agentfootprint
Version:
The explainable agent framework — backtrack a wrong answer to the exact context that caused it (evidence, not guesses). Built on footprintjs.
481 lines • 27.5 kB
JavaScript
;
/**
* runbookAsTool — turn a written operational procedure into a tool whose
* every answer is EVIDENCE: who decided what, against which threshold, on
* which rule version, with the recorded walk to check it against.
*
* The standard bridge from a footprintjs chart to the Agent's tool surface.
* Where `flowchartAsTool` returns bare `JSON.stringify(values)`,
* runbookAsTool supplies the missing middle — the honesty envelope every
* hand-rolled triage tool was building for itself:
*
* THE MANDATORY SPINE (every runbook, whatever its shape):
* - `af_coverage` — the three-list ledger, with every INNER tool's own
* ledger folded upward through the run's dispatch, plus the sentence
* naming the rule set and version;
* - `result.af_provenance` — re-emitted FIRST (a carried `LOCAL SEED`
* confession survives composition);
* - `result.rule_version` — the declared rules' version, or the honest
* `'undeclared'`;
* - `result.walk` — the recorded walk's descriptor. The walk itself
* ships as an artifact ticket (kind `recording/chart-walk`), never as
* bytes; when it does not fit, the CONTROL FLOW survives and the
* projection is declared. Opt into `walk: { recording: true }` and the
* inner chart's own `{ snapshot, events, structure }` is filed beside
* it (kind `recording/run`) and its ref rides the SAME descriptor as
* `walk.recording_ref` — the row projection cannot be drawn, and this
* is what makes the walk mountable as the flowchart it ran.
*
* THE OPTIONAL PROJECTION (selected by `resultKind: 'verdict/*'`):
* verdict rows off the chart's `verdicts` state key, capped with
* truthful counters, a pre-rendered table over the SAME rows, and
* `verdict_meanings` GENERATED from the decider's declared branches +
* the rule labels this run's decide() evidence carried.
*
* WHO RENDERS THE ROWSET (`presentation`, default `'prose'`): the bridge
* cannot see which client it is in, so the caller says. Under `'prose'`
* the model's words are the rowset's only surface — the table ships
* pre-rendered and is output verbatim. Under `'panel'` the host draws
* the rowset itself — no table ships, and the note says not to
* reproduce rows the reader is already looking at.
*
* THREE OUTCOMES, honestly: a clean envelope; an inner ABSENCE passed
* through verbatim (the framework still reads it as an absence); and
* DECLINED rows counted into the ledger as not-checked ground.
*
* The procedure is a FACTORY invoked per call with the run's own tool
* dispatch (`ctx.tools`) — fresh chart every run, stages close over the
* dispatch, and every inner tool's honesty ledger folds into this tool's
* answer.
*
* Reserved state keys the bridge reads off the final scope:
* - `verdicts` — the rowset (verdict projection only);
* - `coverage` — chart-declared coverage entries (`{checked?, not_checked?,
* cannot_cover?}`);
* - `report` — the app's own result fields, spread into `result` verbatim
* BESIDE the spine, never over it: the envelope's own names (the spine
* plus the projection this run assembled) are reserved, and a report
* field spelling one of them is discarded and NAMED in `report_note`.
*
* Pause: NOT yet bridged. A paused inner chart throws with the checkpoint
* attached, exactly like `flowchartAsTool` — the approval-gate integration
* is the next phase of the runbook program.
