@evolvingmachines/evolve 0.0.55-project-sable.20260916.db0bc0bb

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 (98) hide show
  1. package/LICENSE +201 -0
  2. package/README.md +25 -0
  3. package/dist/chunk-5GVMBEYI.js +11 -0
  4. package/dist/chunk-HQJI3HHU.js +1 -0
  5. package/dist/chunk-JS2UTK2I.js +427 -0
  6. package/dist/cli/index.cjs +73 -0
  7. package/dist/cli/index.d.cts +270 -0
  8. package/dist/cli/index.d.ts +270 -0
  9. package/dist/cli/index.js +54 -0
  10. package/dist/index.cjs +669 -0
  11. package/dist/index.d.cts +5023 -0
  12. package/dist/index.d.ts +5023 -0
  13. package/dist/index.js +230 -0
  14. package/dist/managed-modal-IJW62SSK.js +4 -0
  15. package/dist/resumable-HFSICSH3.js +1 -0
  16. package/dist/tar-GVC4KE52.js +1 -0
  17. package/dist/types-DlpTxdR_.d.cts +4777 -0
  18. package/dist/types-DlpTxdR_.d.ts +4777 -0
  19. package/dist/upload-KPYDMWFJ.js +1 -0
  20. package/docs-agents/SKILL.md +138 -0
  21. package/docs-agents/index.md +81 -0
  22. package/docs-agents/python/01-getting-started.md +511 -0
  23. package/docs-agents/python/02-configuration.md +855 -0
  24. package/docs-agents/python/03-runtime.md +899 -0
  25. package/docs-agents/python/04-streaming.md +451 -0
  26. package/docs-agents/python/05-swarm-pipeline.md +953 -0
  27. package/docs-agents/python/index.md +122 -0
  28. package/docs-agents/typescript/01-getting-started.md +494 -0
  29. package/docs-agents/typescript/02-configuration.md +841 -0
  30. package/docs-agents/typescript/03-runtime.md +864 -0
  31. package/docs-agents/typescript/04-streaming.md +478 -0
  32. package/docs-agents/typescript/05-swarm-pipeline.md +957 -0
  33. package/docs-agents/typescript/index.md +121 -0
  34. package/docs-evals/SKILL.md +112 -0
  35. package/docs-evals/cli-reference/agent.mdx +67 -0
  36. package/docs-evals/cli-reference/analysis.mdx +91 -0
  37. package/docs-evals/cli-reference/analyze.mdx +74 -0
  38. package/docs-evals/cli-reference/auth.mdx +60 -0
  39. package/docs-evals/cli-reference/check.mdx +146 -0
  40. package/docs-evals/cli-reference/dataset.mdx +133 -0
  41. package/docs-evals/cli-reference/index.mdx +108 -0
  42. package/docs-evals/cli-reference/job.mdx +239 -0
  43. package/docs-evals/cli-reference/run.mdx +196 -0
  44. package/docs-evals/cli-reference/secrets.mdx +95 -0
  45. package/docs-evals/cli-reference/skill.mdx +51 -0
  46. package/docs-evals/cli-reference/skills.mdx +81 -0
  47. package/docs-evals/cli-reference/trial.mdx +112 -0
  48. package/docs-evals/cli-reference/upload.mdx +36 -0
  49. package/docs-evals/core-concepts/agents.mdx +106 -0
  50. package/docs-evals/core-concepts/analyze.mdx +86 -0
  51. package/docs-evals/core-concepts/check.mdx +51 -0
  52. package/docs-evals/core-concepts/datasets.mdx +138 -0
  53. package/docs-evals/core-concepts/index.mdx +42 -0
  54. package/docs-evals/core-concepts/jobs.mdx +136 -0
  55. package/docs-evals/core-concepts/models.mdx +68 -0
  56. package/docs-evals/core-concepts/sandboxes.mdx +52 -0
  57. package/docs-evals/core-concepts/secrets.mdx +41 -0
  58. package/docs-evals/core-concepts/skills.mdx +42 -0
  59. package/docs-evals/core-concepts/tasks.mdx +216 -0
  60. package/docs-evals/core-concepts/trial-outputs.mdx +103 -0
  61. package/docs-evals/core-concepts/trials.mdx +103 -0
  62. package/docs-evals/core-concepts/upload.mdx +45 -0
