Skip to main content

Limits & Quotas

This page summarizes the validation and runtime limits enforced by the Culvii platform and @culvii/kit.

Agent skills​

Skills are configured in metadata.runtimeDetails.skills on the primary agent. Understanding how these limits apply depends on three scopes:

  • Configured skill source (per entry in metadata.runtimeDetails.skills): File count (200 files) and bundle size (8 MiB) apply independently to each entry in the skills array. If a single entry points to a parent folder containing multiple skills (for example source: 'skills'), all skills in that folder share one 200-file and 8 MiB budget. If you list them as separate entries (for example source: 'skills/pdf' and source: 'skills/xlsx'), each entry gets its own 200-file and 8 MiB budget, even when both come from the same repository and merge into /skills/<repo-name>.
  • Individual skill (SKILL.md): Each SKILL.md file inside a selected source defines one skill via its YAML frontmatter (name and description).
  • Session skill catalog (across the entire session): Full SKILL.md files are not inlined into the system prompt on every turn. Instead, the platform injects a compact JSON catalog (skill_id, name, description) for all installed skills into the primary agent's system prompt, and the agent loads individual skill files on demand using read_skill.

Validation happens in two stages: configuration-shape validation runs during culvii dev and culvii deploy (checking url, ref, credentialId, source, fallback_paths, and repository mount collisions without contacting GitHub), while session-start validation runs when a new session begins (resolving ref to a 40-character commit SHA, fetching the recursive GitHub tree, downloading and verifying blobs, and parsing SKILL.md frontmatter).

LimitValueDetails
Files per configured source200 filesMaximum number of regular Git files (100644 or 100755) imported by a single entry in metadata.runtimeDetails.skills. Counts SKILL.md and all files in subfolders under the resolved source (or first matching fallback_paths entry); excludes directory entries and repository files outside that path.
Size per file1 MiBMaximum raw (unencoded) byte size of any single file in a skill source.
Total size per configured source8 MiBMaximum combined raw (unencoded) byte size of all selected files within one configured skills entry. Separate entries in metadata.runtimeDetails.skills each get their own 200-file and 8 MiB allowance.
Combined catalog prompt size1 MiBMaximum UTF-8 byte length of the session-wide skill catalog prompt (the JSON list of { skill_id, name, description } across all installed skills plus fixed usage instructions) injected into the primary agent's system prompt.
Max skill path length500 charactersMaximum character length for source, each fallback_paths entry, and every repository-relative file path within a skill (measured from the repository root, e.g. skills/pdf/references/checklist.md). Paths cannot start with /, contain \, control characters, or . / .. segments.
Max fallback_paths per source100 entriesWhen fallback_paths is provided on a skill source, it must be a non-empty array of 1–100 ordered alternative repository-relative paths checked if source contains no skill instructions (only the first matching path is imported).
Skill name format1–64 charactersRequired name field in SKILL.md YAML frontmatter. Must match ^[a-z0-9][a-z0-9-]{0,63}$, start with a lowercase ASCII letter or digit, contain only lowercase letters, digits, and hyphens, and be unique across all skills selected by that source.
Skill description length1–1,024 charactersRequired non-empty description field in SKILL.md YAML frontmatter (no control characters other than \n, \r, or \t). The YAML frontmatter block itself must have unique keys and allows at most 10 YAML aliases.
GitHub repository URL lengthMax 500 charactersApplies to url on each github_repository source. Must be an HTTPS https://github.com/<owner>/<repo> URL with no custom port, query string, fragment, or embedded credentials.
GitHub ref length1–200 charactersApplies to the optional ref field (branch, tag, or commit SHA). Defaults to 'HEAD', cannot contain whitespace or control characters, and is resolved to an exact 40-character commit SHA at session start.
GitHub credentialId format1–128 charactersMatches ^[A-Za-z0-9_-]{1,128}$. References a GitHub credential from the Console's Integrations tab and is required for both public and private repositories so skill downloads use authenticated GitHub API rate limits.
Max repository Git tree entries10,000 entriesCounts all files and directories across the entire GitHub repository's recursive Git tree at the target commit, not just the source folder. Repositories whose recursive tree exceeds 10,000 entries are rejected.
Max GitHub API response size10 MiBMaximum JSON payload size accepted from GitHub commit and recursive tree API calls.
GitHub skill acquisition timeouts20 seconds / 5 minutesEach individual GitHub API HTTP request times out after 20 seconds, and downloading an entire configured skill source (commit lookup, tree fetch, and all blob downloads) must finish within 5 minutes.

