mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-17 10:22:34 +00:00
Compare commits
2
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
303bbfb0b8 | ||
|
|
9efe229eee |
-64
@@ -24,7 +24,6 @@ import type { GBrainConfig } from './core/config.ts';
|
||||
import type { AIGatewayConfig } from './core/ai/types.ts';
|
||||
import type { BrainEngine } from './core/engine.ts';
|
||||
import { operations, OperationError } from './core/operations.ts';
|
||||
import { resolveSourceIdEngineFree } from './core/source-resolver.ts';
|
||||
import { formatVolunteeredPage } from './core/context/volunteer.ts';
|
||||
import type { Operation, OperationContext } from './core/operations.ts';
|
||||
import { shouldForceExitAfterMain, finishCliTeardown, flushThenExit, currentExitCode, setCliExitVerdict } from './core/cli-force-exit.ts';
|
||||
@@ -383,15 +382,6 @@ async function main() {
|
||||
if (op.localOnly) {
|
||||
refuseThinClient(command, cfgPre!.remote_mcp!.mcp_url);
|
||||
}
|
||||
// #2098: the local path resolves --source / GBRAIN_SOURCE / .gbrain-source
|
||||
// inside makeContext (ctx.sourceId), which this route never reaches — so
|
||||
// scope must be mapped onto the op's source_id wire param before the call.
|
||||
try {
|
||||
applyThinClientSourceScope(op, params);
|
||||
} catch (e: unknown) {
|
||||
console.error(e instanceof Error ? e.message : String(e));
|
||||
process.exit(1);
|
||||
}
|
||||
await runThinClientRouted(op, params, cfgPre!, cliOpts);
|
||||
return;
|
||||
}
|
||||
@@ -812,60 +802,6 @@ export function parseOpArgs(op: Operation, args: string[]): Record<string, unkno
|
||||
return params;
|
||||
}
|
||||
|
||||
/**
|
||||
* #2098: thin-client source scoping. Locally, --source / GBRAIN_SOURCE /
|
||||
* .gbrain-source resolve to ctx.sourceId in makeContext; the thin-client
|
||||
* route short-circuits before that, so `gbrain query --source X` against a
|
||||
* remote brain silently searched unscoped. This runs the engine-free tiers
|
||||
* (flag → env → dotfile; the DB-backed tiers can't run without an engine —
|
||||
* the server's grant scoping covers the rest) and maps the result onto the
|
||||
* op's `source_id` wire param.
|
||||
*
|
||||
* Ops that declare their OWN `source` param (facts add, etc.) are left
|
||||
* untouched — their --source is an op param, not scope. An explicit --source
|
||||
* on an op with no source_id wire param throws (loud beats silent drop);
|
||||
* ambient env/dotfile scope with nowhere to send it is ignored, matching the
|
||||
* pre-fix behavior for non-scopeable ops. Exported for tests.
|
||||
*/
|
||||
// Ops whose `source_id` wire param is NOT read-scope semantics: get_skill's
|
||||
// source_id flips the lookup from host catalog to brain-resident-pack
|
||||
// (getResidentSkillDetail). Ambient env/dotfile scope must never leak into
|
||||
// these; an explicit --source-id still passes through untouched above.
|
||||
const NON_SCOPE_SOURCE_ID_OPS = new Set(['get_skill']);
|
||||
|
||||
export function applyThinClientSourceScope(
|
||||
op: Operation,
|
||||
params: Record<string, unknown>,
|
||||
cwd?: string,
|
||||
): void {
|
||||
if ('source' in op.params) return; // the op owns --source; not a scope flag
|
||||
const explicit = typeof params.source === 'string' && params.source.length > 0
|
||||
? (params.source as string)
|
||||
: null;
|
||||
delete params.source; // never a wire param on these ops — don't leak it
|
||||
// Explicit per-call scope already on the wire wins over ambient tiers.