  63. package/docs-evals/dashboard/checks.mdx +15 -0
  64. package/docs-evals/dashboard/datasets.mdx +24 -0
  65. package/docs-evals/dashboard/jobs.mdx +65 -0
  66. package/docs-evals/dashboard/traces.mdx +15 -0
  67. package/docs-evals/dashboard/trial-viewer.mdx +30 -0
  68. package/docs-evals/docs.json +180 -0
  69. package/docs-evals/getting-started/installation.mdx +56 -0
  70. package/docs-evals/getting-started/quick-start.mdx +85 -0
  71. package/docs-evals/index.mdx +36 -0
  72. package/docs-evals/sdk/python.mdx +139 -0
  73. package/docs-evals/sdk/typescript.mdx +141 -0
  74. package/docs-evals/sdk-reference/agents.mdx +105 -0
  75. package/docs-evals/sdk-reference/analyses.mdx +125 -0
  76. package/docs-evals/sdk-reference/auth.mdx +76 -0
  77. package/docs-evals/sdk-reference/checks.mdx +166 -0
  78. package/docs-evals/sdk-reference/datasets.mdx +305 -0
  79. package/docs-evals/sdk-reference/errors.mdx +199 -0
  80. package/docs-evals/sdk-reference/index.mdx +58 -0
  81. package/docs-evals/sdk-reference/jobs.mdx +731 -0
  82. package/docs-evals/sdk-reference/meta.mdx +52 -0
  83. package/docs-evals/sdk-reference/skills.mdx +68 -0
  84. package/docs-evals/sdk-reference/trials.mdx +232 -0
  85. package/docs-evals/sdk-reference/types.mdx +272 -0
  86. package/docs-evals/snippets/global-options.mdx +13 -0
  87. package/docs-evals/snippets/list-flags.mdx +23 -0
  88. package/harness-capabilities.json +430 -0
  89. package/hosted-error-codes.json +120 -0
  90. package/package.json +163 -0
  91. package/skills/create-adapter/SKILL.md +287 -0
  92. package/skills/create-task/SKILL.md +491 -0
  93. package/skills/evolve/SKILL.md +39 -0
  94. package/skills/publish/SKILL.md +142 -0
  95. package/skills/rewardkit/SKILL.md +330 -0
  96. package/spec/atif/README.md +45 -0
  97. package/spec/atif/trajectory.schema.json +865 -0
  98. package/spec/openapi.yaml +13447 -0
@@ -0,0 +1 @@
1
+ export{b as EvolveUploadTimeoutError,a as UPLOAD_TIMEOUT_MS,c as postMultipartFile}from'./chunk-5GVMBEYI.js';
@@ -0,0 +1,138 @@
1
+ ---
2
+ # Generated by scripts/generate-skills.ts from docs-agents/SKILL.source.md. Do not edit; edit the source and run npm run generate:skills.
3
+ name: docs-agents
4
+ description: "Evolve SDK development for TypeScript and Python. Use when building applications with Evolve to run AI agents (Claude, Codex, Gemini, Qwen, Kimi, OpenCode, Droid) in secure sandboxes. Triggers: (1) Creating Evolve applications, (2) Configuring agents with skills, Integrations, MCP servers, (3) Using Swarm abstractions (map, filter, reduce, bestOf/best_of, verify), (4) Building Pipelines, (5) Structured output with schemas, (6) Session management, streaming, observability, (7) Checkpointing, storage & StorageClient, (8) Cost tracking (per-run and per-session spend), (9) Historical sessions & trace download via sessions() client. For hosted evals (datasets, jobs, trials, checks, analyses, the evolve CLI) read `evolve skills get evals`."
5
+ metadata:
6
+ internal: true
7
+ ---
8
+
9
+ # Evolve SDK
10
+
11
+ Build applications that run CLI agents in secure cloud sandboxes.
12
+
13
+ **Repo:** https://github.com/evolving-machines-lab/evolve
14
+
15
+ Hosted evals — datasets, jobs, trials, checks, analyses and the `evolve` CLI — are `evolve skills get evals`, not this skill.
