Compare commits

...

6 Commits

Author SHA1 Message Date
kit-agent 0bbccbb0a5 docs(sdk): document Options.DebugLogger and WithDebugLogger
- README.md: add WithDebugLogger to the functional-options helper list
- pkg/kit/README.md: expand the Debug row and add a DebugLogger row in
  the Options field summary
- www/pages/sdk/overview.md: add WithDebugLogger to the helpers table
  with a note that it overrides WithDebug when set
- www/pages/sdk/options.md: surface DebugLogger in the example, expand
  the Debug field description, add a DebugLogger row to the Core
  fields table, and add a "Custom debug logger" section with the
  interface signature and a log/slog adapter example
2026-06-18 14:22:32 +03:00
kit-agent 276c787937 refactor(sdk): drop unreachable kit.AgentConfig surface
kit.AgentConfig (pkg/kit/types.go) and its toInternal converter were
exposed as the documented "low-level / advanced consumer" path for
agent construction, but the converter was unexported and not wired
into any public constructor — neither New(*Options) nor NewAgent(...Option)
accept an AgentConfig. The only call sites were the dedicated
agent_config_internal_test.go (same-package internal test) and two
fantasy-import regression tests in types_test.go.

Net effect today: no SDK consumer outside pkg/kit can populate or use
kit.AgentConfig in any way. The type, the converter, the dedicated
test file, and a chain of godoc cross-references all exist purely for
their own sake — they don't enlarge what consumers can do, but they
do enlarge the SDK's stability contract (every field becomes a public
shape the internal agent layer can't refactor freely).

The companion PR added Options.DebugLogger + WithDebugLogger so the
last functional capability AgentConfig was documented to enable —
installing a custom debug logger — is reachable through the supported
construction path. With that wired, AgentConfig has no remaining
purpose.

Changes:

- pkg/kit/types.go: remove the AgentConfig struct and its toInternal()
  method. Drop the now-unused internal/agent and internal/tools
  imports. Update the DebugLogger godoc to point at Options.DebugLogger
  and WithDebugLogger instead of AgentConfig.
- pkg/kit/agent_config_internal_test.go: deleted (208 LOC). It exercised
  the unexported toInternal() method directly; with the method gone
  the test has no subject.
- pkg/kit/types_test.go: rename TestAgentConfigNoFantasyImport to
  TestOptionsNoFantasyImport and rewrite it against Options
  (SystemPrompt, MaxSteps, Streaming, Tools, ExtraTools,
  DisableCoreTools, OnMCPServerLoaded). The original test also asserted
  ToolWrapper field semantics; that capability migrates to the hook
  system (OnBeforeToolCall / OnAfterToolResult), already covered by
  hooks_test.go, so the assertion is dropped with a pointer in the
  godoc. TestAgentConfigToolWrapperSignature replaced by
  TestToolSliceSignature, which still pins that []kit.Tool is the
  user-visible slice type for every tool-related SDK surface — the
  no-fantasy-import contract the original test guarded.
- pkg/kit/mcp_tasks.go: update the MCPTaskConfig godoc to stop
  referencing AgentConfig. MCPTaskConfig stays — it is still emitted
  through Options.MCPTask* fields and used as the engine-facing
  config type.
- pkg/kit/README.md: drop the kit.AgentConfig line from the type
  inventory.

internal/agent.AgentConfig is untouched and remains the internal
construction shape. With the public type gone the internal one can
evolve freely without breaking the SDK contract.

Verification:
- go build ./pkg/... ./internal/... ./cmd/... — clean
- go vet ./pkg/... ./internal/... ./cmd/... — clean
- go test -race -timeout 300s ./... — all packages pass
2026-06-18 13:45:00 +03:00
kit-agent 40bc710938 feat(sdk): add Options.DebugLogger and WithDebugLogger option
Today the SDK exposes a DebugLogger interface (pkg/kit/types.go) but no
public path to install one — the only consumer of the field is the
unexported kit.AgentConfig.toInternal() method, which itself is not
reachable from outside the package. As a result, embedders that want to
forward Kit's low-level engine + MCP tool plumbing debug output into
their own logging system (slog, zap, charm/log, an in-app TUI panel,
etc.) have no option but the on/off Debug bool, which always installs
the built-in SimpleDebugLogger / BufferedDebugLogger.

This change closes that gap on the supported Options / functional-option
construction path:

- pkg/kit/kit.go: add Options.DebugLogger DebugLogger. When non-nil it
  is used directly and the Debug bool is ignored; the supplied logger's
  IsDebugEnabled() controls whether downstream code emits messages.
- pkg/kit/options.go: add WithDebugLogger(l DebugLogger) Option.
- internal/kitsetup/setup.go: add AgentSetupOptions.DebugLogger and
  switch SetupAgent's logger selection so the caller-supplied logger
  wins unconditionally; otherwise the existing Debug + UseBufferedLogger
  branch picks the built-in implementation. No behaviour change when
  DebugLogger is nil.
- pkg/kit/kit.go: wire opts.DebugLogger into setupOpts so the New()
  path threads it through.
- pkg/kit/viper_isolation_test.go: add TestWithDebugLoggerPlumbing and
  TestWithDebugLoggerNilClears covering the option-to-field contract
  and later-options-override semantics consistent with the other With*
  helpers.