|
||||
if (params.source_id !== undefined || params.all_sources === true) {
|
||||
if (explicit) {
|
||||
throw new Error('Pass either --source or --source-id/--all-sources, not both.');
|
||||
}
|
||||
return;
|
||||
}
|
||||
const resolved = resolveSourceIdEngineFree(explicit, cwd);
|
||||
if (!resolved) return;
|
||||
if (!('source_id' in op.params) || NON_SCOPE_SOURCE_ID_OPS.has(op.name)) {
|
||||
if (explicit) {
|
||||
const hint = NON_SCOPE_SOURCE_ID_OPS.has(op.name)
|
||||
? `(its source_id parameter is not a scope filter; pass --source-id explicitly if you mean it)`
|
||||
: `(the remote op has no source_id parameter; the server scopes it to your grant)`;
|
||||
throw new Error(
|
||||
`gbrain ${op.cliHints?.name || op.name} does not accept --source on a thin-client install ${hint}.`,
|
||||
);
|
||||
}
|
||||
return; // ambient env/dotfile scope with nowhere to send it
|
||||
}
|
||||
params.source_id = resolved;
|
||||
}
|
||||
|
||||
async function makeContext(engine: BrainEngine, params: Record<string, unknown>): Promise<OperationContext> {
|
||||
// v0.31.8 (D11): resolve sourceId via the canonical 6-tier chain. Honors
|
||||
// --source / GBRAIN_SOURCE / .gbrain-source / path-match / brain default /
|
||||
|
||||
+18
-1
@@ -509,8 +509,12 @@ export function extractTimelineFromContent(content: string, slug: string): Extra
|
||||
// DB-level uniqueness cannot collapse.
|
||||
const citationPattern = /\[Source:\s*([^\]]+?),\s*(\d{4}-\d{2}-\d{2})\s*\]/g;
|
||||
const bulletLinePattern = /^-\s+\*\*\d{4}-\d{2}-\d{2}\*\*\s*\|/;
|
||||
// Lines captured by Format 4 (plain bullet) are skipped for the same
|
||||
// reason: quality.md mandates a trailing [Source: ...] on those bullets,
|
||||
// and re-extracting the citation would double-count the event.
|
||||
const plainBulletLinePattern = /^-\s+\d{4}-\d{2}-\d{2}\s*[—–-]/;
|
||||
for (const line of content.split(/\r?\n/)) {
|
||||
if (bulletLinePattern.test(line)) continue;
|
||||
if (bulletLinePattern.test(line) || plainBulletLinePattern.test(line)) continue;
|
||||
const lineMatches = [...line.matchAll(citationPattern)];
|
||||
if (lineMatches.length === 0) continue;
|
||||
// Strip every citation marker from the line to leave the annotated text.
|
||||
@@ -526,6 +530,19 @@ export function extractTimelineFromContent(content: string, slug: string): Extra
|
||||
}
|
||||
}
|
||||
|
||||
// Format 4: Plain bullet — - YYYY-MM-DD — Summary
|
||||
// This is the format gbrain's own enrich skill writes (no bold, no source
|
||||
// pipe). Without it, every brain-authored timeline entry is invisible to
|
||||
// extraction and timeline_coverage stays at 0%. Anchored at line start so a
|
||||
// date inside a summary/link cannot start a spurious entry; a bold Format-1
|
||||
// line (`- **…**`) cannot match here (a `*` follows the bullet, not a
|
||||
// digit), and the citation loop above skips these lines, so a plain bullet
|
||||
// carrying its own [Source: ...] files exactly one entry.
|
||||
const plainBulletPattern = /^-\s+(\d{4}-\d{2}-\d{2})\s*[—–-]\s*(.+)$/gm;
|
||||
while ((match = plainBulletPattern.exec(content)) !== null) {
|
||||
entries.push({ slug, date: match[1], source: 'markdown', summary: match[2].trim() });
|
||||
}
|
||||
|
||||
return entries;
|
||||
}
|
||||
|
||||
|
||||
@@ -1103,6 +1103,11 @@ export interface TimelineCandidate {
|
||||
// Match: `- **YYYY-MM-DD** | summary` or `- **YYYY-MM-DD** -- summary`
|
||||
// or `- **YYYY-MM-DD** - summary` or just `**YYYY-MM-DD** | summary`.