16
+
17
+ ## Language Detection
18
+
19
+ Determine the language from (in priority order):
20
+
21
+ 1. **User specification** — if the user states a language, use it
22
+ 2. **Project signals** — imports, file extensions, package.json vs pyproject.toml
23
+ 3. **Ask** — if ambiguous, ask the user
24
+
25
+ - **TypeScript** (`@evolvingmachines/evolve`) — read from [typescript/](typescript/)
26
+ - **Python** (`evolvingmachines-evolve`) — read from [python/](python/)
27
+
28
+ ## Required Reading
29
+
30
+ Always read these three references **for the detected language** before writing any Evolve code:
31
+
32
+ **TypeScript:**
33
+ - [01-getting-started.md](typescript/01-getting-started.md) — Installation, authentication (Gateway, managed BYO provider keys, direct provider-key mode), core lifecycle, streaming basics, agent reference table
34
+ - [02-configuration.md](typescript/02-configuration.md) — Sandbox providers, full builder API, agent skills catalog, Managed integrations, MCP servers
35
+ - [03-runtime.md](typescript/03-runtime.md) — run(), executeCommand(), upload/download files, session controls, workspace layout, structured output, session management, storage & checkpointing, StorageClient, sessions() client, cost tracking, observability, error handling
36
+
37
+ **Python:**
38
+ - [01-getting-started.md](python/01-getting-started.md) — Installation, authentication (Gateway, managed BYO provider keys, direct provider-key mode), core lifecycle, streaming basics, agent reference table
39
+ - [02-configuration.md](python/02-configuration.md) — Sandbox providers, full constructor API, agent skills catalog, Managed integrations, MCP servers
40
+ - [03-runtime.md](python/03-runtime.md) — run(), execute_command(), upload/download files, session controls, workspace layout, structured output, session management, storage & checkpointing, StorageClient, sessions() client, cost tracking, observability, error handling
41
+
42
+ ## Critical Constraints
43
+
44
+ - **Model names** — Only use exact names from the Agent Reference table. Do not invent or guess model identifiers.
45
+ - [TS](typescript/01-getting-started.md#agent-reference) | [PY](python/01-getting-started.md#agent-reference)
46
+ - **Cleanup** — Always call `kill()` when done. Sandboxes bill until destroyed.
47
+ - [TS](typescript/01-getting-started.md#core-lifecycle) | [PY](python/01-getting-started.md#core-lifecycle)
48
+
49
+ ## Additional References
50
+
51
+ Read on demand when the user's task requires them:
52
+
53
+ | When to read | TypeScript | Python |
54
+ |-------------|-----------|--------|
55
+ | Building a UI, handling real-time events | [04-streaming.md](typescript/04-streaming.md) | [04-streaming.md](python/04-streaming.md) |
56
+ | Parallel agents (map/filter/reduce/bestOf/verify), Pipeline chaining | [05-swarm-pipeline.md](typescript/05-swarm-pipeline.md) | [05-swarm-pipeline.md](python/05-swarm-pipeline.md) |
57
+
58
+ ## Topic Index
59
+
60
+ ### Getting Started
61
+
62
+ | Topic | TypeScript | Python |
63
+ |-------|-----------|--------|
64
+ | Installation & requirements | [TS](typescript/01-getting-started.md#installation) | [PY](python/01-getting-started.md#installation) |
65
+ | Quick start (3 steps) | [TS](typescript/01-getting-started.md#quick-start) | [PY](python/01-getting-started.md#quick-start) |
66
+ | Core lifecycle (run, output, kill) | [TS](typescript/01-getting-started.md#core-lifecycle) | [PY](python/01-getting-started.md#core-lifecycle) |
67
+ | Streaming basics | [TS](typescript/01-getting-started.md#streaming) | [PY](python/01-getting-started.md#streaming) |
68
+ | Gateway, managed BYO provider keys, and direct provider-key mode | [TS](typescript/01-getting-started.md#authentication) | [PY](python/01-getting-started.md#authentication) |
69