- pkg/kit/README.md: list WithDebugLogger in the helper inventory.

Notes:
- kit.DebugLogger and tools.DebugLogger are structurally identical
  (LogDebug(string) / IsDebugEnabled() bool), so the SDK value flows
  into the internal field without a conversion.
- This is purely additive on the SDK surface and does not touch
  kit.AgentConfig — that field already carried a DebugLogger, but the
  AgentConfig path is unreachable from outside the package today.
2026-06-18 13:38:14 +03:00
Ed Zynda 888c6c7953 chore(models): refresh embedded models database from models.dev
- add GLM-5.2 across 9 providers (alibaba-token-plan-cn, baseten,
  cloudflare-workers-ai, fireworks-ai, neuralwatt, opencode-go,
  openrouter, venice, vercel)
- add moonshotai/Kimi-K2.7-Code on baseten
- drop deprecated neuralwatt models (MiniMax-M2.5,
  Devstral-Small-2-24B-Instruct-2512, gpt-oss-20b)
- pick up new reasoning_options metadata on several models
2026-06-18 12:42:11 +03:00
Ed Zynda a9d808eb9f build(deps): bump go module dependencies
- charm.land/fantasy v0.31.0 -> v0.32.0
- alecthomas/chroma/v2 v2.26.1 -> v2.27.0
- charmbracelet/openai-go to 20260617131321
- mark3labs/mcp-go v0.54.1 -> v0.55.0
- kaptinlin/jsonschema v0.8.0 -> v0.8.1
- pelletier/go-toml/v2 v2.3.1 -> v2.4.0
- google.golang.org/api v0.284.0 -> v0.285.0
- google.golang.org/genai v1.60.0 -> v1.61.0
2026-06-18 12:37:37 +03:00
Ed Zynda d7948a64f3 fix(app): make ctx.NewSession wait for agent idle (#63) (#64)
- Add ErrAgentBusy sentinel (shared between internal/app and
  internal/extensions) so callers can detect the busy condition with
  errors.Is instead of substring-matching the error message.
- Add App.WaitForIdle(timeout) backed by a per-busy-cycle idleCh closed
  by a new setBusyLocked chokepoint; all busy transitions now route
  through it to keep the channel in sync with the busy flag.
- Have RequestNewSessionFromExtension wait for idle (up to
  DefaultNewSessionIdleWait = 10m) instead of failing fast on IsBusy.
  This fixes the v0.79.0 phase-handoff race where OnAgentEnd fires from
  inside the agent loop, before drainQueue clears busy, so
  ctx.NewSession reliably failed with 'agent is busy'.
- Expose ext.ErrAgentBusy to Yaegi via symbols.go.
- Update NewSession godoc and phase-handoff example to document the new
  wait-then-send behavior.
- Add regression tests covering already-idle, blocks-until-drain,
  timeout, zero-timeout, app-close, headless guard, and idleCh
  transitions.

Fixes #63
2026-06-18 12:33:54 +03:00
20 changed files with 692 additions and 454 deletions
+4 -4
View File
@@ -691,10 +691,10 @@ host, err := kit.NewAgent(ctx,
Available options: `WithModel`, `WithSystemPrompt`, `WithStreaming`,
`WithMaxTokens`, `WithThinkingLevel`, `WithTools`, `WithExtraTools`,
`WithProviderAPIKey`, `WithProviderURL`, `WithConfigFile`, `WithDebug`, and
`Ephemeral`. For advanced configuration not covered by the helpers (custom MCP
config, in-process MCP servers, session backends, MCP task tuning) construct an
`Options` value explicitly and call `kit.New`.
`WithProviderAPIKey`, `WithProviderURL`, `WithConfigFile`, `WithDebug`,
`WithDebugLogger`, and `Ephemeral`. For advanced configuration not covered by
the helpers (custom MCP config, in-process MCP servers, session backends, MCP
task tuning) construct an `Options` value explicitly and call `kit.New`.
### Per-instance config isolation
+6 -2
View File
@@ -54,8 +54,12 @@ func Init(api ext.API) {
return
}
// NewSession blocks until the TUI completes the switch; run it in
// a goroutine so the agent's turn-end pipeline isn't stalled.
// NewSession blocks while the agent finishes settling and then while
// the TUI completes the switch; run it in a goroutine so the agent's
// turn-end pipeline isn't stalled. The internal wait-for-idle (added
// in response to issue #63) makes this reliable even when post-turn
// tooling (formatters, on-save hooks, hidden tool calls) extends the
// busy window past AgentEnd.
