Changelog
Mirrored from CHANGELOG.md in the library repository. For upgrade instructions, see Upgrading.
[0.37.0] - 2026-11-19
- Breaking:
reasoningnow names a model's own knobs:"default"or{ enabled?, effort?, display? }."off"becomes{ enabled: false }and"on"is gone; use{ effort: "medium" }for the same request.enabled: trueturns thinking on without naming an effort where the provider has a switch (Anthropic, Together AI, OpenRouter, Gemma 4 on Gemini) and throwsINVALID_OPTIONSelsewhere. See Upgrading. - Breaking:
ReasoningEfforthas six levels,minimal,low,medium,high,xhighandmax, sent to the provider as written.xhighandmaxno longer needproviderOptions. AddedREASONING_EFFORTS, and budget-only models get a token budget for every level. See Upgrading. - Added
ModelCatalog.reasoningControl()andreasoningOptions, which report the efforts a model offers and a suggested setting. SavedCatalogDatais now version 5, so older copies are refetched. - Breaking: an
Instructschema is a JSON Schema: pass a plain JSON Schema object or any Standard Schema such as Zod. The model is shown the JSON Schema in place of an example object, so constraints like.min()and.regex()reach it, and schemas that used to throw (.nullable(), unions, tuples, records, non-object roots) are accepted. See Upgrading. - Breaking:
parseResponse()andInstruct.parse()now return a promise.instruct.render()returns the prompt alone, and the schema is stored on the message asoutput.InstructInputsvalues are limited to strings, numbers, booleans andnull. See Upgrading. - Added
Instruct.toJSON()andInstruct.fromJSON(). - Breaking: a remote
sendcommand now carries theInstructas data instead of a rendered prompt. A 0.36 client and a 0.37 host do not interoperate, so deploy both sides together. See Upgrading. - Added
agent.onStep()(andhandle.onStep()onstream()), an awaited hook at the end of each step so a host can save usage and state while a turn runs. CustomStreamHandleimplementations must add it. - Added
agent.session, which returns the session synchronously and works inside hooks, continuations and tools wheresnapshot()would deadlock.agent.snapshot()is deprecated. agent.messagesnow grows as each step ends instead of when the turn ends.turn:endusage now includes failed requests and keeps subagent rows in call order.- Added
@fifthrevision/axle/analyze:analyze()reads stored turns into segments (turns, tools, subagents, compactions, texts and errors), with the predicatesfailed,completed,cancelled,byUser,byAgentandnamed, and the functionsstreaks,repeats,sum,flatten,partOfandsimplify. Experimental. turn:endandTurnnow record how a turn ended:errorfor a thrown error andcancelReasonwhenturnTimeoutMscancelled it.- A send that fails or is cancelled while listing MCP tools now keeps its user message and ends the turn with
errororcancelled, instead of being dropped. - A failed subagent's tool error now names the failure kind and message instead of embedding the failure as JSON.
- Text and thinking stream events now carry
index. This fixes grounding citations that arrived after their text, which Gemini sends, being lost from turns.
[0.36.3] - 2026-11-14
- Fixed an agent becoming unusable after a turn was cancelled or timed out while the model was still writing its response. A tool call that had started streaming was kept with no result, and a text part opened but not yet written to was kept as an empty string; providers rejected every later request. A cancelled model call now keeps only what was written: no tool calls, no empty text and no empty thinking parts. When nothing was written,
error.partialisundefinedand no assistant message is added. See Upgrading. - Anthropic thinking parts now carry
continuityonly once a signature or redacted data has arrived, instead of starting with an empty signature.
[0.36.2] - 2026-11-12
- Fixed an agent becoming unusable after a turn was cancelled, timed out, or hit a fatal tool error while a tool was running. The tool call was left without a result, and providers rejected every later request. Each call in the batch now gets a result: its real one if it finished, or an error of type
cancelledorfatal.agent.messagesand the error'smessagestherefore end in a tool results message. See Upgrading.
[0.36.1] - 2026-11-12
- Breaking: Axle no longer requests citations for documents sent to Anthropic, and there is no option to re-enable them. Answers about PDF or text documents now arrive as plain text parts. Document citations already stored in a conversation are kept on the messages but left out of requests to Anthropic, which would otherwise reject them. Citations from hosted web search are unchanged. See Upgrading.
