UNPKG

@sema-agent/core

Version:

Stateless, task-oriented AI agent core

173 lines (172 loc) • 12.6 kB
/** * The synthetic-call judge — "would this call be refused outright?", asked without a model call, without an * approver and without a hook. One judge, one set of layers, for every consumer that needs the answer for a file the * model did not itself ask to touch. It has TWO FACES over one body (the layer walk below is written once): * * READ — a `Read` of a file the model did not ask for (the changed-file notice; a user's attachment). An ordinary * `ask` — a person's own ask rule — is not a refusal: the person who would answer it is the one asking. * WRITE — a `Write` of a path the engine itself writes in the background (the memory consolidation run). Every `ask` * is an objection here: nobody is present to answer it, so a layer that would ask a person refuses the write. * * It never picks a direction. The read face answers in FOUR states: * * deny — some layer refuses it; * mandated_ask — no layer refuses it, and some layer would put the read to a person no rule may answer for * (the ask's own mandate reading, {@link ruleClearanceOf}: a real-approval demand, the deployment's * own question, an ancestor's, a hook's; or an organization rule's ask) — the person who must * answer is not necessarily the one asking; * no_objection — every layer it consulted answered and none objected; * unanswerable — no layer objected, and at least one could not answer (see the table below). * * The write face answers the same four, with `ask` in place of `mandated_ask`: any layer's ask, mandated or not. * * ONE PRECEDENCE on both faces: a deny anywhere wins over a held ask, and a held ask over an unanswerable layer; the walk * goes on past an ask (a later layer's deny is the stronger answer). The faces differ only in which asks are held. The * CONSUMER decides where `mandated_ask` and `unanswerable` go: a notice that merely tells the model a file changed reads * both as no objection (the worst case is a notice about a file it then cannot re-read); a face that would put a file's * contents in front of the model reads both as a refusal; a background write reads everything but `no_objection` as a * refusal. Every answer but `unanswerable` names the location the layers judged (`judged`, the canonical view of the * stamped target, when a stamp was taken), so a consumer that resolved the file itself can tell the judged file from the * one it opens. * * THE LAYERS (every one that can refuse a model's own call): the run's skill deny rows; the * deny-narrowing fold (session rules, inherited ancestor rules, frozen constraint projections); the * deployment's caller policy; each live inherited parent policy; the person's persisted-rule lane; the org * lane. Not consulted, by design: PreToolUse hooks (the deployment's screening of a model's CALL), the permission mode's write * gate, the integrity guards and the write-protection table (a live `Write` meets them; the read face never needs them and the * write face's background run is not asked), and the read-deny table and containment roots (the path's own resolution judges those first). * * FAULT → STATE (the live gate's own readings, through the same functions — never a second copy): * | layer | fault | state | * | skill rows | throws | unanswerable `threw` | * | narrowing fold | throws / exceeds the judgment's budget | unanswerable `threw`/`timed_out` | * | caller / inherited policy | throws / times out | unanswerable `threw`/`timed_out` | * | caller / inherited policy | its deny carries an engine settlement (an approval | unanswerable `approval_seat` | * | | seat that ended unanswered; in a combinePolicies | | * | | composition a rule deny anywhere is returned instead)| | * | persisted lane | a store partition (or all of it) is unreadable, the lane throws, times out (readPersistedRuleLane ⇒ `{unreadable}`) | unanswerable `store_unreadable` (both faces: a row nobody could read may forbid the call) | * | persisted lane | the call cannot be read against the rows (`reason`) — applyPersistedTightening ⇒ `unreadable` | unanswerable `call_unreadable` | * | org lane | unavailable: throws, garbage (readOrgRuleLane) | unanswerable `org_unavailable` | * | any policy layer | answers with a rewrite of the arguments (`updatedInput`) | unanswerable `rewritten` | * | inherited parent policy | answers `ask` (the ancestor's approver's question) | mandated_ask (write: ask) | * | any layer | the judgment's budget (one dependency timeout, or a | unanswerable `timed_out` | * | | batch's shared deadline) is spent | | * * NEVER AN APPROVER. Every probe STATES that nobody can be asked about it — `approvalReach: "none"` on the request * (`ToolCallRequest.approvalReach`) — and every policy layer is handed a LIVE signal of its own: it ends when the judge stops * waiting for that layer (the layer answered, or its share of the judgment's budget is spent) or when the run's signal ends. * An abort means only that: the task ended, or the judge no longer waits — never "there is no approver". Every engine * policy factory reads the statement before reaching a seat (the approval factory answers a deny attested `no_approver`, * read here as `approval_seat`; the inherited PreToolUse constraint does the same before invoking its hook), and the * engine's own guards composed into a deployment's policy judge the probe as they judge a call — a lookup bounded by a * live deadline answers. A deny that carries no engine settlement is a rule's deny and stands. RESIDUALS (stated, not * closed): a deployment closure that ignores the statement and reaches an approver IS asked — the judge waits for it at * most the judgment's budget (`timed_out`: the write face refuses, the notice face stays silent), then its signal ends * so a closure that honors it releases its approval; a