AGPL-3.0-or-later · forever.

the standard library

nika:done

Mark the current agent loop complete (the loop-completion sentinel · agent loops only). One of 28 builtins in the closed nika: namespace.

the core familycontrol flow and run-stream primitives

  • corefamily6 tools
  • 1argsdeclared contract
  • 0requiredall optional
  • 1skeletonsship this tool

the contract

1 args · 0 required

A missing required arg is a nika check finding before anything runs; the vocabulary below comes from the binary itself (nika catalog --tools --json), not from prose.

result
optional final value (any JSON)

in a real file

from the agent-loop skeleton
agent-loop.nika.yaml
  execute:    with:      steps: ${{ tasks.plan.output.steps }}    agent:      # Say what the JOB is. Do NOT describe the output shape.      #      # The engine binds `schema:` to the FINAL answer: a free-text answer      # that does not conform is RE-ASKED with the schema wired, bounded by a      # retry budget. Measured on ollama/qwen3.5:4b — this task, with zero      # shape instruction, returns a clean typed object.      #      # Hand-instructing "reply with the object, then call nika:done" is      # actively harmful: a `nika:done` carrying `result:` is validated      # DIRECTLY and is NEVER re-asked (nika-verb-agent/src/lib.rs · "a miss      # is a verdict, never a re-ask"), so a model that hands its JSON back      # as a *string* dies NIKA-INFER-002 with the budget already spent.      # Measured twice on that exact instruction. Let the engine own shape.      system: "You are a careful analyst. Work the plan step by step and report what you actually found."   # SLOT      prompt: "Plan · ${{ with.steps }}"      tools:                        # SLOT: the MINIMUM grant for the job        # Pure compute — this pair needs no filesystem, so the skeleton runs        # anywhere. Granting the agent a tool here is only HALF a grant: every        # call still crosses the workflow boundary above. Adding `nika:read`        # to this list WITHOUT adding `permits.fs.read` fails at run with        # `NIKA-SEC-004 · agent tool "nika:read" refused by the security        # boundary` — measured, mid-loop, after the turns are paid for.        - "nika:jq"        - "nika:done"               # the early-exit sentinel · loop-owned      max_turns: 15                 # SLOT: the loop bound      max_tokens_total: 80000       # SLOT: the spend bound      schema:                       # SLOT: the typed final-message contract        type: object        additionalProperties: false        required: [findings]        properties:          findings: { type: array, items: { type: string } }

a verbatim excerpt, real line numbers from agent-loop.nika.yaml, conformance-gated upstream on every spec push. open the full skeleton →

the core family

6 tools

control flow and run-stream primitives.

Machines read the same vocabulary at /tools/catalog.json; the contract lives in spec 06 · stdlib. Install and ask the binary itself: nika catalog --tools. Read the spec →