[0.36.0] - 2026-11-08
- Added deferred tools: a tool definition with no
executethat the caller answers. Calls go toonToolCallonstream(),generate()andagent.onToolCall(), or are answered from outside withtoolCall(id).answer()/.fail(). A call with no answer keeps waiting instead of failing (generate()still fails fast). Added thetool:waitingandaction:waitingevents, thedeferredaction part, and theisCall/isActionOfhelpers. - Breaking:
onToolCallnow receives a single{ id, name, input }call plus the tool context, and only handles deferred tools; it no longer intercepts executable tools. Unanswered calls no longer produce anunanswerederror result. - Added experimental remote agents:
RemoteAgentdrives an Agent served elsewhere overhttpTransportorloopbackTransport, withInMemoryEventStoreandtoEventStreamResponseon the served side. Streams resume from the last cursor after a dropped connection, and a 404 or 410 ends the agent. A runnable example is inexamples/remote. - Added the agent operation lifecycle:
agent.onnow deliversoperation:start,after:start,after:end,operation:endandagent:idleevents, andagent.statusreports whether the agent is idle or busy.TurnEventCallbackis nowAgentEventCallback. - Added
agent.onStart(), which runs before an operation's turn opens and can refuse it. Turns sent inline from a continuation now carry athreadId. - Breaking:
onSettlednow fires once per send or manual compaction, after the continuation finishes, instead of after every turn. - Breaking: removed
signalfrom inlinectx.send()options; it was previously ignored. Cancel the operation to abort an inline turn. - Added
turnTimeoutMsto bound a whole turn, andstreamStallMsto fail a step when the provider stream goes silent. Both are unset by default. send()accepts anidfor its user turn.- Fixed the
stream-web-search-errorcheck failing for the wrong reason on Haiku 5.5, and documented check retries in the checks README.
[0.35.0] - 2026-11-03
- Breaking:
AxleFailureis nowAxleProviderFailure(old names removed);modelfailures split intoapiandincomplete, and every setup mistake throws a codedAxleError(INVALID_OPTIONS,PROVIDER_UNSUPPORTED,FILE_UNREADABLE,MCP_NOT_CONNECTED, …) instead of resolvingok: false.InstructVariableErroris nowAxleInstructVariableError,TaskErroris gone, andisAxleError/AxleErrorCodenarrow catches. See Upgrading. - Breaking: providers are a
protocol(messages,responses,generateContent,chatCompletions) plus anid, replacingAIProvider.name;ModelCatalogsaysprovidernothost. New protocol constructorsmessages(),responses(),generateContent(),chatCompletions({ baseUrl, … }), plusopenrouter(),togetherai(), andbedrock()presets. First-partybaseUrlmoved to the constructors;chatCompletions()takes one options object andvendoris nowid+dialect. - Breaking:
ModelCatalogno longer fetches — build it fromCatalogDataviafetchModelsDev()+ModelCatalogStore+catalogFile();lookup/contextWindowtake{ provider }, data is version 4. NewcomputeCost(usage, catalog)prices per-requestbreakdownrows. - Breaking:
usage.breakdownis one row per request (withagent,at,requestedModel),Stats.breakdownis required — useattributeStats()for hand-built usage.UsageEntry.provideris the providerid(google,openai, vendor id) and optional. - Breaking:
AgentDefinitionandcreateAgentConfig()are removed; rebuildAgentConfigfrom your own saved recipe plusAgentSession. Turns carryfailure(noterror),turn:endcarriesreason(stop|length), cancelled tool calls emitaction:cancelled, cancelled compactions emitcompaction:cancelled, andCompactionPartgainstrigger. - Added
aftercontinuations onsend(): run inline turns viactx.send()after the turn settles, listed underresult.after.onSettlednow fires per committed turn, tool batches run concurrently, and the Gemini SDK floor is 2.31.0.
