fmxexpress/pasclaw-build-deploy
Public
4
runs
Run fmxexpress/pasclaw-build-deploy with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
Input schema
The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| message |
string
|
Build task. The agent runs up to max_iters "
"tool-using iterations to satisfy it.
|
|
| max_iters |
integer
|
50
Min: 1 Max: 500 |
Tool-loop iteration budget. One iteration ~= one "
"model response (which may include multiple tool calls).
|
| timeout_seconds |
integer
|
3600
Min: 30 |
Subprocess timeout in seconds. Default 3600 = 1 h. "
"Set high for long horizon builds; Replicate enforces its own "
"container ceiling on top of this.
|
| workspace_in |
string
|
Workspace archive from a previous build. "
"Leave empty for a fresh run. Replicate handles both "
"file-uploads and URL inputs through this. For very "
"large URL-backed workspaces, prefer workspace_in_url "
"to get parallel pget download.
|
|
| workspace_in_url |
string
|
|
Explicit URL to a previous-build workspace "
"archive. Leave empty for a fresh run. When set, "
"downloaded via pget for parallelism; takes precedence "
"over workspace_in.
|
| openai_api_key |
string
|
OpenAI API key. Stored encrypted; never surfaces in logs.
|
|
| anthropic_api_key |
string
|
Anthropic API key. Stored encrypted; never surfaces in logs.
|
|
| gemini_api_key |
string
|
Google Gemini API key. Stored encrypted; never surfaces in logs.
|
|
| groq_api_key |
string
|
Groq API key. Stored encrypted; never surfaces in logs.
|
|
| openrouter_api_key |
string
|
OpenRouter API key. Stored encrypted; never surfaces in logs.
|
|
| deepseek_api_key |
string
|
DeepSeek API key. Stored encrypted; never surfaces in logs.
|
|
| ollama_url |
string
|
|
Base URL of an Ollama server reachable from the cog "
"container (e.g. an ngrok tunnel to a laptop's local "
"instance). Leave empty to skip.
|
| lmstudio_url |
string
|
|
Base URL of an LM Studio server reachable from the "
"cog container (default LM Studio port is 1234). Leave "
"empty to skip.
|
| vllm_url |
string
|
|
Base URL of a vLLM server reachable from the cog "
"container (default vLLM port is 8000). Leave empty to skip.
|
| custom_provider_kind |
string
|
|
Catalog kind for a custom provider (e.g. mistral, "
"xai, cerebras, moonshot, qwen, zhipu, perplexity, "
"nvidia, volcengine, minimax, novita, litellm, mimo). "
"Use 'openai-compat' for any other OpenAI-compatible "
"endpoint not in PasClaw's catalog. Leave empty to skip.
|
| custom_provider_url |
string
|
|
api_base URL for the custom provider. Required when "
"custom_provider_kind is set.
|
| custom_provider_key |
string
|
API key for the custom provider. Stored encrypted; "
"never surfaces in logs. Leave empty if the endpoint "
"needs no auth.
|
|
| custom_provider_model |
string
|
|
Default model id for the custom provider. Leave "
"empty to let the provider pick (some servers route "
"missing model ids to whatever is currently loaded).
|
| provider |
string
|
|
LLM provider to route through. One of openai, "
"anthropic, gemini, groq, openrouter, deepseek, ollama, "
"lmstudio, vllm, or whatever you put in "
"custom_provider_kind. Empty = first configured "
"provider wins.
|
| model |
string
|
|
Override model id. Empty = provider's catalog default.
|
| mode |
None
|
build
|
None
|
| profile |
string
|
max-build
|
PasClaw config profile applied on top of stock "
"defaults. `max-build` (default) turns on web_fetch, "
"vector_search, auto_router, prompt_cache, task-aware "
"memory orientation, promptware guard, the self-improving-"
"skills suite, and bumps tool_output_cap to 16 KB -- the "
"richest unattended-build toolset. (Note: web_search is a "
"max-build *flag*, but the tool only registers when "
"PasClaw is also configured with a search provider. This "
"cog doesn't supply one, so web_search isn't available "
"out of the box -- use web_fetch.) Other choices: "
"`baseline` (everything off, useful for A/B), `low-token` "
"(cheaper, smaller context window), `security` (workspace "
"restriction + shell deny + private-network block), "
"`all-on` (max-build plus every remaining flag flipped "
"on). Empty to skip profile application.
