mirror of
https://github.com/profullstack/logicsrc.git
synced 2026-08-13 14:37:26 +00:00
Anthony Ettinger
3ab8a4b38b
* 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>
2.1 KiB
2.1 KiB
Multi-agent company
One shared context repository. Five agents. Five different bundles.
opencontext validate --strict
opencontext doctor
for agent in sales-agent support-agent dev-agent finance-agent ops-agent; do
echo "== $agent"
opencontext resolve --agent "$agent" --explain
done
What each agent gets
| Agent | Sees | Never sees |
|---|---|---|
sales-agent |
products, customers, pricing, quoting SOP | churn risk, payroll, architecture |
support-agent |
products, customers, refunds, refund SOP | pricing, payroll, architecture |
dev-agent |
architecture, change management, decisions | customers, pricing, payroll |
finance-agent |
every policy including payroll, customers | architecture, runbooks, card numbers |
ops-agent |
procedures, runbooks, change management | customers, pricing, payroll |
Three mechanisms doing the work
Scope. Each role includes only what it needs. sales additionally excludes
customers.*.churn-risk, so an inferred model score cannot leak into a customer
conversation even though customers.* matches it.
Classification. policies.payroll is confidential. Only finance
declares max_classification: confidential; every other role falls back to
internal and is refused. A role's own declaration wins over the one it
inherits, so a ceiling on a shared base role cannot silently cap a role that was
deliberately granted more — while requesting several roles at once still takes
the lowest of them, so combining roles never escalates.
Redaction. The manifest redacts payment.card repository-wide, so no role —
including finance — ever receives a card number, even from a record it is
fully entitled to read.
Object permissions. policies.payroll also carries
permissions.read: [finance], so it is refused even to a role whose include
pattern matches it. Deny overrides allow, at every level.
The point
Replace support-agent with a different model tomorrow. Run the same command.
The bundle is identical, and its digest proves it. The agent was replaceable;
the context was not.