[0.34.3] - 2026-10-28
- Tool call arguments are now parsed with the tool's schema before
execute. Invalid arguments no longer reachexecute: the model gets an error tool result with typevalidationnaming each issue (for exampledescription: Invalid input: expected string, received undefined) and can correct the call in the same turn.executereceives the parsed value, so schema defaults and transforms now apply. A parallelized tool's call is rejected as a whole when any item is invalid. MCP tools are validated too, and unknown top-level keys are dropped before the call reaches the server, matching a defaultz.object(), rather than rejected.
[0.34.2] - 2026-10-24
- Added
baseUrlto the shared provider client options, soanthropic(),openai()andgemini()can route requests through a proxy that speaks the vendor's API.typesafe()already had it.chatCompletions()keeps its base URL as the first argument and rejects the option.
[0.34.1] - 2026-10-16
- Enabled prompt caching by default for Anthropic and OpenRouter, with a
cacheopt-out. OpenRouter tool-loop requests now stay on the same session, and Together cached-token usage is recognized.
[0.34.0] - 2026-10-10
- Breaking (CLI): untrusted folders no longer load project
.axle/configuration or credentials, and tools that can modify or execute (exec,patch-file, andwrite-file) are disabled until you runaxle trustfor that folder. - Breaking (CLI): schedule commands now register jobs with
axle schedule add; useaxle -jfor a proof run.removeandsessionsselect schedules by name. - Added CLI skill discovery from user and trusted project skill directories;
axle inforeports loaded, shadowed, ignored, and invalid skills. - Added experimental typed decisions with
decide()and thetypesafe()provider. - Added live skill updates that take effect at the next provider request, plus safer skill-name validation and escaped skill output.
- Added per-provider custom fetch support and moved web-search configuration into provider tools.
- Added Agent
onIdlecallbacks, awaitable settlement hooks, queued-operation tracking, and cancellation support; snapshots now wait for the Agent to become idle. - CLI chat now tracks queued sends and compactions as pending work, supports queuing input during a turn, and improves interrupt and session-settlement behavior.
- Added model-catalog context-window lookup and display in
axle info; the CLI status bar now shows context use as a percentage. RemovedAXLE_CONTEXT_WINDOW. - Improved CLI credential loading and development-build version reporting, and removed the generic chat-completions provider from the CLI.
- Fixed OpenAI web-search citations that could crash core, and improved handling of dropped or malformed skill data.
[0.33.0] - 2026-10-06
- Breaking: removed the model registry. The
@fifthrevision/axle/modelsentry point no longer exists; pass model IDs as plain strings ("openai/gpt-5.5"), and OpenRouter IDs are sent unchanged. - Breaking: removed
temperature,topP, andstopfromgenerate(),stream(), and agent request options; send them throughproviderOptionsusing the provider's own field names. - Breaking: normalized provider tool parts across providers with portable
inputandresultfields and per-providercontinuity; addedprovider-tool-resultcontent parts andprovider-tool:input/provider-tool:errorevents, and removedoutputfromprovider-tool:complete. - Breaking: provider refusals are now reported as a dedicated
refusalfailure kind instead of empty or mislabeled successes. - Breaking: flattened failure results so
type,message,status, andusagesit directly onmodelfailures, and rejected API keys are detected astype: "authentication". - Breaking: removed
AxleStopReason.ErrorandAxleStopReason.Custom; unknown stop reasons now fail the request. - Breaking (CLI): local tools (
exec,read-file,write-file,patch-file) are enabled by default in chat and recipes, and thecalculatortool was removed. Addtools: []to keep a recipe tool-free. - Added
axle infoto print the version, config files, defaults, and every configured provider, showing where each value came from and API keys only as set or unset. - Added recipe scheduling on macOS: declare
schedule: { every: 1h }orat: "09:00"in a recipe and useaxle schedulecommands to register, list, inspect sessions, and remove LaunchAgent-based runs. - CLI replies now render as markdown (headings, code, lists, tables), prompts use GitHub CLI-style glyphs, and a default
axle-helptool lets the model answer questions about axle itself. - Thinking text now streams from Claude and OpenAI models when
request.reasoningis enabled. - Anthropic
pause_turnresponses continue automatically within a single step, with usage summed across the follow-up requests. - Surfaced provider code execution output (stdout/stderr/exit code) in action results, newly enabled Anthropic code execution, and preserved Gemini code execution parts across turns.