Agent runtime and sandbox​

LimitValueDetails
Default maxIterations50 stepsMaximum number of model reasoning and tool-loop steps an agent can take in a single run before producing a final answer. Configured on the primary agent and applies to the entire session turn, including all secondary agent delegations.
Default maxToolCalls100 callsMaximum total number of individual tool executions allowed in a single agent run. Configured on the primary agent and applies to the entire session turn, including all secondary agent delegations.
Context windowPer-model catalogContext-window capacity and maximum output token limits are configured per model in the platform model catalog (there is no default context window). The platform includes the current user prompt when deciding whether older session turns must be compacted.
Sandbox file read / attachment size10 MiBMaximum file size when reading whole files from the sandbox for attach_output_file artifacts and read_skill file loads.
read_file excerpt size2,000 lines / 50 KiBMaximum UTF-8 text excerpt returned by a single read_file tool call (paginated via offset and limit).
Sandbox command timeout (exec_process)60 seconds (max 300 seconds)Default wall-clock timeout per exec_process command when timeoutMs is omitted; individual calls can request timeoutMs up to 300,000 ms (5 minutes).
Sandbox command / tool output size50 KiBMaximum stdout / stderr or response output returned per stream by exec_process, list_files, search_text, git, and web_fetch before truncation.
Sandbox pod ready timeout120 secondsMaximum time the platform waits for a session sandbox environment to become ready during creation or restoration.
Sandbox idle TTL30 minutesInactivity duration before an idle session sandbox is snapshotted and its pod is stopped.
sandboxProfile name'default'metadata.runtimeDetails.sandboxProfile defaults to 'default', and only 'default' is supported on the platform's single default sandbox image.
networking.allowed_hosts hostnameMax 253 charactersConfigured in metadata.runtimeDetails.networking.allowed_hosts on the primary agent when type: 'limited'. Must be exact public bare hostnames (63 characters max per DNS label); rejects schemes, ports, paths, wildcards (*), IP addresses, and localhost/.local/.internal names.

Workflows and composition​

LimitValueDetails
Max loop items500 itemsMaximum items a core.loop step can iterate over in a single execution, enforced at culvii dev / culvii deploy for literal items arrays and at runtime for expression-resolved arrays (both sequential and parallel loops). Nested core.loop steps are rejected.
Max agent/workflow composition depth3 nodesMaximum call-chain depth across workflows and agents. Valid 3-node chains are workflow → agent → workflow (where the leaf workflow contains no core.agent step) and agent → workflow → agent (where the leaf agent declares no workflow tools). Chains of 4 or more nodes fail validation on culvii dev and culvii deploy.
Workflow binary file size100 MiBMaximum size of a single binary file processed within a workflow (e.g. via S3 Get or Manual Trigger).
Platform HTTP request body size150 MiBMaximum size of the HTTP request body accepted by the platform (e.g. for workflow execution starts). This is the default whole-request HTTP body cap (accommodating base64 overhead on a 100 MiB binary file).
Single resource definition size5 MiBMaximum UTF-8 JSON byte size of a single agent, workflow, or surface definition during culvii deploy (enforced by both the CLI and the platform deploy service).
Deploy plan request body size20 MiBMaximum HTTP request body size for deploy plans (including decompressed gzip/deflate payloads). culvii deploy automatically gzip-compresses deploy plan payloads over 512 KiB.
Agent definition route body size10 MiBMaximum HTTP request body size on direct agent creation and update API routes.
culvii dev inactivity timeout30 minutesCloses the culvii dev draft-sync WebSocket after 30 minutes without developer activity (saving a file to trigger a sync, or starting a draft workflow/agent run from the Console). Protocol-level 15-second WebSocket ping/pong heartbeats keep the connection alive but do not reset this inactivity timer.

Dynamic UI surfaces​

LimitValueDetails
Surface id format1–63 charactersApplies to Surface.id. Must match ^[a-z0-9][a-z0-9-]{0,62}$ (kebab-case). Individual component id values inside definition.components allow 1–128 characters matching ^[A-Za-z0-9][A-Za-z0-9._-]{0,127}$.
Max serialized definition size256 KiB (262,144 bytes)Maximum UTF-8 byte length of JSON.stringify(definition), including all components, props, actions, and wait-surface form fields.
Max components per surface300 componentsdefinition.components must contain 1–300 components. All components must have unique IDs within the surface and be reachable by traversing children from definition.root.
Max component tree depth12 levelsMaximum nesting depth of the acyclic component graph starting at definition.root (depth 1). Cycles in children references are rejected.
Wait-surface file input maxFiles1–5 filesApplies to { type: 'file' } fields in definition.form.fields on a wait surface. Caps how many files can be uploaded for that field when resuming a paused step (defaults to 5 when multiple: true, or 1 when multiple is omitted/false).
Wait-surface file input maxBytesMax 10 MiB (10,485,760 bytes)Applies to { type: 'file' } fields in definition.form.fields on a wait surface. Positive integer up to 10 * 1024 * 1024 bytes capping the size of each individual file uploaded to that field.