cordis-runtime 0.2.0

Minimal host runtime for Cordis Core.

Cordis Runtime

Cordis Runtime is the minimal host bridge for Cordis Core. It does not call a model and it does not split tasks.

The semantic boundary is explicit:

user language
    -> host/main model interprets intent
    -> structured Task Contract
    -> Cordis Runtime + Core
    -> compact model context and control signal

For an agent with tool calling, the main model fills the begin arguments as part of its normal turn. This does not require a second model call. A non-agent application that accepts raw natural language must provide an optional Task Interpreter. Task decomposition remains the responsibility of a Planner.

Minimal use

from cordis_core import CordisRuntime
from cordis_runtime import CordisHostRuntime

runtime = CordisHostRuntime(CordisRuntime("cordis-state.json"))

turn = runtime.begin({
    "task": {
        "goal": "Fix the login integration test",
        "domain": "software",
        "project_id": "my-app",
        "strategy_id": "inspect_logs_first",
        "stakes": "medium",
    },
    "complexity": 0.4,
    "current_step": "Inspect the failing test and logs",
    "constraints": ["Do not change the database schema"],
    "acceptance_evidence": ["login integration test passes"],
})

# Send turn["model_context"] to the host's existing planner or main model.

The host calls check_action(...) before an action, observe(...) for any plan/tool/artifact/test/error event, and finish(...) with observable evidence after execution. When constructed with a CognitiveStore, Runtime retrieves a small project-safe snapshot on begin, supports deduplicated query(...), and persists the final episode through finish(...).

v0.1 boundary

Runtime provides:

• structured Task Contract validation through Core;
• task-local Focus State;
• deterministic control modes;
• compact model context;
• an experimental lexical drift heuristic, never a safety or attention guarantee;
• evidence-bound feedback delegation.
• optional CognitiveStore retrieval, event capture, and episode write-back.

Runtime does not provide natural-language interpretation, planning, model calls, tool execution, durable conversation memory, or an HTTP service.

check_action is deliberately conservative metadata: it reports lexical overlap and obvious destructive terms. Hosts must not treat it as semantic understanding, an authorization decision, or a complete attention-drift guard.