mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-30 19:49:14 +00:00
Ingmar KruschandGitHub
dde1bd9353
* fix(patterns): make reflections/patterns slug sub-paths configurable gatherReflections()'s SQL WHERE clause and the pattern-page write slug were hardcoded to wiki/personal/reflections/ and wiki/personal/patterns/ respectively. A prior fix (#2415/#2939) made the leading namespace root configurable via dream.synthesize.output_root, but the personal/reflections and personal/patterns sub-path segments stayed pinned literals, so brains whose schema has no personal/ nesting (e.g. a flat meetings/ tree) could not point the phase at their own compiled_truth source. Adds two new config keys: - dream.patterns.source_slug_prefix (default: <output_root>/personal/reflections) - dream.patterns.output_slug_prefix (default: <output_root>/personal/patterns) Both default to the exact literal the code previously hardcoded, so existing installs see no behavior change. A custom output_slug_prefix is also added to the subagent's put_page allow-list, since the filing-rules JSON globs only remap the wiki/personal/patterns/* literal by output_root and would otherwise reject writes to a differently-shaped output path. Updated test/cycle-patterns.test.ts's scope-filter assertions to match; added coverage for the two new config keys and the allow-list addition. * fix(patterns): drain PGLite subagent job inline (no worker claims it) runPhasePatterns submitted a subagent job via queue.add() and waited on it via waitForCompletion, but on PGLite there is no separate Minions worker process (the embedded data-dir holds an exclusive file lock; 'gbrain jobs work' refuses to start against it). synthesize.ts already has runPgliteSubagentsInline to drive the claim -> run -> complete loop inline for exactly this reason; patterns.ts never called it, so a real (non-dry-run) invocation against a PGLite brain always hung until subagentWaitTimeoutMs (default 35 min) with the job stuck in 'waiting'. Exports runPgliteSubagentsInline from synthesize.ts (was test-only via __testing) and calls it from patterns.ts with the same private per-run childQueueName derivation synthesize.ts uses, so the inline drain never claims unrelated 'default'-queue jobs a Postgres worker owns. Updated test/cycle-patterns-child-outcome.test.ts's #2782 regression test: its premise (no worker running with a 1ms wait timeout, so the job never completes and waitForCompletion genuinely times out) is exactly the scenario this fix addresses. With the inline drain, a fake ANTHROPIC_API_KEY test fixture now gets claimed and actually attempted, failing fast and landing the job in 'dead' rather than staying uncompleted until a timeout. The #2782 status-reflects-outcome contract the test exists to pin is unchanged (any non-'complete' outcome with zero writes still surfaces as status 'fail'); updated the expected outcome/error code to match the outcome that now actually occurs. * feat(think): surface usage/cost_usd in --json output think's own cost was previously unsurfaced anywhere: not in this CLI's own --json output, not in budget_ledger (nothing in src/core/think/*.ts ever writes to it), and invisible to a wrapping caller's own token accounting since the LLM call think makes is its own, separate API call from anything the caller's session tracks. runThink() already captured result.usage.{input_tokens,output_tokens} from the underlying client.create() call but discarded it. Adds usage/cost_usd to ThinkResult, populates usage on the real-LLM-call path (undefined on the no-client/stub paths, matching how synthesisOk already distinguishes those), and computes cost_usd in think.ts's CLI handler via the existing canonicalLookup() pricing table (same pattern brain-score-recommendations.ts's estimateAnthropicCost already uses). Extracted the multiply-and-sum into a small exported computeThinkCostUsd for direct unit testing. Also appends the cost to the human-readable footer. Verified live: gbrain think --json against a real anchor returned usage:{input_tokens:3271,output_tokens:1490}, cost_usd:0.0536, matching Opus pricing ($5/$25 per MTok) by hand calculation.
38 lines
1.5 KiB
TypeScript
38 lines
1.5 KiB
TypeScript
import { describe, expect, test } from 'bun:test';
|
|
import { computeThinkCostUsd } from '../src/commands/think.ts';
|
|
|
|
// think's own cost was previously unsurfaced anywhere: not in this CLI's own
|
|
// --json output, not in budget_ledger, and invisible to a wrapping caller's
|
|
// own token accounting (the LLM call think makes is its own, separate API
|
|
// call). computeThinkCostUsd is the small, pure function that turns
|
|
// {input_tokens, output_tokens} + a resolved modelUsed into a USD figure via
|
|
// the existing canonical pricing table.
|
|
describe('computeThinkCostUsd', () => {
|
|
test('computes cost from real usage against a known model', () => {
|
|
const cost = computeThinkCostUsd(
|
|
{ input_tokens: 1_000_000, output_tokens: 1_000_000 },
|
|
'anthropic:claude-sonnet-5',
|
|
);
|
|
// sonnet-5 pricing: input $3.00/MTok, output $15.00/MTok.
|
|
expect(cost).toBe(18);
|
|
});
|
|
|
|
test('undefined usage (no-client/stub path) → undefined, never a fabricated cost', () => {
|
|
expect(computeThinkCostUsd(undefined, 'anthropic:claude-sonnet-5')).toBeUndefined();
|
|
});
|
|
|
|
test('unknown model id → undefined, not zero (no pricing to compute from)', () => {
|
|
expect(computeThinkCostUsd(
|
|
{ input_tokens: 100, output_tokens: 100 },
|
|
'some-unlisted-provider:some-model',
|
|
)).toBeUndefined();
|
|
});
|
|
|
|
test('zero-token usage → zero cost, not undefined (a real call that happened to be free)', () => {
|
|
expect(computeThinkCostUsd(
|
|
{ input_tokens: 0, output_tokens: 0 },
|
|
'anthropic:claude-sonnet-5',
|
|
)).toBe(0);
|
|
});
|
|
});
|