logicsrc/docs/opencontext/sdk.md
Anthony Ettinger 3ab8a4b38b
Add the LogicSRC OpenContext specification (#132)
* Add the LogicSRC OpenContext specification

OpenContext is an open specification for durable, portable, permissioned,
provenance-aware context shared between humans and AI agents. It defines how
organizational knowledge is described, authorized, versioned, resolved,
audited, and handed between replaceable workers without losing institutional
state.

Follows the OpenPRD/OpenOntology pattern already in the repo: self-contained
JSON Schemas in @logicsrc/schemas, a reference implementation package, CLI
subcommands, docs, examples, and an OpenPRD record.

Schemas (8, all self-contained so a third party can fetch one file and
validate against it with no further resolution):
  manifest, object, bundle, role, provenance, decision, diagnostic,
  audit-event — registered in @logicsrc/validators and schemas:validate.

Reference implementation (@logicsrc/opencontext):
  loader with upward manifest discovery, the full resolution pipeline,
  authority/supersession, permissions, redaction, lifecycle, provenance,
  deterministic digests, doctor, search, graph, history/diff, guarded writes,
  audit events, and file/http/git/sqlite adapters.

CLI: all 15 specified commands, as a standalone `opencontext` binary and as
`logicsrc context`, sharing one implementation so the two cannot drift.

Design decisions worth noting:

- Supersession is declared, never inferred from version numbers. Inferring it
  would hide the governance failure it represents and make
  multiple-active-versions and duplicate-canonical impossible to detect.

- The bundle digest identifies the resolved context, not the moment it was
  computed, so generated_at/bundle_id/digest/as_of are excluded while objects,
  lifecycle states, exclusions and warnings are covered. That is what lets a
  decision record cite exactly the context that produced it.

- A role's own max_classification beats an inherited one, so a ceiling on a
  shared base role cannot silently cap a role deliberately granted more;
  requesting several roles at once still takes the lowest, so combining roles
  never escalates.

- Scope wildcards match whole dotted segments only. A trailing .* covers a
  subtree; an interior * matches exactly one segment. Substring matching here
  would be an access-control bug.

- --include narrows an existing scope and is applied after it, never merged
  into it, so a request can never widen what a role holds.

Verified: 226 tests across core primitives, permissions/redaction, the
resolution pipeline, security, the published conformance fixtures (13 valid,
35 invalid, 8 resolution scenarios), project behaviour, and the five shipped
examples — which are held to --strict and a 100% health score. Benchmarks meet
every published budget (resolve 1,000 objects in ~33ms against a 2s target).

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* Point install docs at @logicsrc/opencontext; record the npm name collision

The unscoped `opencontext` name is already published on npm by an unrelated
third party (federicodeponte/opencontext, 2.0.0), so `npx opencontext` would
install a stranger's package. Docs now use `npx @logicsrc/opencontext`; the bin
stays named `opencontext` so the command reads as the PRD specifies once
installed.

Recorded in PRD 0003 as a blocker to resolve before any publication, along with
the fact that no @logicsrc spec package has ever been published, so there is no
existing release path to slot into.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* Advance the logicsrc-mcp next-PRD-id assertion to 0004

standards.test.ts asserts prd_next_id against the live prd/ directory, so
adding PRD 0003 makes the next free id 0004. The test's own comment
anticipates this: "advances with every PRD added".

Caught by CI, not locally — the earlier verification ran per-package tests for
the packages this branch touches, and logicsrc-mcp is coupled to the PRD
directory without importing from it.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-09 11:46:11 -07:00

6.7 KiB

TypeScript SDK

npm install @logicsrc/opencontext

Node.js 22+, Bun, and compatible modern server runtimes. ESM.

import { OpenContext } from "@logicsrc/opencontext";

const oc = await OpenContext.load("./opencontext.yaml");

const result = await oc.resolve({
  agent: "support-agent",
  task: "Handle ACME refund"
});

console.log(result.bundle);

The resolver core is importable without the CLI, so an agent runtime can embed resolution without taking a dependency on argument parsing or terminal output. Every method the class wraps is also exported as a free function.

OpenContext.load

static load(pathOrDir?: string, options?: {
  offline?: boolean;      // skip adapters that reach the network
  loadContent?: boolean;  // resolve content_uri (default true)
  adapters?: Adapter[];   // additional adapters
}): Promise<OpenContext>

Accepts a manifest path or a directory. A directory searches upward, so load() with no argument works from anywhere inside a project.

resolve

oc.resolve({
  agent: "support-agent",
  role: ["support"],
  task: "Handle ACME refund",
  at: "2026-08-09T15:00:00Z",
  includeHistorical: false,
  explain: true,
  limit: 20,
  minRelevance: 2,
  include: ["policies.*"],
  requested: ["policies.refunds"]
}): { bundle, excluded, scopeSummary }

bundle() returns just the bundle when the exclusion detail is not needed.

