跳转至

PRAXO-CORE for MATLAB and Octave

Native Core implementation with source tag matlab/v0.2.1. It passes all eleven vector groups under GNU Octave 11.3.0 and includes the native agent loop, memory store, checkpoint allowlist, lexical path policy, context compaction, event sinks, middleware helpers, and tool selection. It does not delegate its behavior to Go or another language Core.

Local validation uses GNU Octave 11.3.0; MATLAB compatibility is a target, not yet independently verified. The source tag does not imply package-registry publication, production readiness, or a delivery date.

Run the Checks

With Python 3.10+ and an Octave CLI available, from the repository root:

python language/matlab/run-tests.py
python language/matlab/api-snapshot.py --check

Set OCTAVE or pass --octave /path/to/octave-cli to select the interpreter. Python only launches the native tests and checks the source API inventory. The implementation and tests run in Octave, not Python. The runner covers all eleven shared vector groups and verifies each fixture's group and SPEC_VERSION before running it.

API

Add language/matlab to the interpreter path and call:

node = praxo.parse_json('{"name":"echo","input":{"text":"hi"}}');
raw = praxo.encode_json(node);
call = praxo.parse_tool_call(raw);
paths = praxo.validate_schema(praxo.parse_json('{"type":"string"}'), node);
[valid, manifest] = praxo.validate_manifest('{}');
result = praxo.agent_run('hello', @(request) struct('content', 'hello'), {}, struct());

JSON nodes have kind and value fields. Objects use an N-by-2 cell array of original keys and typed values; arrays use cells; null is a distinct kind. This avoids host JSON decoders conflating null, empty arrays, and singleton arrays or rewriting object keys. JSON strings are represented as UTF-8 bytes in character vectors; MATLAB's character model has not yet been validated.

Agent Loop

praxo.agent_run(prompt, model, tools, options) accepts a character-vector prompt, a model function handle, a cell array of tool structs, and an options struct. The model receives a struct with messages and tools cell arrays and returns a struct with character-vector content, optional toolCalls cell array, and optional nonnegative integer inputTokens and outputTokens. Each call has character-vector id and name, and arguments as a typed JSON object node. Each tool has a unique name, optional description, and an invoke function handle receiving the arguments node and returning a JSON node. The tool result is JSON-encoded and added to subsequent model messages with its toolCallId. Calls run sequentially. Callback exceptions fail the run.

Options maxSteps and maxTokens default to 8 and 0 respectively; zero tokens means unlimited, and steps must be positive. The result contains output, steps, token counts, ordered event names, toolInvocations, messages, errorCode, and errorMessage. An empty errorCode indicates success. Budget failures use AGENT_MAX_STEPS or AGENT_MAX_TOKENS; missing tools use TOOL_NOT_FOUND, while invalid or failing model and tool callbacks use local MODEL_ERROR and TOOL_ERROR. Invalid configuration raises praxo:agent. Events are recorded rather than streamed. Token budgets depend on counts reported by the model, and are checked before accepting its message.

Local parity inventory: agent.Agent.Run maps partially to praxo.agent_run (P2); the callback API and loop cover the shared agent-loop vectors, not the full reference agent surface. The shared parity inventory remains unchanged.

Current Limits

  • Numbers are finite double-precision values; large integers and decimal spellings may lose precision. Do not use these codecs for values requiring exact numeric preservation. Invalid UTF-8, malformed escapes, trailing data, and nonfinite numbers are rejected.
  • JSON input and output are bounded to 1,048,576 characters and nesting to 64. The tool-call helpers reject inputs over 262,144 characters.
  • Tool calls cover canonical JSON, XML-style, dotted tags and plain dotted lines. Other reference formats such as DSML, invoke, todo and skill-install are not implemented. Parsed governance metadata is returned under metadata; generated call IDs are not provided. Markup stripping is not an authorization control or security sanitizer.
  • Schema patterns accept a limited anchored ASCII subset, not full RE2. Unsupported patterns fail explicitly with praxo:schema; pattern input is bounded. Unknown JSON Schema keywords follow the documented subset behavior.
  • Manifest validation rejects duplicate and unknown fields and validates declarations. It does not verify signatures, establish trust, execute plugins, or enforce OS sandboxing. Duplicate-field rejection is stricter than the Go JSON decoder.
  • Core-local errors are not new shared wire error codes. Neither passing all eleven vector groups nor an Octave test implies full Framework or Go feature parity.

The source is MIT; see LICENSE. Octave is a separate GPL-licensed interpreter and test tool, not a package dependency or code copied into this implementation. MATLAB is a separate proprietary runtime.

See language policy, parity inventory, and implementation support.