|
||||
const TIMELINE_LINE_RE = /^\s*-?\s*\*\*(\d{4}-\d{2}-\d{2})\*\*\s*[|\-–—]+\s*(.+?)\s*$/;
|
||||
// Plain bullet: `- YYYY-MM-DD — summary` (no bold, no source pipe). Kept in
|
||||
// sync with extractTimelineFromContent's Format 4 (the fs-source path).
|
||||
// Anchored flush-left so a date inside an indented continuation line cannot
|
||||
// start a spurious entry.
|
||||
const PLAIN_TIMELINE_LINE_RE = /^-\s+(\d{4}-\d{2}-\d{2})\s*[—–-]\s*(.+?)\s*$/;
|
||||
|
||||
/**
|
||||
* Parse timeline entries from content. Looks at:
|
||||
@@ -1119,7 +1124,7 @@ export function parseTimelineEntries(content: string): TimelineCandidate[] {
|
||||
|
||||
let i = 0;
|
||||
while (i < lines.length) {
|
||||
const m = TIMELINE_LINE_RE.exec(lines[i]);
|
||||
const m = TIMELINE_LINE_RE.exec(lines[i]) ?? PLAIN_TIMELINE_LINE_RE.exec(lines[i]);
|
||||
if (!m) {
|
||||
i++;
|
||||
continue;
|
||||
@@ -1136,7 +1141,7 @@ export function parseTimelineEntries(content: string): TimelineCandidate[] {
|
||||
let j = i + 1;
|
||||
while (j < lines.length) {
|
||||
const next = lines[j];
|
||||
if (TIMELINE_LINE_RE.test(next)) break;
|
||||
if (TIMELINE_LINE_RE.test(next) || PLAIN_TIMELINE_LINE_RE.test(next)) break;
|
||||
if (/^#{1,6}\s/.test(next)) break;
|
||||
if (next.trim().length === 0 && detailLines.length === 0) {
|
||||
// skip leading blank line; if we hit a blank after detail content
|
||||
@@ -1166,7 +1171,7 @@ export function parseTimelineEntries(content: string): TimelineCandidate[] {
|
||||
// bullet pass are skipped (a bullet often carries its own citation).
|
||||
const citationRe = /\[Source:\s*([^\]]+?),\s*(\d{4}-\d{2}-\d{2})\s*\]/g;
|
||||
for (const line of lines) {
|
||||
if (TIMELINE_LINE_RE.test(line)) continue;
|
||||
if (TIMELINE_LINE_RE.test(line) || PLAIN_TIMELINE_LINE_RE.test(line)) continue;
|
||||
const matches = [...line.matchAll(citationRe)];
|
||||
if (matches.length === 0) continue;
|
||||
const summary = line
|
||||
|
||||
@@ -160,33 +160,6 @@ export async function resolveSourceId(
|
||||
return 'default';
|
||||
}
|
||||
|
||||
/**
|
||||
* Engine-free tiers (1-3) of the resolution chain: explicit flag →
|
||||
* GBRAIN_SOURCE env → .gbrain-source dotfile walk. Used by the thin-client
|
||||
* CLI path (#2098), which has no local engine to run tiers 4-6 or
|
||||
* assertSourceExists against — the remote server enforces existence + grant.
|
||||
* Returns null when no engine-free tier fires.