const bundle = oc.bundle({ agent: "support-agent", task: "refund" });
bundle.digest;      // sha256:… deterministic for the same inputs and sources
bundle.objects;     // authorized, valid, redacted, ordered by layer
bundle.warnings;    // stale, conflicts, missing provenance, untrusted content
bundle.provenance;  // survives compilation

validate and doctor

const findings = oc.validate({ strict: true });   // Diagnostic[]
const report = oc.doctor({ at: "2026-12-01" });   // DiagnosticReport

import { hasFailure } from "@logicsrc/opencontext";
if (hasFailure(findings, "error")) process.exit(1);
oc.list({ scope, type: "policy", layer: "L3", includeSuperseded: false });
oc.get("policies.refunds");
oc.get("policies.refunds@2", { scope });
oc.search("refund policy", { scope, limit: 20 });

get returns null both when the object does not exist and when the scope may not read it — deliberately indistinguishable, so probing for ids reveals nothing. list and search apply the same filter before returning any metadata.

scope

const scope = oc.scope({ agent: "support-agent" });
const combined = oc.scope({ role: ["support", "finance"] });

scope.include;            // effective patterns
scope.maxClassification;  // effective ceiling
scope.permissions;        // capability strings
scope.principals;         // matched against object-level permissions

history, diff, graph

const history = await oc.history("pricing.enterprise");
const diffs = oc.diff("pricing.enterprise@1", "pricing.enterprise@2");
const graph = oc.graph({ roots: ["policies.refunds"], depth: 2, includeOwners: true });

Writes

oc.add({ id: "policies.returns", type: "policy", content: "Within 14 days." });

oc.supersede("policies.refunds", {
  scope,
  changes: { content: "Within 60 days." },
  allowPromotion: true
});

const oc2 = await oc.reload();

Writes validate authorization and schema before persisting, and throw WriteDeniedError otherwise. Promotion to canonical or approved requires allowPromotion: true. add refuses to overwrite; use supersede.

The store is a snapshot — call reload() after writing.

registerAdapter

import { OpenContext, type Adapter } from "@logicsrc/opencontext";

const crmAdapter: Adapter = {
  name: "crm",
  schemes: ["crm"],
  remote: true,
  async load(uri, ctx) {
    if (ctx.offline) throw new Error(`Cannot fetch ${uri} in offline mode.`);
    const record = await fetchFromCrm(uri);
    return {
      content: JSON.stringify(record),
      contentType: "application/json",
      trust: "untrusted"   // it is data from another system
    };
  }
};

const oc = await OpenContext.load("./opencontext.yaml", { adapters: [crmAdapter] });

See adapters.

Rendering

import { renderBundle, renderExplanation, renderHealth } from "@logicsrc/opencontext";

renderBundle(bundle, "json" | "yaml" | "markdown");
renderExplanation(bundle, excluded);
renderHealth(report, oc.store);

renderBundle(bundle, "markdown") is what you paste into a system prompt: it groups by layer, and fences and labels untrusted content. See security.

Errors

Error Meaning
ManifestNotFoundError No manifest here or in any parent
ManifestInvalidError Manifest failed schema or cross-field rules; carries diagnostics
UnknownConsumerError Agent or role not defined
UnknownSchemeError No adapter claims the URI scheme
PathTraversalError A source resolves outside the context root
OfflineError A remote fetch was attempted in offline mode
WriteDeniedError Authorization, schema, or promotion guard refused a write
ContextParseError A document failed to parse; carries file and line

Free functions

import {
  loadStore, resolve, validateStore, doctor, search, buildGraph, history, diffObjects,
  authorize, resolveScope, applyRedactions, computeLifecycle,
  resolveSupersession, detectConflicts, compareCandidates,
  digestBundle, canonicalJson, bundleIdFromDigest,
  initProject, AdapterRegistry
} from "@logicsrc/opencontext";

Useful when embedding one part of the pipeline — for example authorizing a set of candidates your own retriever produced, without adopting the loader.

Types

import type {
  Manifest, ContextObject, ContextBundle, BundledObject,
  EffectiveScope, RoleDefinition, Diagnostic, DiagnosticReport,
  Layer, Authority, Trust, Durability, Classification, LifecycleState,
  Adapter, AdapterResult, ResolveOptions
} from "@logicsrc/opencontext";

Worked example: an agent handoff

import { OpenContext, renderBundle } from "@logicsrc/opencontext";

const oc = await OpenContext.load("./opencontext.yaml");

const { bundle } = oc.resolve({
  role: "support",
  task: "continue ticket 4821",
  explain: true
});

const systemPrompt = renderBundle(bundle, "markdown");

// Record which context the decision was made from.
await recordDecision({
  id: `decisions.${today}-refund-4821`,
  type: "decision",
  title: "Refund ticket 4821",
  decision: "Credited against the next invoice.",
  bundle: { bundle_id: bundle.bundle_id, digest: bundle.digest }
});

Replace the model tomorrow and run the same code: the bundle is identical, and its digest proves it.