go func() {
if err := ctx.NewSession(HANDOFFPrompt); err != nil {
ctx.PrintError("phase-handoff: " + err.Error())
+8 -8
View File
@@ -5,16 +5,16 @@ go 1.26.4
require (
charm.land/bubbles/v2 v2.1.0
charm.land/bubbletea/v2 v2.0.7
charm.land/fantasy v0.31.0
charm.land/fantasy v0.32.0
charm.land/huh/v2 v2.0.3
charm.land/lipgloss/v2 v2.0.4
github.com/alecthomas/chroma/v2 v2.26.1
github.com/alecthomas/chroma/v2 v2.27.0
github.com/atotto/clipboard v0.1.4
github.com/aymanbagabas/go-udiff v0.4.1
github.com/charmbracelet/colorprofile v0.4.3
github.com/charmbracelet/fang v1.0.0
github.com/charmbracelet/log v1.0.0
github.com/charmbracelet/openai-go v0.0.0-20260319145158-d0740cc34266
github.com/charmbracelet/openai-go v0.0.0-20260617131321-5e4b9c18c4be
github.com/charmbracelet/ultraviolet v0.0.0-20260615092913-2399af76d5b1
github.com/charmbracelet/x/editor v0.2.0
github.com/clipperhouse/displaywidth v0.11.0
@@ -23,7 +23,7 @@ require (
github.com/fsnotify/fsnotify v1.10.1
github.com/indaco/herald v0.13.0
github.com/indaco/herald-md v0.3.0
github.com/mark3labs/mcp-go v0.54.1
github.com/mark3labs/mcp-go v0.55.0
github.com/spf13/cobra v1.10.2
github.com/spf13/viper v1.21.0
github.com/traefik/yaegi v0.16.1
@@ -85,13 +85,13 @@ require (
github.com/googleapis/gax-go/v2 v2.22.0 // indirect
github.com/gorilla/websocket v1.5.3 // indirect
github.com/kaptinlin/jsonpointer v0.4.26 // indirect
github.com/kaptinlin/jsonschema v0.8.0 // indirect
github.com/kaptinlin/jsonschema v0.8.1 // indirect
github.com/mitchellh/hashstructure/v2 v2.0.2 // indirect
github.com/muesli/mango v0.2.0 // indirect
github.com/muesli/mango-cobra v1.3.0 // indirect
github.com/muesli/mango-pflag v0.2.0 // indirect
github.com/muesli/roff v0.1.0 // indirect
github.com/pelletier/go-toml/v2 v2.3.1 // indirect
github.com/pelletier/go-toml/v2 v2.4.0 // indirect
github.com/sagikazarmark/locafero v0.12.0 // indirect
github.com/santhosh-tekuri/jsonschema/v6 v6.0.2 // indirect
github.com/spf13/afero v1.15.0 // indirect
@@ -116,8 +116,8 @@ require (
golang.org/x/net v0.56.0 // indirect
golang.org/x/oauth2 v0.36.0 // indirect
golang.org/x/time v0.15.0 // indirect
google.golang.org/api v0.284.0 // indirect
google.golang.org/genai v1.60.0 // indirect
google.golang.org/api v0.285.0 // indirect
google.golang.org/genai v1.61.0 // indirect
google.golang.org/genproto/googleapis/rpc v0.0.0-20260615183401-62b3387ff324 // indirect
google.golang.org/grpc v1.81.1 // indirect
google.golang.org/protobuf v1.36.11 // indirect
+20 -20
View File
@@ -2,8 +2,8 @@ charm.land/bubbles/v2 v2.1.0 h1:YSnNh5cPYlYjPxRrzs5VEn3vwhtEn3jVGRBT3M7/I0g=
charm.land/bubbles/v2 v2.1.0/go.mod h1:l97h4hym2hvWBVfmJDtrEHHCtkIKeTEb3TTJ4ZOB3wY=
charm.land/bubbletea/v2 v2.0.7 h1:7qw2tTAVar7m7klOPBYfTB0mniv/RuexsYwMRNxSeL0=
charm.land/bubbletea/v2 v2.0.7/go.mod h1:DGW2q8gvzHnOpMpZTORs0aySVHCox5C+2Svk0fci1qs=
charm.land/fantasy v0.31.0 h1:ioLVRi7A8lZXR8mrCIeseuCcq0KqAak46revmGumnpc=
charm.land/fantasy v0.31.0/go.mod h1:lAE2gO68SrB1S5TrW5g0TRoxz9V+qJcg0Elx/uPWsDI=
charm.land/fantasy v0.32.0 h1:tlC1qlOdXi2CkF6KB0x8YAAm3hiarI2/69u6pZmOZk8=
charm.land/fantasy v0.32.0/go.mod h1:CWAFEOB21guhmt4qWN9sOnAHkZzVWjKbhxbPHG+oRs8=
charm.land/huh/v2 v2.0.3 h1:2cJsMqEPwSywGHvdlKsJyQKPtSJLVnFKyFbsYZTlLkU=
charm.land/huh/v2 v2.0.3/go.mod h1:93eEveeeqn47MwiC3tf+2atZ2l7Is88rAtmZNZ8x9Wc=
charm.land/lipgloss/v2 v2.0.4 h1:lcPeVtcp23SNra7lHy8iYE4UC2aIipVQ47sbGyyxR5Q=
@@ -28,8 +28,8 @@ github.com/MakeNowJust/heredoc v1.0.0 h1:cXCdzVdstXyiTqTvfqk9SDHpKNjxuom+DOlyEeQ
github.com/MakeNowJust/heredoc v1.0.0/go.mod h1:mG5amYoWBHf8vpLOuehzbGGw0EHxpZZ6lCpQ4fNJ8LE=