|
||||
*/
|
||||
export function resolveSourceIdEngineFree(
|
||||
explicit: string | null | undefined,
|
||||
cwd: string = process.cwd(),
|
||||
): string | null {
|
||||
if (explicit) {
|
||||
if (!SOURCE_ID_RE.test(explicit)) {
|
||||
throw new Error(`Invalid --source value "${explicit}". Must match [a-z0-9-]{1,32}.`);
|
||||
}
|
||||
return explicit;
|
||||
}
|
||||
const env = process.env.GBRAIN_SOURCE;
|
||||
if (env && env.length > 0) {
|
||||
if (!SOURCE_ID_RE.test(env)) {
|
||||
throw new Error(`Invalid GBRAIN_SOURCE value "${env}". Must match [a-z0-9-]{1,32}.`);
|
||||
}
|
||||
return env;
|
||||
}
|
||||
return readDotfileWalk(cwd);
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns the id of the SINGLE registered non-default source with a
|
||||
* local_path, when exactly one such row exists. Returns null when:
|
||||
|
||||
@@ -185,6 +185,49 @@ describe('extractTimelineFromContent', () => {
|
||||
expect(entries).toHaveLength(1);
|
||||
expect(entries[0].summary).toBe('Landed the enterprise pilot with acme-example.');
|
||||
});
|
||||
|
||||
// Format 4: the plain bullet `- YYYY-MM-DD — Summary` that gbrain's own
|
||||
// enrich skill writes. Before this was supported, every brain-authored
|
||||
// timeline entry was invisible and timeline_coverage was stuck at 0%.
|
||||
it('extracts plain bullet format (- YYYY-MM-DD — Summary)', () => {
|
||||
const content = `## Timeline\n- 2026-06-01 — Catch-up call with alice-example; intros offered.`;
|
||||
const entries = extractTimelineFromContent(content, 'people/alice-example');
|
||||
expect(entries).toHaveLength(1);
|
||||
expect(entries[0].date).toBe('2026-06-01');
|
||||
expect(entries[0].source).toBe('markdown');
|
||||
expect(entries[0].summary).toBe('Catch-up call with alice-example; intros offered.');
|
||||
});
|
||||
|
||||
it('files exactly one entry for a plain bullet that carries its own citation', () => {
|
||||
// quality.md mandates this shape; it must not double-count via the
|
||||
// citation arm (Format 3) AND the plain-bullet arm (Format 4).
|
||||
const content = `- 2026-05-31 — Confirmed full name. [Source: User, 2026-05-31]`;
|
||||
const entries = extractTimelineFromContent(content, 'people/charlie-example');
|
||||
expect(entries).toHaveLength(1);
|
||||
expect(entries[0].date).toBe('2026-05-31');
|
||||
expect(entries[0].source).toBe('markdown');
|
||||
expect(entries[0].summary).toContain('Confirmed full name.');
|
||||
});
|
||||
|
||||
it('does not double-count bold (Format 1) lines as plain bullets', () => {
|
||||
const content = `- **2025-03-18** | Meeting — Discussed partnership`;
|
||||
const entries = extractTimelineFromContent(content, 'test');
|
||||
expect(entries).toHaveLength(1);
|
||||
expect(entries[0].source).toBe('Meeting');
|
||||
});
|
||||
|
||||
it('does not start a spurious entry from a date inside a summary', () => {
|
||||
const content = `- 2026-06-01 — See [meeting](meetings/2026-06-01).`;
|
||||
const entries = extractTimelineFromContent(content, 'people/alice-example');
|
||||
expect(entries).toHaveLength(1);
|
||||
expect(entries[0].date).toBe('2026-06-01');
|
||||
});
|
||||
|
||||
it('handles en dash and hyphen separators in plain bullets', () => {
|
||||
const content = `- 2026-06-01 – First\n- 2026-06-02 - Second`;
|
||||
const entries = extractTimelineFromContent(content, 'test');
|
||||
expect(entries).toHaveLength(2);
|
||||
});
|
||||
});
|
||||
|
||||
describe('walkMarkdownFiles', () => {
|
||||
|
||||
@@ -720,6 +720,30 @@ More prose here.
|
||||
const entries = parseTimelineEntries(content);
|
||||
expect(entries.length).toBe(2);
|
||||
});
|
||||
|
||||
// Plain bullet (extract.ts Format 4 parity — the db-source path must see
|
||||
// the same entries as the fs-source path).