+ | BYO subscriptions (Claude Max, Codex, Gemini) | [TS](typescript/01-getting-started.md#byo-claude-max-subscription) | [PY](python/01-getting-started.md#byo-claude-max-subscription) |
70
+ | Supported agents, models & defaults | [TS](typescript/01-getting-started.md#agent-reference) | [PY](python/01-getting-started.md#agent-reference) |
71
+ | Harness and model pairing (per-harness constraints) | [TS](typescript/01-getting-started.md#harness-and-model-pairing) | [PY](python/01-getting-started.md#harness-and-model-pairing) |
72
+
73
+ ### Configuration
74
+
75
+ | Topic | TypeScript | Python |
76
+ |-------|-----------|--------|
77
+ | Sandbox providers (E2B, Modal, Daytona) | [TS](typescript/02-configuration.md#sandbox-providers) | [PY](python/02-configuration.md#sandbox-providers) |
78
+ | Provider auto-resolution from env | [TS](typescript/02-configuration.md#auto-resolution) | [PY](python/02-configuration.md#auto-resolution) |
79
+ | Sandbox create options (image, network, user, homeDir) | [TS](typescript/02-configuration.md#sandbox-create-options) | [PY](python/02-configuration.md#sandbox-create-options) |
80
+ | Workspace modes (knowledge / swe) | [TS](typescript/02-configuration.md#workspace-modes) | [PY](python/02-configuration.md#workspace-modes) |
81
+ | Full builder/constructor API | [TS](typescript/02-configuration.md#evolve-instance) | [PY](python/02-configuration.md#evolve-instance) |
82
+ | Browser automation guide (setup, live view, replay) | [TS](typescript/02-configuration.md#browser-automation) | [PY](python/02-configuration.md#browser-automation) |
83
+ | Browser credentials (saved website logins) | [TS](typescript/02-configuration.md#browser-credentials) | [PY](python/02-configuration.md#browser-credentials) |
84
+ | Agent plugins/extensions | [TS](typescript/02-configuration.md#agent-plugins) | [PY](python/02-configuration.md#agent-plugins) |
85
+ | Agent skills catalog | [TS](typescript/02-configuration.md#agent-skills) | [PY](python/02-configuration.md#agent-skills) |
86
+ | Managed secrets (Dashboard-stored env secrets) | [TS](typescript/02-configuration.md#managed-secrets) | [PY](python/02-configuration.md#managed-secrets) |
87
+ | Managed integrations (auth paths, tool filtering, types) | [TS](typescript/02-configuration.md#managed-integrations) | [PY](python/02-configuration.md#managed-integrations) |
88
+ | MCP server config (STDIO / HTTP / SSE) | [TS](typescript/02-configuration.md#evolve-instance) | [PY](python/02-configuration.md#evolve-instance) |
89
+
90
+ ### Runtime
91
+
92
+ | Topic | TypeScript | Python |
93
+ |-------|-----------|--------|
94
+ | run() options (timeout, background, checkpoint) | [TS](typescript/03-runtime.md#run) | [PY](python/03-runtime.md#run) |
95
+ | executeCommand() / execute_command() | [TS](typescript/03-runtime.md#executecommand) | [PY](python/03-runtime.md#execute_command) |
96
+ | Upload files to sandbox | [TS](typescript/03-runtime.md) | [PY](python/03-runtime.md) |
97
+ | Download output files | [TS](typescript/03-runtime.md) | [PY](python/03-runtime.md) |
98
+ | Session controls (interrupt, pause, resume, kill) | [TS](typescript/03-runtime.md#session-controls) | [PY](python/03-runtime.md#session-controls) |
99
+ | Port forwarding | [TS](typescript/03-runtime.md#gethost) | [PY](python/03-runtime.md#get_host) |
100
+ | Workspace filesystem layout | [TS](typescript/03-runtime.md) | [PY](python/03-runtime.md) |
101
+ | Structured output (Zod / Pydantic / JSON Schema) | [TS](typescript/03-runtime.md#structured-output) | [PY](python/03-runtime.md#structured-output) |
102
+ | Multi-turn conversations | [TS](typescript/03-runtime.md#session-management) | [PY](python/03-runtime.md#session-management) |
103
+ | Pause, resume, reconnect, switch sandboxes | [TS](typescript/03-runtime.md#session-management) | [PY](python/03-runtime.md#session-management) |
