeConfigInput {
+  agent?: string;
   model_name?: string;
   rubric?: Rubric;
   prompt?: string;