|
| deploy_to_cloudflare |
boolean
|
True
|
After pasclaw build completes, run `wrangler "
"deploy --temporary` against any wrangler.toml the agent "
"produced in the workspace. Cloudflare's temporary-accounts "
"feature (https://blog.cloudflare.com/temporary-accounts/) "
"gives you a 60-minute throwaway account + a claim URL to "
"convert it to permanent, with no API key required on the "
"cog side. Skipped silently if no wrangler.toml is in the "
"workspace. Set False to skip the deploy step entirely.
|
| wrangler_project_path |
string
|
|
Path INSIDE the workspace to the directory "
"containing wrangler.toml. Default empty = auto-detect "
"the first wrangler.toml found under "
"$PASCLAW_HOME/workspace/. Use this when the agent "
"produces multiple wrangler projects and you want a "
"specific one deployed.
|
{
"type": "object",
"title": "Input",
"required": [
"message"
],
"properties": {
"mode": {
"enum": [
"build",
"plan",
"plan build",
"plan build goal"
],
"type": "string",
"title": "mode",
"description": "An enumeration.",
"default": "build",
"x-order": 20
},
"model": {
"type": "string",
"title": "Model",
"default": "",
"x-order": 19,
"description": "Override model id. Empty = provider's catalog default."
},
"message": {
"type": "string",
"title": "Message",
"x-order": 0,
"description": "Build task. The agent runs up to max_iters \"\n \"tool-using iterations to satisfy it."
},
"profile": {
"type": "string",
"title": "Profile",
"default": "max-build",
"x-order": 21,
"description": "PasClaw config profile applied on top of stock \"\n \"defaults. `max-build` (default) turns on web_fetch, \"\n \"vector_search, auto_router, prompt_cache, task-aware \"\n \"memory orientation, promptware guard, the self-improving-\"\n \"skills suite, and bumps tool_output_cap to 16 KB -- the \"\n \"richest unattended-build toolset. (Note: web_search is a \"\n \"max-build *flag*, but the tool only registers when \"\n \"PasClaw is also configured with a search provider. This \"\n \"cog doesn't supply one, so web_search isn't available \"\n \"out of the box -- use web_fetch.) Other choices: \"\n \"`baseline` (everything off, useful for A/B), `low-token` \"\n \"(cheaper, smaller context window), `security` (workspace \"\n \"restriction + shell deny + private-network block), \"\n \"`all-on` (max-build plus every remaining flag flipped \"\n \"on). Empty to skip profile application."
},
"provider": {
"type": "string",
"title": "Provider",
"default": "",
"x-order": 18,
"description": "LLM provider to route through. One of openai, \"\n \"anthropic, gemini, groq, openrouter, deepseek, ollama, \"\n \"lmstudio, vllm, or whatever you put in \"\n \"custom_provider_kind. Empty = first configured \"\n \"provider wins."
},
"vllm_url": {
"type": "string",
"title": "Vllm Url",
"default": "",
"x-order": 13,
"description": "Base URL of a vLLM server reachable from the cog \"\n \"container (default vLLM port is 8000). Leave empty to skip."
},
"max_iters": {
"type": "integer",
"title": "Max Iters",
"default": 50,
"maximum": 500,
"minimum": 1,
"x-order": 1,
"description": "Tool-loop iteration budget. One iteration ~= one \"\n \"model response (which may include multiple tool calls)."
},
"ollama_url": {
"type": "string",
"title": "Ollama Url",
"default": "",
"x-order": 11,
"description": "Base URL of an Ollama server reachable from the cog \"\n \"container (e.g. an ngrok tunnel to a laptop's local \"\n \"instance). Leave empty to skip."
},
"groq_api_key": {
"type": "string",
"title": "Groq Api Key",
"format": "password",
"x-order": 8,
"nullable": true,
"writeOnly": true,
"description": "Groq API key. Stored encrypted; never surfaces in logs.",
"x-cog-secret": true
},
"lmstudio_url": {
"type": "string",
"title": "Lmstudio Url",
"default": "",
"x-order": 12,
"description": "Base URL of an LM Studio server reachable from the \"\n \"cog container (default LM Studio port is 1234). Leave \"\n \"empty to skip."
},
"workspace_in": {
"type": "string",
"title": "Workspace In",
"format": "uri",
"x-order": 3,
"nullable": true,
"description": "Workspace archive from a previous build. \"\n \"Leave empty for a fresh run. Replicate handles both \"\n \"file-uploads and URL inputs through this. For very \"\n \"large URL-backed workspaces, prefer workspace_in_url \"\n \"to get parallel pget download."