github.com/alecthomas/assert/v2 v2.11.0 h1:2Q9r3ki8+JYXvGsDyBXwH3LcJ+WK5D0gc5E8vS6K3D0=
github.com/alecthomas/assert/v2 v2.11.0/go.mod h1:Bze95FyfUr7x34QZrjL+XP+0qgp/zg8yS+TtBj1WA3k=
github.com/alecthomas/chroma/v2 v2.26.1 h1:2X21EdxGZNv5GF9mG5u+uzc02GCFyGxbcBm3Grd9A78=
github.com/alecthomas/chroma/v2 v2.26.1/go.mod h1:lxhRRa9H4hPmRLOOdYga4zkQIQjq3dtrrdwQeCfu78Y=
github.com/alecthomas/chroma/v2 v2.27.0 h1:FodwmyOBgJULFYmDqibcp9pvfDLWdtPRh9v/r5BXYZs=
github.com/alecthomas/chroma/v2 v2.27.0/go.mod h1:NjJ3ciIgrqBNeIkWZ4e46nseoLDslxU1LmfCoL+wcY8=
github.com/alecthomas/repr v0.5.2 h1:SU73FTI9D1P5UNtvseffFSGmdNci/O6RsqzeXJtP0Qs=
github.com/alecthomas/repr v0.5.2/go.mod h1:Fr0507jx4eOXV7AlPV6AVZLYrLIuIeSOWtW57eE/O/4=
github.com/atotto/clipboard v0.1.4 h1:EH0zSVneZPSuFR11BlR9YppQTVDbh5+16AmcJi4g1z4=
@@ -84,8 +84,8 @@ github.com/charmbracelet/lipgloss v1.1.1-0.20250404203927-76690c660834 h1:ZR7e0r
github.com/charmbracelet/lipgloss v1.1.1-0.20250404203927-76690c660834/go.mod h1:aKC/t2arECF6rNOnaKaVU6y4t4ZeHQzqfxedE/VkVhA=
github.com/charmbracelet/log v1.0.0 h1:HVVVMmfOorfj3BA9i8X8UL69Hoz9lI0PYwXfJvOdRc4=
github.com/charmbracelet/log v1.0.0/go.mod h1:uYgY3SmLpwJWxmlrPwXvzVYujxis1vAKRV/0VQB7yWA=
github.com/charmbracelet/openai-go v0.0.0-20260319145158-d0740cc34266 h1:BW/sZtyd1JyYy0h5adMm3tzpNyL857LWjuTRET6OhpY=
github.com/charmbracelet/openai-go v0.0.0-20260319145158-d0740cc34266/go.mod h1:1DahUaExbUZx/jD+FNT2PKP4L9rLE5+ZBRuI8mZjd/E=
github.com/charmbracelet/openai-go v0.0.0-20260617131321-5e4b9c18c4be h1:pg+OWlIkk9HOe/8P5J95aKe2wGDzFUiiyFOUpwR30B4=
github.com/charmbracelet/openai-go v0.0.0-20260617131321-5e4b9c18c4be/go.mod h1:1DahUaExbUZx/jD+FNT2PKP4L9rLE5+ZBRuI8mZjd/E=
github.com/charmbracelet/ultraviolet v0.0.0-20260615092913-2399af76d5b1 h1:4+r3uOJ69ueRBt4okgEfWZeXs3BD36HcDBmOIAUlETk=
github.com/charmbracelet/ultraviolet v0.0.0-20260615092913-2399af76d5b1/go.mod h1:f/jRa757WUmaOZrbPspXymbg/GnbF+rwe4OLsG7aXYo=
github.com/charmbracelet/x/ansi v0.11.7 h1:kzv1kJvjg2S3r9KHo8hDdHFQLEqn4RBCb39dAYC84jI=
@@ -191,8 +191,8 @@ github.com/indaco/herald-md v0.3.0 h1:hN1cKyrexPPM9PeHBsKuaWvIizSi/iYvM9yzRgtdb8
github.com/indaco/herald-md v0.3.0/go.mod h1:RUHVaDSG45ymJjKyxpDwBocLXrZo93FB4OeYMsw9B9s=
github.com/kaptinlin/jsonpointer v0.4.26 h1:tw616yszHek+B3/GtDSia+uzBa3sLXGpmo4tYeMhBZw=
github.com/kaptinlin/jsonpointer v0.4.26/go.mod h1:wVOBaXGGnP42YsMb6zev/3W5POTvspdNfh8DXzf8XS8=
github.com/kaptinlin/jsonschema v0.8.0 h1:GhY966O2q3ZQsg1zkQj988KF2MADJ6EA7pKBMpGmb9A=
github.com/kaptinlin/jsonschema v0.8.0/go.mod h1:dxt7s98W5NEuWEwCnAwGrhYGQdaRLqXZImR28DuxcMU=
github.com/kaptinlin/jsonschema v0.8.1 h1:Krhuq1HpE+olHoPfcxkohqKKCnXfixUPv+aUYRegBBQ=
github.com/kaptinlin/jsonschema v0.8.1/go.mod h1:mCH2W5lXd29tdDjvoFfY32nedPORnlk7pCVrrcs/NkQ=
github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
@@ -201,8 +201,8 @@ github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0
github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=
github.com/lucasb-eyer/go-colorful v1.4.0 h1:UtrWVfLdarDgc44HcS7pYloGHJUjHV/4FwW4TvVgFr4=
github.com/lucasb-eyer/go-colorful v1.4.0/go.mod h1:R4dSotOR9KMtayYi1e77YzuveK+i7ruzyGqttikkLy0=
github.com/mark3labs/mcp-go v0.54.1 h1:Ap/ptEB9FtWzFKM8NDsTA7QDxerQOC06eZigrTldVj0=
github.com/mark3labs/mcp-go v0.54.1/go.mod h1:+8WclSK1ZUweCP3hvktSji8n8ABG/95QaEkeVE/Uwas=
github.com/mark3labs/mcp-go v0.55.0 h1:lJfz2aoctiwK+sI991+uIYwmKNIBciI+O7zsyDsa4U8=
github.com/mark3labs/mcp-go v0.55.0/go.mod h1:+8WclSK1ZUweCP3hvktSji8n8ABG/95QaEkeVE/Uwas=
