This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
Summary
AI summaryResponse token counter now reports accurate token counts instead of placeholder zeros.
Full changelog
Agents Remember 0.9.5
Makes the response token counter functional: every MCP tool response now reports an accurate token count instead of placeholder zeros.
Highlights
- The token-accounting engine (
models/tokens.py) is now wired into the single response choke point (_tool_payload), so every public tool response carries a realtokens,tokenizer, andtokenCountExact. Previously these shipped as Pydantic defaults (0/""/false). - Default tokenizer is tiktoken
o200k_base(tokenCountExact: true), with a deterministic approximate counter retained as a fallback. - Widened
response_payload/dump_with_token_countto accept anyResponseModel, so operation-less responses such aspingare counted too. - Added
test_tokens.py— first direct coverage of the counters, serializers, and the count fixpoint.
Verification
Full quality wrapper green (ruff clean, Pyright 0 errors, 289 passed / 3 skipped). ping now reports tokens: 44, tokenizer: "tiktoken:o200k_base", tokenCountExact: true.
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About Agents Remember
All releases →Related context
Related tools
Earlier breaking changes
- vmcp-v2.9.0 Removed tools direct_closeout_preview and direct_closeout_apply.
- vmcp-v2.0.0 `WorkflowKind` enum drops `heavy` and `heavy-task` values.
- vmcp-v2.0.0 `skills_install` no longer accepts a `layout` input; installer performs flat copy.
- vmcp-v2.0.0 Removed workflows W-01-heavy-task-workflow and W-03-chat-task-workflow.
Beta — feedback welcome: [email protected]