|
||||
test('parses plain bullet: - YYYY-MM-DD — summary', () => {
|
||||
const entries = parseTimelineEntries('## Timeline\n- 2026-06-01 — Catch-up call with alice-example');
|
||||
expect(entries.length).toBe(1);
|
||||
expect(entries[0].date).toBe('2026-06-01');
|
||||
expect(entries[0].summary).toBe('Catch-up call with alice-example');
|
||||
});
|
||||
|
||||
test('files exactly one entry for a plain bullet carrying its own citation', () => {
|
||||
const entries = parseTimelineEntries('- 2026-05-31 — Confirmed full name. [Source: User, 2026-05-31]');
|
||||
expect(entries.length).toBe(1);
|
||||
expect(entries[0].date).toBe('2026-05-31');
|
||||
});
|
||||
|
||||
test('skips invalid dates in plain bullets', () => {
|
||||
expect(parseTimelineEntries('- 2026-13-45 — Bad date').length).toBe(0);
|
||||
});
|
||||
|
||||
test('does not double-count a bold bullet as a plain bullet', () => {
|
||||
const entries = parseTimelineEntries('- **2026-01-15** | Met with Alice');
|
||||
expect(entries.length).toBe(1);
|
||||
});
|
||||
});
|
||||
|
||||
// ─── isAutoLinkEnabled ─────────────────────────────────────────
|
||||
|
||||
@@ -1,142 +0,0 @@
|
||||
/**
|
||||
* #2098: thin-client routing dropped --source / GBRAIN_SOURCE / .gbrain-source.
|
||||
*
|
||||
* The local CLI path resolves source scope in makeContext (ctx.sourceId); the
|
||||
* thin-client route short-circuits before that and sent params verbatim, so
|
||||
* `gbrain query --source X` against a remote brain silently searched unscoped
|
||||
* (the server op ignores the unknown `source` key).
|
||||
*
|
||||
* applyThinClientSourceScope runs the engine-free tiers (flag → env → dotfile)
|
||||
* and maps the result onto the op's `source_id` wire param. These tests fail
|
||||
* without the fix (params.source_id stays undefined / params.source leaks).
|
||||
*/
|
||||
|
||||
import { describe, test, expect } from 'bun:test';
|
||||
import { mkdtempSync, rmSync, writeFileSync } from 'fs';
|
||||
import { join } from 'path';
|
||||
import { tmpdir } from 'os';
|
||||
import { applyThinClientSourceScope, parseOpArgs } from '../src/cli.ts';
|
||||
import { operationsByName } from '../src/core/operations.ts';
|
||||
import { withEnv } from './helpers/with-env.ts';
|
||||
|
||||
const queryOp = operationsByName.query;
|
||||
|
||||
describe('applyThinClientSourceScope (#2098)', () => {
|
||||
test('--source maps onto the query op wire param source_id', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
|
||||
const params = parseOpArgs(queryOp, ['find things', '--source', 'wiki']);
|
||||
expect(params.source).toBe('wiki'); // pre-fix state: wrong key
|
||||
applyThinClientSourceScope(queryOp, params, '/');
|
||||
expect(params.source_id).toBe('wiki');
|
||||
expect('source' in params).toBe(false); // never leaks the unknown key
|
||||
});
|
||||
});
|
||||
|
||||
test('GBRAIN_SOURCE env tier fires when no flag is passed', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: 'gstack' }, () => {
|
||||
const params = parseOpArgs(queryOp, ['find things']);
|
||||
applyThinClientSourceScope(queryOp, params, '/');
|
||||
expect(params.source_id).toBe('gstack');
|
||||
});
|
||||
});
|
||||
|
||||
test('.gbrain-source dotfile tier fires when flag and env are absent', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
|
||||
const tmp = mkdtempSync(join(tmpdir(), 'gbrain-thin-scope-'));
|
||||
try {
|
||||
writeFileSync(join(tmp, '.gbrain-source'), 'essays\n');
|
||||
const params = parseOpArgs(queryOp, ['find things']);
|
||||
applyThinClientSourceScope(queryOp, params, tmp);
|
||||
expect(params.source_id).toBe('essays');
|
||||
} finally {
|
||||
rmSync(tmp, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
test('explicit --source-id on the wire wins over ambient env scope', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: 'gstack' }, () => {
|