- Kept Anthropic server tool results when a server tool runs alongside client tools, so follow-up requests no longer fail.
- Chat Completions HTTP errors now report the provider's error type and message instead of the raw status and body, and custom headers can be passed through provider client options.
- Agent session IDs are forwarded to OpenRouter so conversations stick to one upstream provider.
- OpenAI assistant items are replayed in their original order, fixing requests that reasoned between web searches.
- Adjacent text parts are joined without separators, fixing broken sentences and unparseable
InstructJSON. - OpenAI responses cut off at
maxOutputTokensand Anthropic'smodel_context_window_exceedednow finish withlengthand keep partial content. web_searchresolves to newer provider versions, and Gemini searches now surface aprovider-toolpart with the queries used.- Anthropic's implicit
max_tokensdefault is now 128,000.
[0.32.0] - 2026-09-12
- Breaking: renamed thinking stream events and separated displayable thinking summaries from raw reasoning content for clearer reasoning handling.
- Unified generation request handling for streaming transports, improving consistency between standard and streaming responses.
- Preserved OpenRouter and Gemini reasoning continuity metadata across generation, streaming, and assistant message conversion.
- Added portable controls for displaying, hiding, or retaining reasoning only for provider continuity.
- Improved usage reporting for OpenAI cached responses by tracking cache write tokens in standard and streaming flows.
- Fixed Gemini thinking/signature handling and related provider issues.
- Updated runtime support to require Node.js 22.
[0.31.0] - 2026-09-08
- Added portable reasoning controls with named modes and effort levels, including validation and updated reasoning documentation.
- Redesigned
axle-cliaround interactive chat by default, with batch and resume commands, persistent sessions, and improved terminal rendering. - Added CLI session resumption, automatic context compaction, and configurable compaction size controls for longer-running conversations.
- Added layered CLI configuration loading and validation, support for the v3 job configuration schema, and timestamped CLI log files.
- Improved CLI reliability for piped input, non-interactive runs, interrupted runs, failed batches, session cleanup, and credential handling.
- Updated available model definitions.
[0.30.2] - 2026-08-23
- Added support for OpenRouter streaming thinking deltas so reasoning output is handled correctly during chat completions.
- Added reasoning option support for prompt compaction, enabling thinking-capable model configurations during compaction.
- Updated available model definitions.
[0.30.1] - 2026-08-13
- Fixed
PromptCompactorprogress reporting and summary handling so completed compactions are reported reliably without duplicating generated summaries.
[0.30.0] - 2026-08-13
- Breaking: replaced agent-owned history with host-owned transcripts: use
agent.messagesfor active conversation state and attach aTranscriptto the event stream for persistence. - Breaking: renamed
TurnAccumulatortoTranscriptand updated the related transcript exports and persistence APIs. - Breaking: removed built-in memory APIs and automatic recall/record behavior; use tools for model-directed memory and
Instruct.addContext()for host-provided context. - Breaking: removed session-level annotations and transcript state; annotations now belong to turns or parts, with session-wide application state kept by the host.
- Breaking: refactored compaction into trigger, policy, and compactor layers with stateful compaction parts and
compaction:update/complete/errorevents; automatic compaction failures are now recorded without failing the user turn. - Improved
PromptCompactorprogress reporting and summary handling so repeated compactions avoid reusing prior summaries. - Updated the README, terminology docs, and 0.30.0 migration guide.
[0.29.0] - 2026-08-05
- Added Qwen 3.7 Flash and Qwen 3.8 Max model definitions.
- Updated Qwen model metadata with larger output limits for selected Qwen 3.6 and 3.7 models.
- Breaking: renamed tool-loop terminology from “turn” to “step”:
maxIterationsis nowmaxSteps,"max-iterations"is now"max-steps", stream events are nowstep:start/step:complete, andgenerateTurnis nowgenerateStep. - Added a 0.29.0 migration guide and terminology reference for the step/turn naming changes.