*
* @example the smallest legal call — still yields the honest spine
* const tool = runbookAsTool({
* name: 'restart_check',
* description: 'Run the restart-safety procedure.',
* procedure: () =>
* flowChart<{ safe: boolean }>('restart-safety', (scope) => {
* scope.safe = true;
* }, 'check').build(),
* });
*
* @example a triage runbook with rules, verdicts, and an inner tool
* const triage = runbookAsTool({
* name: 'backup_triage',
* description: 'Assess backup protection posture for every subject.',
* resultKind: 'verdict/backup-posture',
* rules: { name: 'health-signal', version: 'v1' },
* verdicts: { decider: 'posture' },
* composedOf: ['backup_inventory'],
* procedure: (tools) =>
* flowChart<TriageState>('backup-triage', async (scope) => {
* const inner = (await tools.call('backup_inventory', {})) as InventoryResult;
* scope.subjects = inner.result.rows;
* }, 'inventory')
* .addDeciderFunction('Posture', postureDecider, 'posture')
* .addFunctionBranch('protected', 'Protected', landProtected)
* .addFunctionBranch('unprotected', 'Unprotected', landUnprotected)
* .end()
* .build(),
* });
*/
Object.defineProperty(exports, "__esModule", { value: true });
exports.runbookAsTool = void 0;
const footprintjs_1 = require("footprintjs");
const trace_1 = require("footprintjs/trace");
const innerRunRecords_js_1 = require("../innerRunRecords.js");
const policy_js_1 = require("../../redaction/policy.js");
const marker_js_1 = require("../../redaction/marker.js");
const servableSnapshot_js_1 = require("../servableSnapshot.js");
const toolShownArgs_js_1 = require("../toolShownArgs.js");
const tools_js_1 = require("../../tools/tools.js");
const coverage_js_1 = require("./coverage.js");
const dispatch_js_1 = require("./dispatch.js");
const recording_js_1 = require("./recording.js");
const report_js_1 = require("./report.js");
const verdicts_js_1 = require("./verdicts.js");
const walk_js_1 = require("./walk.js");
/** The projection selector: a `resultKind` in the `verdict/` namespace gets
* the rowset projection; every other kind ships the spine plus the chart's
* own `report`. */
const VERDICT_KIND_PREFIX = 'verdict/';
/** The presentations, as the dial spells them. */
const PRESENTATIONS = ['prose', 'panel'];
/**
* The projection's RESERVED VOCABULARY: the keys this run assembled, plus
* `table` — which `presentation: 'panel'` deliberately omits so that no table
* reaches the model at all. A `report` field spelling the freed name would put
* one straight back, so the mode's promise outranks the vacancy.
*/
function reservedProjectionNames(projection) {
return projection === undefined ? [] : [...Object.keys(projection), 'table'];
}
function bagOf(value) {
return value !== null && typeof value === 'object' && !Array.isArray(value)
? value
: undefined;
}
/** Lift the chart's declared input schema when it is a PLAIN JSON-Schema
* object. A parseable schema (`.safeParse`/`.parse` — zod et al.) validates
* at the executor but cannot be serialized for the model: skipped, default
* applies. */
function liftInputSchema(chart) {
const schema = bagOf(chart.inputSchema);
if (schema === undefined)
return undefined;
const parseable = typeof schema.safeParse === 'function' ||
typeof schema.parse === 'function';
return parseable ? undefined : schema;
}
/**
* Wrap a footprintjs procedure as a `Tool` whose every answer carries the
* honesty spine. See the module header for the envelope; see
* {@link RunbookAsToolOptions} for the full options bag. The smallest legal
* call is `{ name, description, procedure }`.