github.com/mattn/go-isatty v0.0.22 h1:j8l17JJ9i6VGPUFUYoTUKPSgKe/83EYU2zBC7YNKMw4=
github.com/mattn/go-isatty v0.0.22/go.mod h1:ZXfXG4SQHsB/w3ZeOYbR0PrPwLy+n6xiMrJlRFqopa4=
github.com/mattn/go-runewidth v0.0.24 h1:cpokDiIn0MGnhdHwuWnJBITySJ20QyNGnY2kR/ay2DU=
@@ -221,8 +221,8 @@ github.com/muesli/roff v0.1.0 h1:YD0lalCotmYuF5HhZliKWlIx7IEhiXeSfq7hNjFqGF8=
github.com/muesli/roff v0.1.0/go.mod h1:pjAHQM9hdUUwm/krAfrLGgJkXJ+YuhtsfZ42kieB2Ig=
github.com/muesli/termenv v0.16.0 h1:S5AlUN9dENB57rsbnkPyfdGuWIlkmzJjbFf0Tf5FWUc=
github.com/muesli/termenv v0.16.0/go.mod h1:ZRfOIKPFDYQoDFF4Olj7/QJbW60Ol/kL1pU3VfY/Cnk=
github.com/pelletier/go-toml/v2 v2.3.1 h1:MYEvvGnQjeNkRF1qUuGolNtNExTDwct51yp7olPtrEc=
github.com/pelletier/go-toml/v2 v2.3.1/go.mod h1:2gIqNv+qfxSVS7cM2xJQKtLSTLUE9V8t9Stt+h56mCY=
github.com/pelletier/go-toml/v2 v2.4.0 h1:Mwu0mAkUKbittDs3/ADDWXqMmq3EOK2VHiuCkV00Row=
github.com/pelletier/go-toml/v2 v2.4.0/go.mod h1:2gIqNv+qfxSVS7cM2xJQKtLSTLUE9V8t9Stt+h56mCY=
github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c h1:+mdjkGKdHQG3305AYmdv1U2eRNDiU2ErMBj1gwrq8eQ=
github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c/go.mod h1:7rwL4CYBLnjLxUqIJNnCWiEdr3bn6IUYi15bNlnbCCU=
github.com/planetscale/vtprotobuf v0.6.1-0.20240319094008-0393e58bdf10 h1:GFCKgmp0tecUJ0sJuv4pzYCqS9+RGSn52M3FUwPs+uo=
@@ -312,14 +312,14 @@ golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U=
golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno=
gonum.org/v1/gonum v0.17.0 h1:VbpOemQlsSMrYmn7T2OUvQ4dqxQXU+ouZFQsZOx50z4=
gonum.org/v1/gonum v0.17.0/go.mod h1:El3tOrEuMpv2UdMrbNlKEh9vd86bmQ6vqIcDwxEOc1E=
google.golang.org/api v0.284.0 h1:i+cKTgeQRcRySkP7QTl5PDO7/pAm8EcMFIUMlNbk4Vc=
google.golang.org/api v0.284.0/go.mod h1:AU44fU+XVZOCcd8uLaBIa/ZgzgPf/0qqY3+m7lQaado=
google.golang.org/genai v1.60.0 h1:uAkea4tYhCz1LlUmxdiOFAmlrLFaLs8PbXucgZHqHVo=
google.golang.org/genai v1.60.0/go.mod h1:mDdPDFXo1Ats7f1WXVyZgWb/CkMzFWTWJruIMy7hGIU=
google.golang.org/genproto v0.0.0-20260526163538-3dc84a4a5aaa h1:mfj8IS4EA4VAR9a6QDVxTQkLY64iBybb5QI1B4pXrpE=
google.golang.org/genproto v0.0.0-20260526163538-3dc84a4a5aaa/go.mod h1:fuT7yonGw1Iq2oa+YC0fyqPPQJkgo/54gPNC6VitOkI=
google.golang.org/genproto/googleapis/api v0.0.0-20260526163538-3dc84a4a5aaa h1:Kjn0N0tCrDgiAFW+lGO4JZ3ck44CehvJQMAwj9QF0G8=
google.golang.org/genproto/googleapis/api v0.0.0-20260526163538-3dc84a4a5aaa/go.mod h1:q4lMZS6kskjT5HvCPrnnypcDPVJqT/f4nfxmkE7gryY=
google.golang.org/api v0.285.0 h1:B7eHHoKGAX/LrPkQvhQqnGwjgWxofbdGwCTQvpm8FkM=
google.golang.org/api v0.285.0/go.mod h1:NlOlUIr8MPoIhT9Bb/oUnRuHbJOLwxb6JSYJM8Yz+jQ=
google.golang.org/genai v1.61.0 h1:wCyNGiaC9q5A59B80zuEtNBhq3ypEvICFkZYOfK7IO0=
google.golang.org/genai v1.61.0/go.mod h1:mDdPDFXo1Ats7f1WXVyZgWb/CkMzFWTWJruIMy7hGIU=
google.golang.org/genproto v0.0.0-20260610212136-7ab31c22f7ad h1:cYL1DPJAQr4JMvhfGao0PDXoaf03ifMljAuDyrbMBd0=
google.golang.org/genproto v0.0.0-20260610212136-7ab31c22f7ad/go.mod h1:cVHIikDNAdx8ISZeW+2rYkEMf3xn0GSaBYmVnWXQBUo=
google.golang.org/genproto/googleapis/api v0.0.0-20260610212136-7ab31c22f7ad h1:3iLyITS/sySRwbUKoC7ogfj2Yr1Cjs0pfaRKj5U5HEw=
google.golang.org/genproto/googleapis/api v0.0.0-20260610212136-7ab31c22f7ad/go.mod h1:KdNqO+rCIWgFumrNBSEDlDNrkrQnpkax7Tv1WxNY8V4=
google.golang.org/genproto/googleapis/rpc v0.0.0-20260615183401-62b3387ff324 h1:9HZDLIdYBJXAnaFOr9WHrKVycfpY+75s9HGadC0305A=
google.golang.org/genproto/googleapis/rpc v0.0.0-20260615183401-62b3387ff324/go.mod h1:4Hqkh8ycfw05ld/3BWL7rJOSfebL2Q+DVDeRgYgxUU8=
google.golang.org/grpc v1.81.1 h1:VnnIIZ88UzOOKLukQi+ImGz8O1Wdp8nAGGnvOfEIWQQ=