deployment wrapper that answers the statement with a deny of its * own (no settlement) is read as a deny — the attachment face then withholds, the notice face stays silent. * * THE PROBE'S IDENTITY. Every layer sees the probed tool's name (`Read` / `Write`), the probed arguments, the statement * above, and a stable synthetic call id (`<face>-visibility-probe` for a read, `<face>-write-probe` for a write; * {@link syntheticReadProbeId}, {@link syntheticWriteProbeId}), so a deployment's audit can tell a probe from a model's call. The write face stamps the * facts the live gate stamps on a write (the roster's `Write` face, the tracked cwd and root, the advertised writable * directories, the data root's exemption): a containment fence and a data-root exemption judge the probe as they judge the call. */ import type { ToolCallRequest, ToolCallFace, ToolPolicy } from "./tool-policy.js"; import { type CallTargetStamp } from "./effective-path-target.js"; import { type SkillGrantLane } from "./skill-grant.js"; import type { OrgGateVerdict, PersistedRuleAnswer } from "./hooks.js"; /** The layers the judge consults, as named in its verdicts. */ export declare const SYNTHETIC_READ_LAYERS: readonly ["skill_rows", "narrowing", "caller_policy", "inherited_constraint", "persisted_rules", "org_rules"]; export type SyntheticReadLayer = (typeof SYNTHETIC_READ_LAYERS)[number]; /** Why a layer could not answer — the consumer's disclosure word. */ export declare const SYNTHETIC_READ_UNANSWERABLE_CAUSES: readonly ["threw", "timed_out", "approval_seat", "call_unreadable", "org_unavailable", "rewritten", "store_unreadable"]; export type SyntheticReadUnanswerableCause = (typeof SYNTHETIC_READ_UNANSWERABLE_CAUSES)[number]; export type SyntheticReadVerdict = { verdict: "deny"; layer: SyntheticReadLayer; message?: string; judged?: string; } | { verdict: "mandated_ask"; layer: SyntheticReadLayer; message?: string; judged?: string; } | { verdict: "no_objection"; judged?: string; } | { verdict: "unanswerable"; layer: SyntheticReadLayer; cause: SyntheticReadUnanswerableCause; reason: string; }; /** The write face's answer: the read face's states with `ask` — any layer's ask, mandated or not — in place of `mandated_ask`. */ export type SyntheticWriteVerdict = Exclude<SyntheticReadVerdict, { verdict: "mandated_ask"; }> | { verdict: "ask"; layer: SyntheticReadLayer; message?: string; judged?: string; }; export interface SyntheticReadLayers { skillGrants?: Pick<SkillGrantLane, "denying">; denyNarrowingPolicy?: ToolPolicy; callerPolicy?: ToolPolicy; inheritedPolicies?: readonly ToolPolicy[]; persistedRuleLane?: { adjudicate: (req: ToolCallRequest) => PersistedRuleAnswer | Promise<PersistedRuleAnswer>; }; orgRuleLane?: { adjudicate: (req: ToolCallRequest) => Promise<OrgGateVerdict>; }; /** The leg's target-reading stamp: the probe's request carries a reading of its target, as the live gate's does. */ stampCallTarget?: CallTargetStamp; /** The run's signal: its end ends the judgment's every wait (each policy layer's own signal ends with it). */ signal?: AbortSignal; } /** The arguments a synthetic `Read` carries, and the facts a request stamps. */ export interface SyntheticReadCall { file_path: string; offset?: number; limit?: number; /** The tracked working directory a relative `file_path` resolves against. */ cwd?: string; /** The live roster's face for `Read`, when the consumer has one. */ face?: ToolCallFace; } /** The path a synthetic `Write` probes. The request's other facts come from the judge's {@link SyntheticWriteFacts}. */ export interface SyntheticWriteCall { file_path: string; } /** The facts the live gate stamps on a write, read at the moment of each judgment (the leg's cells move: the tracked cwd, * the advertised-directory ledger). Every member is optional — a leg without hands has no roster face, cwd or root. */ export interface SyntheticWriteFacts { /** The live roster's face for `Write` (a containment fence admits a write only by the tool's own declared path target). */ face?: ToolCallFace | undefined; cwd?: string | undefined; root?: string | undefined; advertisedWritableDirs?: { readonly roots: readonly string[]; } | undefined; exemptRoots?: readonly string[] | undefined; } /** The stable synthetic call id a probe carries: `<face>-visibility-probe`, `face` a lowercase word * (letters and hyphens) naming the consumer. */ export declare function syntheticReadProbeId(face: string): string; /** The write face's stable synthetic call id: `<face>-write-probe`, `face` the same lowercase word. */ export declare function syntheticWriteProbeId(face: string): string; /** One judgment's wait budget. `deadlineAt` (epoch ms) bounds the WHOLE judgment — every layer waits at most * what is left of it, and a layer reached after it has passed is not consulted (`timed_out`). Absent ⇒ the * dependency timeout from the start of this judgment. A consumer judging a batch passes one shared deadline, * so a hung layer costs the batch one bound, not one per file per layer. */ export interface SyntheticReadBudget { deadlineAt?: number; } export type SyntheticReadJudge = (call: SyntheticReadCall, face: string, budget?: SyntheticReadBudget) => Promise<SyntheticReadVerdict>; export type SyntheticWriteJudge = (call: SyntheticWriteCall, face: string, budget?: SyntheticReadBudget) => Promise<SyntheticWriteVerdict>; /** The READ face: only a mandated ask is held (a person's own ask is that person's question). */ export declare function createSyntheticReadJudge(layers: SyntheticReadLayers): SyntheticReadJudge; /** The WRITE face: every ask is held as an objection (no approver is present), and a persisted store that cannot be read is * unanswerable rather than silent. */ export declare function createSyntheticWriteJudge(layers: SyntheticReadLayers, facts: () => SyntheticWriteFacts): SyntheticWriteJudge;