*/
function runbookAsTool(opts) {
const label = `runbookAsTool(${opts.name || '?'})`;
if (!opts.name || opts.name.trim().length === 0) {
throw new Error('runbookAsTool: `name` is required and must be non-empty.');
}
if (!opts.description || opts.description.length === 0) {
throw new Error(`${label}: \`description\` is required — a description-less tool is invisible to the model.`);
}
if (typeof opts.procedure !== 'function') {
throw new Error(`${label}: \`procedure\` is required — a factory invoked per call with the run's ` +
`tool dispatch, returning a built chart. (Migrating from flowchartAsTool? Wrap ` +
`your chart: \`procedure: () => chart\` builds it fresh each run.)`);
}
if (opts.rules !== undefined) {
const { name, version } = opts.rules;
if (typeof name !== 'string' ||
name.trim() === '' ||
typeof version !== 'string' ||
version.trim() === '') {
throw new Error(`${label}: \`rules\` must carry a non-empty name and version — it is the provenance ` +
`stamp every evidence sentence names. Got ${JSON.stringify(opts.rules)}.`);
}
}
if (opts.verdicts !== undefined) {
if (typeof opts.verdicts.decider !== 'string' || opts.verdicts.decider.trim() === '') {
throw new Error(`${label}: \`verdicts.decider\` must name the decider stage whose branches generate ` +
`verdict_meanings. Got ${JSON.stringify(opts.verdicts.decider)}.`);
}
const maxRows = opts.verdicts.maxRows;
if (maxRows !== undefined && (!Number.isInteger(maxRows) || maxRows < 1)) {
throw new Error(`${label}: \`verdicts.maxRows\` must be a whole number of rows, at least 1 — got ` +
`${String(maxRows)}.`);
}
}
if (opts.presentation !== undefined && !PRESENTATIONS.includes(opts.presentation)) {
throw new Error(`${label}: \`presentation\` names WHO renders the rowset — 'prose' (the default: the ` +
`model's prose is the rowset's only surface, so the pre-rendered table ships and is ` +
`output verbatim) or 'panel' (the host draws the rowset, so no table ships). Got ` +
`${JSON.stringify(opts.presentation)}.`);
}
const cap = opts.walk?.cap;
if (cap !== undefined && (!Number.isInteger(cap) || cap < 1)) {
throw new Error(`${label}: \`walk.cap\` must be a whole number of rows, at least 1 — got ${String(cap)}.`);
}
const recordingOpt = opts.walk?.recording;
if (recordingOpt !== undefined &&
typeof recordingOpt !== 'boolean' &&
(recordingOpt === null || typeof recordingOpt !== 'object' || Array.isArray(recordingOpt))) {
throw new Error(`${label}: \`walk.recording\` must be \`true\` (file the inner chart's recording with ` +
`the defaults), \`false\`/absent (do not file one), or an options bag ` +
`\`{ label?, maxBytes? }\` — got ${JSON.stringify(recordingOpt)}.`);
}
if (typeof recordingOpt === 'object' && recordingOpt !== null) {
const maxBytes = recordingOpt.maxBytes;
if (maxBytes !== undefined && (!Number.isInteger(maxBytes) || maxBytes < 1)) {
throw new Error(`${label}: \`walk.recording.maxBytes\` must be a whole number of bytes, at least 1 — ` +
`got ${String(maxBytes)}. It is the declared ceiling a recording is REFUSED over, ` +
`never truncated to.`);
}
}
if (opts.keepRecordLimit !== undefined) {
if (opts.keepRecord !== true) {
throw new Error(`${label}: \`keepRecordLimit\` caps records that are never kept — add ` +
`\`keepRecord: true\`, or drop the limit.`);
}
if (!Number.isInteger(opts.keepRecordLimit) || opts.keepRecordLimit < 1) {
throw new Error(`${label}: \`keepRecordLimit\` must be a whole number of invocations, at least 1 — ` +
`got ${String(opts.keepRecordLimit)}.`);
}
}
// ── Definition-time probe: read the chart's declared contract ─────────
let probeChart;
try {
probeChart = opts.procedure((0, dispatch_js_1.probeDispatch)(opts.name));
}
catch (err) {
throw new Error(`${label}: the procedure factory threw at the definition probe — ` +
`${err instanceof Error ? err.message : String(err)}. The factory is invoked once ` +
`at definition (stage bodies do not run) to read the chart's declared contract; ` +
`it must be side-effect-free at build.`);
}
if (probeChart === null ||
typeof probeChart !== 'object' ||
typeof probeChart.stageMap !== 'object') {
throw new Error(`${label}: \`procedure\` must return a BUILT chart (call .build() on the builder).`);
}
const inputSchema = opts.inputSchema ?? liftInputSchema(probeChart);
const isVerdictKind = opts.resultKind?.startsWith(VERDICT_KIND_PREFIX) === true;
const rendersItsOwnRows = opts.presentation === 'panel';
const maxRows = opts.verdicts?.maxRows ?? verdicts_js_1.DEFAULT_MAX_ROWS;
const walkCap = opts.walk?.cap ?? walk_js_1.DEFAULT_WALK_CAP;
// Resolved ONCE at definition. `undefined` is the whole off-switch: every
// line the recording feature adds sits behind this being defined, so an
// undeclared runbook takes no second snapshot, measures no bytes, and makes
// no store call — its envelope is byte-identical to 9.78.0.
