feat: v0.17.3 — Agent Runtime Controls#26
Merged
johnnichev merged 3 commits intomainfrom Mar 22, 2026
Merged
Conversation
v0.17.3 Agent Runtime Controls: token budget, cancellation, cost attribution, structured tool results, per-tool approval, SimpleStepObserver. v0.17.4 Agent Intelligence: token estimation, model switching, knowledge memory enhancement with 4 store backends. Multi-agent orchestration moved from v0.17.2 to v0.18.0.
R7: Tool-level cost attribution — cost_usd field on TraceStep, populated
on LLM_CALL steps from provider usage stats.
R8: Structured tool results — Tool._serialize_result() auto-serializes
dict, list, Pydantic, and dataclass returns as JSON instead of str().
R9: Per-tool approval gate — requires_approval flag on @tool() decorator
and Tool class. Overrides policy ALLOW → REVIEW for flagged tools.
R4: SimpleStepObserver — convenience observer that routes all 30 lifecycle
events to a single callback(event_name, run_id, **kwargs).
R1: Token budget per run — max_total_tokens and max_cost_usd on AgentConfig.
Agent loop checks budget at each iteration start; returns partial result
with BUDGET_EXCEEDED trace step and on_budget_exceeded observer event.
R2: Agent cancellation — CancellationToken (thread-safe) checked at iteration
boundaries and after tool execution. CANCELLED trace step, on_cancelled
observer event. Token is reusable via reset().
New StepTypes: BUDGET_EXCEEDED, CANCELLED (16 total).
New exports: CancellationToken, CancellationError, BudgetExceededError,
SimpleStepObserver.
6 features: token budget, cancellation, cost attribution, structured tool results, per-tool approval gate, SimpleStepObserver. 61 new tests (total: 1908).
johnnichev
added a commit
that referenced
this pull request
Mar 24, 2026
Agent core observers (6 fixes): - astream() cancellation/budget paths now build proper results with trace steps and async observer events (#14) - arun() fires async observers for cancel/budget/max-iter (#15) - _aexecute_tools_parallel fires async observer events (#16) - _aexecute_tools_parallel tracks tool_usage/tool_tokens (#17) - _acheck_policy fires async on_policy_decision observer (#10M) - astream() max-iter path fires async on_run_end (#12M) Tools + providers (7 fixes): - Anthropic empty content list guard (#19) - Bool rejected for int/float params (#20) - ToolRegistry.tool() has screen_output/terminal/requires_approval (#21) - MultiMCPClient list_all_tools() copies tools before prefixing (#22) - Streamable-http 3-tuple unpacking robust handling (#23) - _serialize_result returns "" for None (#24) - StructuredOutputEvaluator handles __slots__ (#45) RAG (6 fixes): - SQLiteVectorStore search documented limitation (#25) - InMemoryVectorStore max_documents warning (#26) - Pinecone metadata.get instead of .pop (#27) - ContextualChunker None content guard (#28) - Filter overfetch: top_k*4 when filter present (#29) - OpenAI embed_texts batching at 2048 (#30) Memory (5 fixes): - FileKnowledgeStore reads under lock (#32) - SQLiteSessionStore WAL mode (#33) - SQLiteKnowledgeStore indexes on query columns (#34) - query() LIMIT after TTL filter (#35) - Redis save() category update in pipeline (#36) Evals (4 fixes): - 16 LLM evaluators fail on unparseable score (#37) - XSS fix: textContent instead of innerHTML (#38) - Donut SVG 360° arc: two semicircles (#39) - Suite completed counter under threading.Lock (#46) Security (5 fixes): - REWRITE/WARN guardrails tracked in trace (#40) - SSN regex requires consistent separators (#41) - Topic guardrail Unicode normalization (#42) - Coherence usage tracked in agent costs (#43) - Coherence fail_closed option (#44) Full suite: 2013 passed.
johnnichev
added a commit
that referenced
this pull request
Mar 24, 2026
HIGH fixes recovered: - Bug #22: MultiMCPClient copy.copy(tool) before prefix mutation - Bug #26: InMemoryVectorStore max_documents capacity warning - Bug #27: Pinecone metadata.get not .pop (stops mutating response) - Bug #28: ContextualChunker (content or "").strip() None guard - Bug #29: InMemoryVectorStore overfetch top_k*4 when filter present - Bug #36: Redis save() category srem moved into pipeline - Bug #38: XSS fix — createElement/textContent replaces innerHTML - Bug #41: SSN regex uses strict alternation (?:\d{3}-\d{2}-\d{4}|\d{9}) LOW fix: - Bug #35: KnowledgeMemory.remember() uses UTC consistently - Fixed naive/aware datetime comparison in prune_old_logs - Updated tests to use UTC dates Full suite: 2013 passed.
johnnichev
added a commit
that referenced
this pull request
Apr 5, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
max_total_tokensandmax_cost_usdonAgentConfigwithBUDGET_EXCEEDEDtrace step and observer eventCancellationToken(thread-safe) checked at iteration boundaries and after tool executioncost_usdfield onTraceStepforLLM_CALLstepsrequires_approvalflag on@tool()decoratorTest plan
🤖 Generated with Claude Code