+148 -13
View File
@@ -2,6 +2,7 @@ package app
import (
"context"
"errors"
"fmt"
"log"
"os"
@@ -24,6 +25,26 @@ type queueItem struct {
Files []kit.LLMFilePart
}
// ErrAgentBusy is returned when an operation cannot proceed because the agent
// is still processing a turn (including any post-turn extension hooks) and did
// not become idle before the operation's deadline.
//
// This is an alias for extensions.ErrAgentBusy so the extension API and the
// app layer share a single sentinel value — callers can detect the condition
// with errors.Is(err, app.ErrAgentBusy) without substring-matching the error
// message.
var ErrAgentBusy = extensions.ErrAgentBusy
// DefaultNewSessionIdleWait bounds how long RequestNewSessionFromExtension
// will block waiting for the agent to settle. It needs to be generous enough
// to cover real-world post-turn tooling (project formatters, on-save linters,
// hidden tool calls) which routinely hold the busy flag for seconds and
// occasionally minutes — yet still short enough to surface a wedged agent.
//
// Issue #63 reported workloads where the busy window regularly exceeded
// 6 seconds; ten minutes is the same bound the workaround in that issue used.
const DefaultNewSessionIdleWait = 10 * time.Minute
// App is the application-layer orchestrator. It owns the agentic loop,
// conversation history (via MessageStore), and queue management. It is
// designed to be created once per session and reused across multiple prompts.
@@ -55,11 +76,25 @@ type App struct {
// each new step and called by CancelCurrentStep().
cancelStep context.CancelFunc
// mu protects busy, queue, and cancelStep.
// mu protects busy, queue, cancelStep, and idleCh.
mu sync.Mutex
busy bool
queue []queueItem
// idleCh is closed when the agent transitions from busy back to idle.
// While the agent is idle the channel is already closed (recv returns
// immediately). When busy transitions to true a fresh open channel is
// allocated so callers blocked on the previous one are released. All
// transitions are funnelled through setBusyLocked to keep the channel
// pointer in sync with the busy flag.
//
// This is the underlying primitive WaitForIdle and
// RequestNewSessionFromExtension wait on to fix the AgentEnd→NewSession
// race described in issue #63: AgentEnd is emitted from inside the agent
// loop, before drainQueue clears busy, so any extension hook that calls
// ctx.NewSession synchronously would otherwise observe busy==true.
idleCh chan struct{}
// wg tracks in-flight goroutines; Close() waits on it.
wg sync.WaitGroup
@@ -95,6 +130,10 @@ type App struct {
// initialMessages may be nil or empty for a fresh session.
func New(opts Options, initialMessages []kit.LLMMessage) *App {
rootCtx, rootCancel := context.WithCancel(context.Background())
// idleCh starts already closed: the freshly constructed App is idle, so
// any caller blocking on it via WaitForIdle should be released immediately.
idleCh := make(chan struct{})
close(idleCh)
return &App{
opts: opts,
store: NewMessageStoreWithMessages(initialMessages),
@@ -102,6 +141,90 @@ func New(opts Options, initialMessages []kit.LLMMessage) *App {
rootCancel: rootCancel,
// cancelStep starts as a no-op so CancelCurrentStep() is always safe.
cancelStep: func() {},
idleCh: idleCh,
}
}
// setBusyLocked is the single chokepoint for mutating a.busy. It keeps the
// idleCh signalling channel in sync with the busy flag:
//
// - false → true: allocate a fresh open channel so future WaitForIdle
// callers block until the next idle transition.