},
"gemini_api_key": {
"type": "string",
"title": "Gemini Api Key",
"format": "password",
"x-order": 7,
"nullable": true,
"writeOnly": true,
"description": "Google Gemini API key. Stored encrypted; never surfaces in logs.",
"x-cog-secret": true
},
"openai_api_key": {
"type": "string",
"title": "Openai Api Key",
"format": "password",
"x-order": 5,
"nullable": true,
"writeOnly": true,
"description": "OpenAI API key. Stored encrypted; never surfaces in logs.",
"x-cog-secret": true
},
"timeout_seconds": {
"type": "integer",
"title": "Timeout Seconds",
"default": 3600,
"minimum": 30,
"x-order": 2,
"description": "Subprocess timeout in seconds. Default 3600 = 1 h. \"\n \"Set high for long horizon builds; Replicate enforces its own \"\n \"container ceiling on top of this."
},
"deepseek_api_key": {
"type": "string",
"title": "Deepseek Api Key",
"format": "password",
"x-order": 10,
"nullable": true,
"writeOnly": true,
"description": "DeepSeek API key. Stored encrypted; never surfaces in logs.",
"x-cog-secret": true
},
"workspace_in_url": {
"type": "string",
"title": "Workspace In Url",
"default": "",
"x-order": 4,
"description": "Explicit URL to a previous-build workspace \"\n \"archive. Leave empty for a fresh run. When set, \"\n \"downloaded via pget for parallelism; takes precedence \"\n \"over workspace_in."
},
"anthropic_api_key": {
"type": "string",
"title": "Anthropic Api Key",
"format": "password",
"x-order": 6,
"nullable": true,
"writeOnly": true,
"description": "Anthropic API key. Stored encrypted; never surfaces in logs.",
"x-cog-secret": true
},
"openrouter_api_key": {
"type": "string",
"title": "Openrouter Api Key",
"format": "password",
"x-order": 9,
"nullable": true,
"writeOnly": true,
"description": "OpenRouter API key. Stored encrypted; never surfaces in logs.",
"x-cog-secret": true
},
"custom_provider_key": {
"type": "string",
"title": "Custom Provider Key",
"format": "password",
"x-order": 16,
"nullable": true,
"writeOnly": true,
"description": "API key for the custom provider. Stored encrypted; \"\n \"never surfaces in logs. Leave empty if the endpoint \"\n \"needs no auth.",
"x-cog-secret": true
},
"custom_provider_url": {
"type": "string",
"title": "Custom Provider Url",
"default": "",
"x-order": 15,
"description": "api_base URL for the custom provider. Required when \"\n \"custom_provider_kind is set."
},
"custom_provider_kind": {
"type": "string",
"title": "Custom Provider Kind",
"default": "",
"x-order": 14,
"description": "Catalog kind for a custom provider (e.g. mistral, \"\n \"xai, cerebras, moonshot, qwen, zhipu, perplexity, \"\n \"nvidia, volcengine, minimax, novita, litellm, mimo). \"\n \"Use 'openai-compat' for any other OpenAI-compatible \"\n \"endpoint not in PasClaw's catalog. Leave empty to skip."
},
"deploy_to_cloudflare": {
"type": "boolean",
"title": "Deploy To Cloudflare",
"default": true,
"x-order": 22,
"description": "After pasclaw build completes, run `wrangler \"\n \"deploy --temporary` against any wrangler.toml the agent \"\n \"produced in the workspace. Cloudflare's temporary-accounts \"\n \"feature (https://blog.cloudflare.com/temporary-accounts/) \"\n \"gives you a 60-minute throwaway account + a claim URL to \"\n \"convert it to permanent, with no API key required on the \"\n \"cog side. Skipped silently if no wrangler.toml is in the \"\n \"workspace. Set False to skip the deploy step entirely."
},
"custom_provider_model": {
"type": "string",
"title": "Custom Provider Model",
"default": "",
"x-order": 17,
"description": "Default model id for the custom provider. Leave \"\n \"empty to let the provider pick (some servers route \"\n \"missing model ids to whatever is currently loaded)."
},
"wrangler_project_path": {
"type": "string",
"title": "Wrangler Project Path",
"default": "",
"x-order": 23,
"description": "Path INSIDE the workspace to the directory \"\n \"containing wrangler.toml. Default empty = auto-detect \"\n \"the first wrangler.toml found under \"\n \"$PASCLAW_HOME/workspace/. Use this when the agent \"\n \"produces multiple wrangler projects and you want a \"\n \"specific one deployed."
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{
"type": "array",
"items": {
"type": "string",
"format": "uri"
},
"title": "Output"
}