can1357 3f304ee5a8 refactor(agent-core): isolated token counting into a new local tokenizer ...

- Extracted native token counting into a new localized `tokenizer.ts` wrapping `@oh-my-pi/pi-natives`.
- Introduced a lightning-fast byte-length estimation logic for token counting when accurate counting is disabled.
- Diverted token calculations to the faster estimator during test environments and when `PI_TOKENIZER_ACCURATE` is falsy.
- Updated agent base and coding-agent sessions to consume the new localized `countTokens` utility.

2026-06-18 01:57:23 +02:00

..

compaction

refactor(agent-core): isolated token counting into a new local tokenizer

2026-06-18 01:57:23 +02:00

utils

refactor(agent): replaced keepalive utility with disposable EventLoopKeepalive

2026-05-28 09:51:57 +02:00

agent-loop.ts

feat(agent): added transformAssistantMessage hook

2026-06-18 00:59:56 +02:00

agent.ts

feat(agent): added transformAssistantMessage hook

2026-06-18 00:59:56 +02:00

append-only-context.ts

refactor: renamed grammar module to dialect with unified transcript rendering

2026-06-15 13:58:12 +02:00

compaction.ts

refactor(compaction): moved compaction APIs to @oh-my-pi/pi-agent-core

2026-05-15 18:31:12 +02:00

index.ts

refactor(agent-core): isolated token counting into a new local tokenizer

2026-06-18 01:57:23 +02:00

proxy.ts

refactor(catalog)!: split model catalog from pi-ai

2026-06-10 04:06:57 +02:00

run-collector.ts

perf: replaced WeakMap caches with symbol-keyed properties

2026-05-17 03:47:45 +02:00

telemetry.ts

Merge PR #1879: fix(agent): handle string systemPrompt in telemetry content capture

2026-06-15 19:46:11 +02:00

thinking.ts

feat: introduced Effort enum and ThinkingConfig for model-aware reasoning

2026-03-06 12:35:01 +01:00

tokenizer.ts

refactor(agent-core): isolated token counting into a new local tokenizer

2026-06-18 01:57:23 +02:00

types.ts

feat(agent): added transformAssistantMessage hook

2026-06-18 00:59:56 +02:00