||||
const params = parseOpArgs(queryOp, ['find things', '--source-id', 'wiki']);
|
||||
applyThinClientSourceScope(queryOp, params, '/');
|
||||
expect(params.source_id).toBe('wiki');
|
||||
});
|
||||
});
|
||||
|
||||
test('--source together with --source-id is rejected loudly', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
|
||||
const params = parseOpArgs(queryOp, ['q', '--source', 'a', '--source-id', 'b']);
|
||||
expect(() => applyThinClientSourceScope(queryOp, params, '/')).toThrow(/not both/);
|
||||
});
|
||||
});
|
||||
|
||||
test('invalid --source value is rejected loudly', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
|
||||
const params = parseOpArgs(queryOp, ['q', '--source', 'Bad_Value!']);
|
||||
expect(() => applyThinClientSourceScope(queryOp, params, '/')).toThrow(/Invalid --source/);
|
||||
});
|
||||
});
|
||||
|
||||
test('--source on an op with no source_id wire param errors instead of silently dropping', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
|
||||
const op = operationsByName.add_tag;
|
||||
expect('source_id' in op.params).toBe(false);
|
||||
const params = { slug: 'x', tag: 'y', source: 'wiki' };
|
||||
expect(() => applyThinClientSourceScope(op, params, '/')).toThrow(/--source/);
|
||||
});
|
||||
});
|
||||
|
||||
test('ambient env scope on an op with no source_id wire param is ignored (no throw)', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: 'wiki' }, () => {
|
||||
const op = operationsByName.add_tag;
|
||||
const params: Record<string, unknown> = { slug: 'x', tag: 'y' };
|
||||
applyThinClientSourceScope(op, params, '/');
|
||||
expect(params.source_id).toBeUndefined();
|
||||
});
|
||||
});
|
||||
|
||||
test('ops that declare their OWN source param are left untouched', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
|
||||
const op = operationsByName.put_raw_data;
|
||||
expect('source' in op.params).toBe(true);
|
||||
const params: Record<string, unknown> = { slug: 'x', source: 'crustdata', data: {} };
|
||||
applyThinClientSourceScope(op, params, '/');
|
||||
expect(params.source).toBe('crustdata');
|
||||
expect(params.source_id).toBeUndefined();
|
||||
});
|
||||
});
|
||||
|
||||
test('get_skill: ambient scope never leaks into its non-scope source_id param', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: 'wiki' }, () => {
|
||||
const op = operationsByName.get_skill;
|
||||
expect('source_id' in op.params).toBe(true); // has the param, but it is a mode switch
|
||||
const params: Record<string, unknown> = { name: 'ingest' };
|
||||
applyThinClientSourceScope(op, params, '/');
|
||||
expect(params.source_id).toBeUndefined(); // would flip host catalog → brain-pack lookup
|
||||
});
|
||||
});
|
||||
|
||||
test('get_skill: explicit --source errors instead of masquerading as --source-id', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
|
||||
const op = operationsByName.get_skill;
|
||||
const params: Record<string, unknown> = { name: 'ingest', source: 'wiki' };
|
||||
expect(() => applyThinClientSourceScope(op, params, '/')).toThrow(/--source-id/);
|
||||
});
|
||||
});
|
||||
|
||||
test('get_skill: explicit --source-id passes through untouched', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: 'gstack' }, () => {
|
||||
const op = operationsByName.get_skill;
|
||||
const params: Record<string, unknown> = { name: 'ingest', source_id: 'wiki' };
|
||||
applyThinClientSourceScope(op, params, '/');
|
||||
expect(params.source_id).toBe('wiki');
|
||||
});
|
||||
});
|
||||
|
||||
test('no scope from any tier leaves params unchanged', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
|
||||
const params = parseOpArgs(queryOp, ['find things']);
|
||||
applyThinClientSourceScope(queryOp, params, '/');
|
||||
expect(params.source_id).toBeUndefined();
|
||||
});
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user