Skip to content

AI Mode configuration

Experimental

Provider-backed AI, Planner behavior, investigation sessions, code patches, memory, and Studio AI internals are experimental in v0.7.0.

Aksara configuration uses the global aksara.conf.settings object. Do not add an AKSARA = {...} dictionary; the runtime does not read that pattern.

Enable provider-backed AI explicitly:

AKSARA_AI_ENABLED=true

Then configure a provider with the current AI Hub path:

aksara ai-hub configure openai
aksara ai-hub status
aksara ai-hub doctor

See AI providers for current, compatibility, and deprecated provider layers.

Runtime limits

The real prompt-pack runtime accepts in-process limits per call:

from aksara.ai.limits import AgentRuntimeLimits
from aksara.ai.runtime import run_prompt_pack

result = await run_prompt_pack(
    prompt_pack,
    limits=AgentRuntimeLimits(
        run_timeout_seconds=30,
        provider_timeout_seconds=20,
        token_budget=2_000,
    ),
)

These limits reset with the process. There is no AI_AGENT_RUNTIME dictionary, stable AgentRuntime class, or durable provider budget in v0.7.0.

MCP is separate

MCP tool execution is a stable boundary retained in v0.7 and does not require a model provider. Enable its Streamable HTTP server separately:

AKSARA_MCP_ENABLED=true
AKSARA_MCP_TOKEN_AUDIENCE=my-app

MCP clients connect to /mcp/. The /ai/tools/mcp route is an HTTP JSON inspection catalog. Follow the MCP quickstart to add server-side Principal resolution before enabling tool execution.