104
+ | Storage & checkpointing (gateway mode) | [TS](typescript/03-runtime.md#storage--checkpointing) | [PY](python/03-runtime.md#storage--checkpointing) |
105
+ | StorageClient (list, get, download checkpoints) | [TS](typescript/03-runtime.md#listing--browsing-checkpoints) | [PY](python/03-runtime.md#listing--browsing-checkpoints) |
106
+ | Checkpoint lineage & restore | [TS](typescript/03-runtime.md#checkpoint-lineage) | [PY](python/03-runtime.md#checkpoint-lineage) |
107
+ | Historical sessions & trace download | [TS](typescript/03-runtime.md#historical-sessions--trace-download) | [PY](python/03-runtime.md#historical-sessions--trace-download) |
108
+ | Cost tracking (per-run & per-session spend) | [TS](typescript/03-runtime.md#cost-tracking) | [PY](python/03-runtime.md#cost-tracking) |
109
+ | Observability (dashboard + local logs) | [TS](typescript/03-runtime.md#observability) | [PY](python/03-runtime.md#observability) |
110
+ | Error handling | [TS](typescript/03-runtime.md#error-handling) | [PY](python/03-runtime.md#error-handling) |
111
+
112
+ ### Streaming
113
+
114
+ | Topic | TypeScript | Python |
115
+ |-------|-----------|--------|
116
+ | Event listeners (content, lifecycle, stdout, stderr) | [TS](typescript/04-streaming.md#event-listeners) | [PY](python/04-streaming.md#event-listeners) |
117
+ | LifecycleEvent & LifecycleReason | [TS](typescript/04-streaming.md#lifecycleevent) | [PY](python/04-streaming.md#lifecycleevent-typeddict-shape) |
118
+ | OutputEvent & SessionUpdate types | [TS](typescript/04-streaming.md#sessionupdate-types) | [PY](python/04-streaming.md#event-types-summary) |
119
+ | Tool events (ToolCall, ToolCallUpdate, ToolKind) | [TS](typescript/04-streaming.md#tool-events) | [PY](python/04-streaming.md#toolkind-reference) |
120
+ | Browser lifecycle event fields | [TS](typescript/04-streaming.md#browser-automation-streaming) | [PY](python/04-streaming.md#browser-automation-streaming) |
121
+ | UI integration example | [TS](typescript/04-streaming.md#ui-integration-example) | [PY](python/04-streaming.md#ui-integration-example) |
122
+
123
+ ### Swarm & Pipeline
124
+
125
+ | Topic | TypeScript | Python |
126
+ |-------|-----------|--------|
127
+ | Swarm setup (config, concurrency, retry) | [TS](typescript/05-swarm-pipeline.md) | [PY](python/05-swarm-pipeline.md) |
128
+ | Input types (FileMap, folders) | [TS](typescript/05-swarm-pipeline.md#input-types) | [PY](python/05-swarm-pipeline.md#input-types) |
129
+ | bestOf / best_of (N candidates + judge) | [TS](typescript/05-swarm-pipeline.md#bestof) | [PY](python/05-swarm-pipeline.md#best_of) |
130
+ | map (parallel processing) | [TS](typescript/05-swarm-pipeline.md#map) | [PY](python/05-swarm-pipeline.md#map) |
131
+ | filter (evaluate + threshold) | [TS](typescript/05-swarm-pipeline.md#filter) | [PY](python/05-swarm-pipeline.md#filter) |
132
+ | reduce (synthesize many to one) | [TS](typescript/05-swarm-pipeline.md#reduce) | [PY](python/05-swarm-pipeline.md#reduce) |
133
+ | verify (quality gate with feedback loop) | [TS](typescript/05-swarm-pipeline.md#verify-quality-gate) | [PY](python/05-swarm-pipeline.md#verify-quality-gate) |
134
+ | Result types (SwarmResult, ReduceResult, BestOfResult) | [TS](typescript/05-swarm-pipeline.md#result-types) | [PY](python/05-swarm-pipeline.md#result-types) |
135
+ | Chaining operations | [TS](typescript/05-swarm-pipeline.md#chaining-operations) | [PY](python/05-swarm-pipeline.md#chaining-operations) |
136
+ | Pipeline (fluent chaining, events, terminal) | [TS](typescript/05-swarm-pipeline.md#pipeline) | [PY](python/05-swarm-pipeline.md#pipeline) |
137
+
138
+ The installed CLI serves the current version of this skill: `evolve skills get agents --full`.