const recordingPolicy = (0, recording_js_1.resolveRecordingPolicy)(recordingOpt);
const store = opts.keepRecord === true
? (0, innerRunRecords_js_1.innerRunStore)(opts.keepRecordLimit ?? innerRunRecords_js_1.DEFAULT_INNER_RUN_LIMIT)
: undefined;
const tool = (0, tools_js_1.defineTool)({
name: opts.name,
description: opts.description,
...(inputSchema !== undefined && { inputSchema }),
// GAP-8 closed: the rail-read declarations forward verbatim.
...(opts.resultKind !== undefined && { resultKind: opts.resultKind }),
...(opts.resultClass !== undefined && { resultClass: opts.resultClass }),
...(opts.owner !== undefined && { owner: opts.owner }),
...(opts.resultCeiling !== undefined && { resultCeiling: opts.resultCeiling }),
...(opts.wants !== undefined && { wants: opts.wants }),
...(opts.argumentsFrom !== undefined && { argumentsFrom: opts.argumentsFrom }),
...(opts.composedOf !== undefined && { composedOf: opts.composedOf }),
execute: async (args, ctx) => {
const dispatch = (0, dispatch_js_1.recordingDispatch)(ctx.tools, opts.name);
const chart = opts.procedure(dispatch.tools);
// This tool's own policy joined with the one the calling run is covered
// by (`ctx.redact`) — the procedure runs NESTED in the agent's run, and a
// run's policy covers the runs nested in it: one union for the run, the
// walk, the recording and the kept record. The envelope the MODEL reads
// is the tool's own business (`modelFacingState`, below).
const policy = (0, policy_js_1.unionRedactionPolicies)(opts.redact, ctx.redact);
const watch = policy !== opts.redact ? (0, servableSnapshot_js_1.watchRunRule)(chart) : undefined;
const executor = new footprintjs_1.FlowChartExecutor(chart, watch !== undefined ? { scopeFactory: watch.scopeFactory } : undefined);
if (policy) {
executor.setRedactionPolicy(policy);
// The kept record says it was served under a policy, so its readers
// read a placeholder as a value kept out (`redaction/marker.ts`).
executor.attachCombinedRecorder((0, marker_js_1.redactionMarker)());
}
for (const recorder of opts.recorders ?? []) {
executor.attachCombinedRecorder(recorder);
}
// Values off: the walk is about the DECISIONS — a per-key value dump
// would bury six branch choices under four hundred reads.
const walkRecorder = (0, footprintjs_1.narrative)({ includeValues: false });
executor.attachCombinedRecorder(walkRecorder);
// Meanings harvest — resolve the decider on THIS run's chart (a fresh
// chart per call; the static branches are the same, the resolution is
// cheap) and collect rule labels as the evidence fires.