[0.28.0] - 2026-07-27
- Added
agent.stop()to stop an active turn at the next tool-batch boundary without interrupting in-flight work. - Added
agent.clear()to cancel queued agent operations while leaving the active turn untouched. - Added
PromptCompactorand automatic before/after-turn compaction triggers for easier long-session management. - Improved compaction cancellation, history handling, and messages for repeated compactions.
- Updated available model definitions and fixed Gemini thinking configuration for newer Gemini 3.x models.
[0.27.1] - 2026-07-17
- Added support for the Kimi K3 model.
[0.27.0] - 2026-07-10
- Improved model registry support for clearer model selection.
- Updated TypeScript support and improved type narrowing definitions.
[0.26.1] - 2026-07-09
- Fixed OpenAI tool schemas so optional properties are accepted correctly.
- Improved generation failure handling and exposed the clearer
AxleFailurename while keepingGenerateErroras an alias. - Improved stream turn accumulation error handling for more reliable failures.
- Removed the Gemini 3.5 Pro model option.
[0.26.0] - 2026-07-06
- Added experimental context compaction:
agent.onCompaction(callback)supplies the policy and strategy,await agent.compact()triggers it. Active history is replaced;agent.historynow exposesmessages(active),archive(raw append-only), andcompactions(receipts). Compaction renders as an agent turn containing a newcompactionpart and emitscompaction:start/compaction:endturn events. - Added
maxContextTokenstostream()/generate(): a token budget for the tool loop, checked after each turn settles. - Behavior change: loop limits are stops, not errors.
maxIterationsandmaxContextTokensreturnok: truewithstopped: "max-iterations" | "token-limit"instead of an error result. Non-positive limits throw at call time. - Breaking:
agent.history.logis nowagent.history.messages. - Breaking:
agent.snapshot()is now async; it waits for in-flight work to settle so snapshots are always at rest. - Breaking: removed
Agent.restore(); resume withnew Agent(config, session). - Breaking: removed
indexfromStreamEvent. Correlate tool events byid; text/thinking deltas belong to the most recently opened part. - Breaking: removed the
createHandleexport. - Added an
agent-compactionbaseline check exercising compaction end to end against live providers.
[0.25.5] - 2026-07-03
- Add Claude Fable, Sonnet 5; Gemini 3.5 models
[0.25.4] - 2026-06-17
- Improved
parallelizehandling for more reliable batched tool execution.
[0.25.3] - 2026-06-16
- Fixed OpenAI file handling so filenames and URLs are resolved correctly.
[0.25.2] - 2026-06-15
- Fixed tool calls with syntactically invalid JSON parameters so they are handled gracefully instead of failing.
[0.25.1] - 2026-06-13
- Consolidate vendor options for ChatCompletions
[0.25.0] - 2026-06-12
- Added a web search fallback for more reliable search behavior.
- Improved handling of non-text tool results.
[0.24.0] - 2026-06-11
- Added experimental subagent tools for delegating bounded work to other agents, with child turn-event forwarding (
action:child-event). - Added experimental parallel tool execution for running batched tool calls concurrently.
- Added tool context helpers for reporting usage and adding contextual information during runs, including a flat per-provider/model
Stats.breakdown. - Added the
tool:exec-errorstream event for fatal/aborted tool calls;Agent.on()now returns an unsubscribe function. - Behavior change: in
stream(), a user-providedonToolCallreturningnull/undefinednow falls through to executing the matching registry tool (matchinggenerate()'s existing semantics) instead of producing anot-foundresult. - Behavior change: a tool throwing an error merely named
AbortErrorwhile the run's signal is live is reported to the model as an ordinary tool error instead of aborting the run. - Fixed output fencing in generated content.