// - true → false: close the current channel so any waiters wake up.
//
// No-op when the requested state already matches. The caller must hold a.mu.
func (a *App) setBusyLocked(busy bool) {
if a.busy == busy {
return
}
a.busy = busy
if busy {
a.idleCh = make(chan struct{})
} else {
close(a.idleCh)
}
}
// idleSnapshot returns the current busy state and the channel that will be
// closed on the next idle transition. The snapshot is taken under a.mu so the
// pair is consistent (busy==true ⇒ ch is the open channel for *this* busy
// cycle, not a stale one).
func (a *App) idleSnapshot() (busy bool, ch chan struct{}) {
a.mu.Lock()
defer a.mu.Unlock()
return a.busy, a.idleCh
}
// WaitForIdle blocks until the agent is idle, the given timeout elapses, or
// the app shuts down. Returns nil on idle, ErrAgentBusy on timeout, or the
// rootCtx error if the app is closing.
//
// A non-positive timeout disables the deadline and waits indefinitely (until
// idle or app shutdown). Safe to call from any goroutine, but never from
// inside the Bubble Tea Update() loop — it blocks.
//
// Idiomatic use from extensions:
//
// if err := app.WaitForIdle(0); err != nil { /* shutdown */ }
//
// The loop guards against the agent re-arming itself between wakeups: if
// another prompt is queued (or a steer message lands) while we're waiting,
// setBusyLocked allocates a fresh idleCh and we wait again.
func (a *App) WaitForIdle(timeout time.Duration) error {
var deadline time.Time
if timeout > 0 {
deadline = time.Now().Add(timeout)
}
for {
busy, ch := a.idleSnapshot()
if !busy {
return nil
}
var timer *time.Timer
var timerCh <-chan time.Time
if timeout > 0 {
remaining := time.Until(deadline)
if remaining <= 0 {
return ErrAgentBusy
}
timer = time.NewTimer(remaining)
timerCh = timer.C
}
select {
case <-ch:
// Idle transition observed — loop and re-check under the
// mutex in case a new busy cycle started immediately after.
case <-timerCh:
return ErrAgentBusy
case <-a.rootCtx.Done():
if timer != nil {
timer.Stop()
}
return a.rootCtx.Err()
}
if timer != nil {
timer.Stop()
}
}
}
@@ -155,7 +278,7 @@ func (a *App) RunWithFiles(prompt string, files []kit.LLMFilePart) int {
return qLen
}
a.busy = true
a.setBusyLocked(true)
a.wg.Add(1)
a.mu.Unlock()
go a.drainQueue(item)
@@ -235,7 +358,7 @@ func (a *App) SteerWithFiles(prompt string, files []kit.LLMFilePart) int {
if !a.busy {
// Not busy — start immediately, same as RunWithFiles().
item := queueItem{Prompt: prompt, Files: files}
a.busy = true
a.setBusyLocked(true)
a.wg.Add(1)
a.mu.Unlock()
go a.drainQueue(item)
@@ -271,7 +394,7 @@ func (a *App) InterruptAndSend(prompt string) {
if !a.busy {
// Not busy — start immediately, same as Run().
a.busy = true
a.setBusyLocked(true)
a.wg.Add(1)
a.mu.Unlock()
go a.drainQueue(item)
@@ -470,7 +593,7 @@ func (a *App) CompactConversation(customInstructions string) error {
a.mu.Unlock()
return fmt.Errorf("SDK instance not available")
}
a.busy = true
a.setBusyLocked(true)
a.wg.Add(1)
a.mu.Unlock()
@@ -532,7 +655,7 @@ func (a *App) CompactAsync(customInstructions string, onComplete func(), onError
a.mu.Unlock()
return fmt.Errorf("SDK instance not available")
}
a.busy = true
a.setBusyLocked(true)
a.wg.Add(1)
a.mu.Unlock()
@@ -621,7 +744,7 @@ func (a *App) releaseBusyAfterCompact() {
// in just before closed was set.
if a.closed {
a.queue = a.queue[:0]
a.busy = false
a.setBusyLocked(false)
a.mu.Unlock()
return
}
@@ -633,7 +756,7 @@ func (a *App) releaseBusyAfterCompact() {
a.queue = a.queue[:0]
if len(pending) == 0 {
a.busy = false
a.setBusyLocked(false)
a.mu.Unlock()
return
}
@@ -850,7 +973,7 @@ func (a *App) drainQueue(first queueItem) {
// Mark as no longer busy
a.mu.Lock()
a.busy = false
a.setBusyLocked(false)
a.mu.Unlock()
}
@@ -1233,8 +1356,17 @@ func (a *App) SetEditorTextFromExtension(text string) {
// RequestNewSessionFromExtension sends a NewSessionRequestEvent to the TUI
// to end the current session and start a fresh one. If initialPrompt is
// non-empty it is submitted as the first user turn of the new session.