@@ -0,0 +1,81 @@
1
+ ## Documentation
2
+
3
+ - [TypeScript SDK](./typescript/)
4
+ - [Python SDK](./python/)
5
+ - [Cookbooks](https://github.com/evolving-machines-lab/evolve/tree/main/cookbooks)
6
+ - [Changelog](https://github.com/evolving-machines-lab/evolve/blob/main/CHANGELOG.md)
7
+
8
+ The SDK has two halves. One runs a CLI agent in a sandbox you control — that is the quickstart below. The other scores agents against datasets of tasks on Evolve's own infrastructure: you start a job, and read back per-trial rewards. Hosted evals are documented at https://docs.evolvingmachines.ai: `jobs()`, `datasets()`, and the `evolve` CLI.
9
+
10
+ ## Get Started
11
+
12
+ ### 1. Install the SDK
13
+
14
+ ```bash
15
+ npm install @evolvingmachines/evolve # TypeScript
16
+ pip install evolvingmachines-evolve # Python
17
+ ```
18
+
19
+ **Note:** Requires [Node.js 18+](https://nodejs.org/) (the Python SDK uses a lightweight Node.js bridge).
20
+
21
+ ### 2. Run your first agent
22
+
23
+ Get your Evolve API key at [dashboard.evolvingmachines.ai](https://dashboard.evolvingmachines.ai) ([see 3. below](#evolve-gateway)):
24
+ ```bash
25
+ # .env - Gateway
26
+ EVOLVE_API_KEY=sk-...
27
+ ```
28
+
29
+ To bring your own provider billing while keeping gateway features, save an Anthropic or OpenAI key in Dashboard → Secrets → BYO Provider Keys — those are the two providers this route serves today. Your app still uses only `EVOLVE_API_KEY`.
30
+
31
+ For fully local direct provider keys:
32
+ ```bash
33
+ # .env - Direct Provider Key Mode (local BYOK)
34
+ ANTHROPIC_API_KEY=sk-ant-... # or CLAUDE_CODE_OAUTH_TOKEN (Claude Max), OPENAI_API_KEY, GEMINI_API_KEY
35
+ E2B_API_KEY=e2b_... # sandbox provider, get at https://e2b.dev
36
+ ```
37
+
38
+ Then run:
39
+ ```typescript
40
+ import { Evolve } from "@evolvingmachines/evolve";
41
+
42
+ const evolve = new Evolve(); // auto-resolves env variables
43
+ await evolve.run({ prompt: "Create hello.txt with 'Hello World'" });
44
+ const output = await evolve.getOutputFiles(); // output.files
45
+ ```
46
+
47
+ ```python
48
+ from evolve import Evolve
49
+
50
+ evolve = Evolve() # auto-resolves env variables
51
+ await evolve.run(prompt="Create hello.txt with 'Hello World'")
52
+ output = await evolve.get_output_files() # output.files
53
+ ```
54
+
55
+ <a id="evolve-gateway"></a>
56
+
57
+ ### 3. Unlock full power with Evolve API key
58
+
59
+ Sign up at [dashboard.evolvingmachines.ai](https://dashboard.evolvingmachines.ai/) and get your **Evolve API key** for:
60
+ - Agent execution traces, observability and analytics
61
+ - Centralized billing across all providers
62
+ - Mix any model with any CLI agent
63
+ - $10 FREE CREDITS, no CC required
64
+
65
+ ### 4. Learn more
66
+
67
+ Check out the [documentation](https://github.com/evolving-machines-lab/evolve/tree/main/docs) and [cookbooks](https://github.com/evolving-machines-lab/evolve/tree/main/cookbooks).
68
+
69
+ ## Support + Talk with Founders
70
+
71
+ - [Community Discord](https://discord.gg/Q36D8dGyNF)
72
+ - [Schedule Demo](https://cal.com/brando-magnani/evolve-1-1-onboarding-chat)
73
+ - Email: [brandomagnani@evolvingmachines.ai](mailto:brandomagnani@evolvingmachines.ai)
74
+
75
+ ## Reporting Bugs
76
+
77
+ We welcome your feedback. File a [GitHub issue](https://github.com/evolving-machines-lab/evolve/issues) to report bugs or request features.
78
+
79
+ ## License
80
+
81
+ See the [LICENSE](https://github.com/evolving-machines-lab/evolve/blob/main/LICENSE) file for full terms and conditions.