const identity = opts.verdicts !== undefined ? (0, verdicts_js_1.resolveDecider)(chart, opts.verdicts.decider) : undefined;
const harvest = identity !== undefined ? (0, verdicts_js_1.meaningsRecorder)(identity) : undefined;
if (harvest !== undefined)
executor.attachCombinedRecorder(harvest.recorder);
const ctrl = store ? (0, trace_1.controlDepRecorder)() : undefined;
if (ctrl)
executor.attachCombinedRecorder(ctrl);
const keepRecordOf = (outcome, known) => {
if (!store)
return;
try {
const snapshot = known ?? (0, servableSnapshot_js_1.servableSnapshot)(executor, policy);
const commitLog = snapshot.commitLog;
const lines = walkRecorder.getEntries()
.map((entry) => entry.text)
.filter((text) => typeof text === 'string' && text.length > 0);
store.keep({
toolCallId: ctx.toolCallId,
...(ctx.runId !== undefined && { runId: ctx.runId }),
toolName: opts.name,
outcome,
steps: Array.isArray(commitLog) ? commitLog.length : 0,
recording: {
snapshot,
structure: chart.buildTimeStructure,
},
...(ctrl !== undefined && { controlDeps: ctrl.asLookup() }),
...(lines.length > 0 && { narrative: lines }),
});
}
catch (e) {
store.keep({
toolCallId: ctx.toolCallId,
...(ctx.runId !== undefined && { runId: ctx.runId }),
toolName: opts.name,
outcome,
steps: 0,
problem: e instanceof Error ? e.message : String(e),
});
}
};
const env = {};
if (ctx.signal)
env.signal = ctx.signal;
try {
await executor.run({ input: args, env });
}
catch (e) {
const signal = (0, dispatch_js_1.absenceSignalOf)(e);
if (signal !== undefined) {
// ABSENCE PASS-THROUGH: the inner source answered "I looked and
// there is nothing", and the runbook has nothing to add. It goes
// back EXACTLY as it arrived so the framework still reads it as an
// absence. The kept record files as 'error' — the closed outcome
// word nearest "the traversal ended on a thrown signal".
keepRecordOf('error');
return signal.absence;
}
keepRecordOf('error');
throw e;
}
if (executor.isPaused()) {
keepRecordOf('paused');
const err = new Error(`${label}: the inner chart paused. Approval-gate integration (typed resume ` +
`through agent.resume) is the runbook program's next phase; until it lands a ` +
`paused procedure cannot be resumed through the tool boundary. The checkpoint ` +
`is on err.checkpoint.`);
err.checkpoint = executor.getCheckpoint();
throw err;
}
// The RECORD view, for the kept record and the recording: the redacted
// mirror exactly as footprintjs serves it when a policy is set, the raw
// snapshot otherwise — see `servableSnapshot`.
const served = (0, servableSnapshot_js_1.servableSnapshot)(executor, policy);
keepRecordOf('ok', served);
// The envelope's state — rows, coverage, report: what the MODEL reads —
// under the tool's own `redact` only; with no caller policy joined, the
// served view's state, as always (`servableSnapshot.ts` ·
// `modelFacingState`).
const state = (0, servableSnapshot_js_1.modelFacingState)(executor, opts.redact, watch !== undefined ? ctx.redact : undefined, watch?.rule());
// ── The walk ────────────────────────────────────────────────────────
const entries = walkRecorder.getEntries();
const projected = (0, walk_js_1.projectWalk)(entries, walkCap);
const walkOnly = await (0, walk_js_1.mintWalk)(ctx, projected, {
toolName: opts.name,
toolCallId: ctx.toolCallId,
...(ctx.runId !== undefined && { runId: ctx.runId }),
stepsExecuted: walkRecorder.stepCount,
});
// ── The recording, beside the walk (opt-in) ─────────────────────────
// The row projection cannot be drawn — `structure` is the only route to
// a drawable graph and no snapshot carries it. The snapshot here is the
// SAME served view the kept record and the envelope's state came from:
// the redacted mirror under a policy (the walk and the recording are
// scrubbed by one rule, at one moment), the raw snapshot without one.