[0.23.1] - 2026-06-08
- Updated Anthropic thinking configuration support
[0.23.0] - 2026-06-08
- Improved observability with a simplified span-based tracing interface
- Added richer trace events, span completion details, and token/content logging for agent and streaming runs
- Added provider tool logging and support for routing observability data to multiple sinks
[0.22.1] - 2026-06-07
- Improved handling of chat-completions streaming errors
- Fixed Gemini citation handling
[0.22.0] - 2026-06-06
- Added support for OpenRouter web search citations
- Improved citation handling for web search results
- Fixed tool handling for interleaved tool calls
[0.21.0] - 2026-05-30
- Added support for Opus 4.8
- Added support for citations and thinking formats
- Added configurable retry options
- Added a convenience method for rehydrating agents
- Added metadata support for turns and messages
[0.20.0] - 2026-05-25
- Split the library and CLI into separate packages for clearer installation and usage
- Added
AgentSessionand snapshot restore APIs for saving and resuming agent sessions - Added
createAgentConfigfor easier agent configuration - Updated memory handling so memory is managed separately from
AgentConfig - Added documentation updates and removed Brave-related docs/support
[0.19.0] - 2026-05-24
- Added a browser-only export for client-side bundles that omits server-only code
- Added annotations support to Turns
[0.18.0] - 2026-05-22
- Added support for Gemini 3.5 Flash
- Standardized request options across providers, including output tokens, temperature, top-p, stop sequences, tool choice, and provider-specific options
- Renamed provider option types and runtime parameters; see the 0.18.0 migration guide for update details
- Updated usage stats to include cached tokens and thinking tokens
- Added a simple context counter and split MCP tools for more flexible tool usage
- Fixed bugs found during smoke testing
[0.17.0] - 2026-05-13
- Updated the Instruct constructor to use object-style options
- Improved Instruct schema typing to support any Zod schema
- Added clearer errors for missing template variables
- Improved result ergonomics for easier handling by applications
[0.16.3] - 2026-05-13
- Added vars mode to Instruct for easier variable-based prompting
- Fixed bugs found through live provider testing
[0.16.2] - 2026-05-11
- Fixed OpenAI and Chat Completions providers:
reasoning: falsenow sends no reasoning effort instead of minimal reasoning
[0.16.1] - 2026-05-11
- Added
z.enumandz.literalsupport to Instruct structured-output schemas
[0.16.0] - 2026-05-11
- Added
instructsupport to generate and stream APIs for supplying structured instructions directly - Updated structured output instructions to use JSON for more reliable parsing
- Added open-weight model options
- Improved cancellation behavior by propagating abort signals through MCP tool calls
[0.15.1] - 2026-05-08
- Added
AxleToolFatalErrorfor fatal tool failures, allowing generation, streaming, and agent runs to stop immediately without retrying or exposing the error to the model - Fatal tool errors now preserve available partial output, messages, usage, and tool context for easier handling by applications
[0.15.0] - 2026-05-08
- Abort operations now throw errors, making cancellation behavior easier to detect and handle
[0.14.0] - 2026-05-07
- Simplified the Agent and Instruct APIs for easier use and better TypeScript support
- Added support for binding inputs to Instruct templates with
withInputs,withInput, andclone - Improved template variable handling by consistently reporting missing required variables
[0.13.0] - 2026-05-06
- Added provider tool registries for configuring and organizing available tools
- Added streaming support for tool outputs and tool arguments
- Improved tool execution with abort-signal support and streamed command output
- Updated available models
[0.12.0] - 2026-04-30
- Added basic thinking/reasoning support to the generation API
- Added file support improvements: better
FileInfotypes, improved image type checks, file data support in chat completions, and new usage examples - Removed
instructionsas a concept fromInstruct, simplifying the interface
[0.11.0] - 2026-04-24
- Added support for OpenAI models
- Provider models are now exported from the package
[0.10.2] - 2026-04-24
- Added timing information to agent/generation output
- Added support for Claude Opus 4.7
[0.10.1] - 2026-04-07
- Update distribution artifacts and config
[0.10.0] - 2026-04-05
- Agent now emits Turns, with an updated agent interface to match
- Agent history now carries both Turn and Message parts in parallel, improving fidelity when converting between representations
- Added configuration support to hooks
- Improved error semantics and error reporting for tool-call not found cases
- Fixed a bug where history could be incorrectly committed when a cancellation was in flight
- Updated to latest dependencies and models
[0.9.0] - 2026-02-22
- Added procedural memory support, allowing agents to retain and recall information across interactions
- Made the tool call callback optional when using
generate, reducing boilerplate for simple use cases - Simplified tracing interfaces for easier integration and usage