Project context

Project context gives the Cactal agent durable information about one website. The Context tab shows it as three groups of the same kind of entry, a title and text: About this project goes with every request, everything under Read when relevant is looked up only when a request calls for it, and Agent notes are what the agent keeps for itself. Open any entry to read or edit it in the same editor. The agent loads project knowledge, agent notes, and the file index when it starts handling your request, including when it continues after an approval pause. During the request, search and read tools retrieve current document content, and tool results report changes the agent makes. Notes consolidated during preparation are available to the same run.

​

About this project

About this project (project knowledge in the API) is one free-form text document per website that the Cactal agent sees in full on every request. Use plain text, Markdown, headings, lists, or any structure that works for you. Write the brand voice, audience details, business facts, terminology, and design rules that should consistently shape the agent’s work. Only you edit this text; the document holds up to 20,000 characters, and your current request still takes precedence when it conflicts with older project knowledge.

​

Agent notes

Agent notes appear on the Context tab once the agent has written some, and go with every request too. Cactal writes them for you: whenever a long conversation is summarized, it distills the durable facts, decisions, rejected directions, and constraints from the turns being summarized into a short list, drops anything the agent can rediscover from the website itself such as progress logs and version numbers, and keeps the whole list under 4,000 characters, asking itself to compress when a rewrite runs long. Each rewrite shows up as a step in the agent conversation. Tell the agent to remember or forget something and the next rewrite carries it into the notes. Open either entry to edit it whenever it is wrong or out of date; saving an empty text clears it. If a text changed while you were editing it, saving asks you to load the latest version first so nothing is overwritten. Agents connected over MCP or the API read the same texts and keep their own notes through the agent notes operations; see Bring your own agent.

​

Context entries

Everything under Read when relevant is an entry: pasted text, an uploaded document, or an image. Use Add on the Context tab to write or paste text, or to upload files; you can also drop files anywhere on the tab, or attach them to a message in the agent conversation, where a document becomes a context entry the same way and appears here at once. Each document is converted into bounded Markdown. PDFs and DOCX files use Firecrawl Parse, while text files and pasted text are normalized locally. Cactal creates a one-sentence description that helps the agent decide when to read the entry, and a short title for pasted text; uploads keep their filename as the title. The agent receives only a compact index by default, then searches or reads selected ranges on demand. Open an entry to edit it. You can rename it and change the text the agent reads, which is useful when a PDF extracted badly or contains sections that do not matter. Editing never changes an uploaded original, which stays downloadable from the editor. API and MCP clients do the same with websiteKnowledge.create (POST /websiteKnowledge/text), websiteKnowledge.update (PATCH /websiteKnowledge/{resourceId}), and websiteKnowledge.get (GET /websiteKnowledge/{resourceId}), which returns the full text. Images remain images and are returned directly when the agent needs to inspect them. Each image also carries its extracted color palette as colors, transparentShare, and translucentShare in the index the agent receives, so the exact brand colors in a moodboard or reference screenshot reach the agent without a request. For short relevant documents, the agent can read directly. For larger documents, it can search several literal terms across selected files together and receive compact passages with overlapping text merged. This lets it gather evidence for independent questions in one request and read further only when needed. API and MCP clients can use websiteKnowledge.search (POST /websiteKnowledge/search) with websiteId, selected resourceIds, and 1–8 queries. Matching ignores case and treats each query as literal text within a line. All queries share maxCharacters, from 4,000 to 16,000 characters, defaulting to 8,000. The response includes up to 20 passages with source line ranges and zero-based queryIndexes into the returned queries array. Each query reports matched and truncated; truncation means more evidence may remain. A passage’s clipped flag indicates that its first or last line is partial. Missing, unavailable, non-text, and out-of-website ids appear in unavailableResourceIds, while available documents still return results. This is the single search operation, using the websiteKnowledge.search permission. To search one document for one term, pass one entry in each array. Ranged reads remain available.

​

Supported files and limits

A website can keep up to 25 context entries, pasted text included. You can download an uploaded original directly from private storage at any time from its editor. PDFs can contain up to 50 pages. Documents can be up to 10 MiB, while images can be up to 2 MB. On the Context tab, a larger photo is compressed to fit, and HEIC, AVIF, and BMP images are converted to JPEG or WebP before they upload. Uploads reserve a slot while the request is running. If preparation fails, Cactal discards the upload and releases the slot. Adding a file or text whose contents already exist in Context, from the tab, the API, or a chat message, reuses the existing entry instead of adding a copy. Password-protected, corrupt, unsupported mismatches, legacy DOC/PPT, executable, archive, audio, video, and unlisted file types are rejected. Firecrawl processes no more than 50 PDF pages, and Cactal rejects the upload rather than retaining truncated content.

​

Processing limits

Firecrawl first extracts native PDF text and automatically falls back to OCR for scanned or image-only pages. TXT and Markdown files are normalized directly by Cactal without being sent for document parsing. TXT and Markdown files saved as UTF-8, UTF-16, or common Windows text are converted automatically. If a file named as TXT or Markdown is actually a DOCX document, Cactal detects and repairs its type before processing it. Markdown preserves document content for search and ranged reads, but it does not reproduce every visual detail of a PDF or Word document.

​

Privacy

Originals and normalized text remain private to the website. PDF and DOCX bytes are sent to Firecrawl solely for document parsing and are subject to Firecrawl’s data-processing terms. To create the short description, Cactal sends a bounded text excerpt or the uploaded image to its configured AI inference provider. The full document is not added to every agent request. Project knowledge remains private to the website and is sent to the configured AI inference provider as part of each agent request. Clearing the field removes it from the context loaded for the next agent run or approval continuation. Deleting a context entry makes it unavailable to search and read tools immediately and removes it from the index loaded for the next agent run or approval continuation. Physical storage cleanup follows Cactal’s retained deletion lifecycle.