const walk = recordingPolicy === undefined
? walkOnly
: {
...walkOnly,
...(await (0, recording_js_1.mintChartRecording)(ctx, (0, recording_js_1.chartRecordingOf)(served, chart.buildTimeStructure), {
toolName: opts.name,
toolCallId: ctx.toolCallId,
...(ctx.runId !== undefined && { runId: ctx.runId }),
policy: recordingPolicy,
})),
};
// ── The projection (verdict kinds only) ─────────────────────────────
let rows;
let shown;
let declined;
if (isVerdictKind) {
rows = (0, verdicts_js_1.verdictRowsOf)(state);
shown = rows.slice(0, maxRows);
declined = rows.filter((row) => row.verdict === verdicts_js_1.DECLINED_VERDICT).length;
}
const meanings = identity !== undefined && harvest !== undefined
? (0, verdicts_js_1.composeMeanings)(identity, harvest.observed)
: undefined;
// ── The ledger ──────────────────────────────────────────────────────
// The procedure's display name: the chart's own root name (what the
// author called it) — the tool name is the fallback, never the
// auto-generated multi-line description.
const chartName = chart.buildTimeStructure?.name ?? opts.name;
const ledger = (0, coverage_js_1.composeLedger)((0, coverage_js_1.foldInnerCoverage)(dispatch.records), (0, coverage_js_1.chartCoverageOf)(state), {
chartName,
stepsExecuted: walkRecorder.stepCount,
...(opts.rules !== undefined && { rules: opts.rules }),
...(rows !== undefined && { rowsTotal: rows.length }),
...(declined !== undefined && { declinedRows: declined }),
});
// ── Provenance — re-emitted FIRST ───────────────────────────────────
const af_provenance = {
...(0, coverage_js_1.carriedProvenanceOf)(dispatch.records),
tool: opts.name,
toolCallId: ctx.toolCallId,
};
// ── The envelope ────────────────────────────────────────────────────
// The spine and the projection are assembled FIRST, and the chart's
// `report` is admitted against the names they took: spine keys win, as
// the contract says, by explicit precedence rather than by spread order
// (which had the report land on top of `af_provenance` and
// `rule_version`). A refused field is named in `report_note` — see
// report.ts for the law and why the refusal is spoken.
const spine = {
af_provenance,
rule_version: opts.rules?.version ?? 'undeclared',
walk,
};
// The rowset half is the same in both presentations — the dial names who
// RENDERS the rows, never which rows there are. Only the surface differs:
// prose gets the pre-rendered table plus "output it verbatim"; a panel
// host gets no table and the opposite law, because the rows it would
// retype are already on the reader's screen.
const projection = shown !== undefined && rows !== undefined
? {
verdicts: shown,
rows_shown: shown.length,
rows_total: rows.length,
rows_complete: shown.length === rows.length,
...(rendersItsOwnRows
? { render_note: verdicts_js_1.PANEL_RENDER_NOTE }
: { table: (0, verdicts_js_1.renderVerdictTable)(shown), render_note: verdicts_js_1.VERDICT_RENDER_NOTE }),
...(meanings !== undefined && { verdict_meanings: meanings }),
}
: undefined;
const report = (0, report_js_1.admitReport)(bagOf(state.report) ?? {}, [
...Object.keys(spine),
...reservedProjectionNames(projection),
]);
const envelope = {
af_coverage: ledger,
result: {
af_provenance: spine.af_provenance,
rule_version: spine.rule_version,
...report.fields,
...(projection ?? {}),
...(report.refused.length > 0 && {
[report_js_1.REPORT_NOTE_KEY]: (0, report_js_1.shadowedFieldsNote)(report.refused),
}),
walk: spine.walk,
},
};
return envelope;
},
});
// The policy that scrubs the served result also governs the ARGUMENTS an
// event may show (`../toolShownArgs.ts` · `argsRedactedBy`) — the
// `flowchartAsTool` rule, one rule for both halves of the call.
const shown = opts.redact !== undefined ? { [toolShownArgs_js_1.SHOWN_ARGS]: (0, toolShownArgs_js_1.argsRedactedBy)(opts.redact) } : {};
if (store === undefined)
return opts.redact === undefined ? tool : { ...tool, ...shown };
const keepsRecords = { ...tool, ...shown, [innerRunRecords_js_1.INNER_RUN_RECORDS]: store };
return keepsRecords;
}
exports.runbookAsTool = runbookAsTool;
//# sourceMappingURL=runbookAsTool.js.map