// Returns an error when running headless (no TUI attached), when the agent
// is busy, or when a BeforeSessionSwitch extension hook cancels the switch.
//
// If the agent is currently busy (e.g. the caller is an OnAgentEnd hook that
// fires before drainQueue clears the busy flag, or there are queued prompts
// still being processed) the call blocks until the agent becomes idle, up to
// DefaultNewSessionIdleWait. If that deadline elapses, ErrAgentBusy is
// returned and callers can detect it with errors.Is. This wait-then-send
// behavior fixes the v0.79.0 phase-handoff race documented in issue #63.
//
// Returns an error when running headless (no TUI attached), when the wait
// for idle times out (ErrAgentBusy), when the app is shutting down, or when
// a BeforeSessionSwitch extension hook cancels the switch.
//
// This is the implementation behind ctx.NewSession(prompt) for the
// interactive TUI. It blocks the caller until the TUI processes the
@@ -1246,8 +1378,11 @@ func (a *App) RequestNewSessionFromExtension(initialPrompt string) error {
if prog == nil {
return fmt.Errorf("new session unavailable: no interactive TUI attached")
}
if a.IsBusy() {
return fmt.Errorf("cannot start new session while agent is busy")
if err := a.WaitForIdle(DefaultNewSessionIdleWait); err != nil {
if errors.Is(err, ErrAgentBusy) {
return fmt.Errorf("cannot start new session: %w", err)
}
return err
}
ch := make(chan error, 1)
prog.Send(NewSessionRequestEvent{InitialPrompt: initialPrompt, ResponseCh: ch})
+283 -5
View File
@@ -794,7 +794,7 @@ func TestReleaseBusyAfterCompact_flushesQueuedMessages(t *testing.T) {
// summarising. (Run() would have appended them and returned a queue
// length > 0 to the caller.)
app.mu.Lock()
app.busy = true
app.setBusyLocked(true)
app.queue = append(app.queue,
queueItem{Prompt: "queued during compact #1"},
queueItem{Prompt: "queued during compact #2"},
@@ -834,7 +834,7 @@ func TestReleaseBusyAfterCompact_idleWhenQueueEmpty(t *testing.T) {
defer app.Close()
app.mu.Lock()
app.busy = true
app.setBusyLocked(true)
app.mu.Unlock()
app.releaseBusyAfterCompact()
@@ -901,7 +901,7 @@ func TestReleaseBusyAfterCompact_splicesSteerAheadOfQueue(t *testing.T) {
// Simulate the state at the end of compaction: busy is set and a couple
// of regular Run() prompts have piled up after the steer messages.
app.mu.Lock()
app.busy = true
app.setBusyLocked(true)
app.queue = append(app.queue,
queueItem{Prompt: "queued-1"},
queueItem{Prompt: "queued-2"},
@@ -950,7 +950,7 @@ func TestReleaseBusyAfterCompact_dropsQueueWhenClosed(t *testing.T) {
app := newTestApp(stub)
app.mu.Lock()
app.busy = true
app.setBusyLocked(true)
app.queue = append(app.queue, queueItem{Prompt: "would have run"})
app.closed = true
app.mu.Unlock()
@@ -999,7 +999,7 @@ func TestPopLastUserMessage_WhileBusy(t *testing.T) {
defer app.Close()
app.mu.Lock()
app.busy = true
app.setBusyLocked(true)
app.mu.Unlock()
_, _, err := app.PopLastUserMessage()
@@ -1115,3 +1115,281 @@ func TestPopLastUserMessage_NoUserOnBranch(t *testing.T) {
t.Fatalf("expected error mentioning missing user message, got %q", err.Error())
}
}
// --------------------------------------------------------------------------
// WaitForIdle / RequestNewSessionFromExtension (issue #63)
// --------------------------------------------------------------------------
// TestWaitForIdle_AlreadyIdle verifies the fast path: a freshly constructed
// App is idle and WaitForIdle returns immediately without consulting the
// timeout.
func TestWaitForIdle_AlreadyIdle(t *testing.T) {
app := newTestApp(newStub())
defer app.Close()
start := time.Now()
if err := app.WaitForIdle(2 * time.Second); err != nil {
t.Fatalf("WaitForIdle on idle app: %v", err)
}
if elapsed := time.Since(start); elapsed > 100*time.Millisecond {
t.Fatalf("WaitForIdle blocked for %s on already-idle app", elapsed)
}
}
// TestWaitForIdle_BlocksUntilDrain reproduces the issue #63 race: while
// drainQueue holds busy==true the call should block, then return nil as soon
// as the drain completes.
func TestWaitForIdle_BlocksUntilDrain(t *testing.T) {
gate := make(chan struct{})
var gateOnce sync.Once
closeGate := func() { gateOnce.Do(func() { close(gate) }) }
stub := newStubWithFuncs(
func(ctx context.Context) (*kit.TurnResult, error) {
select {
case <-gate:
case <-ctx.Done():
return nil, ctx.Err()
}
return turnResult("done"), nil
},
)
app := newTestApp(stub)
t.Cleanup(func() {
closeGate()
app.Close()
})
app.Run("hello")
// Confirm the agent is busy before we start waiting.
if !waitForCondition(2*time.Second, func() bool { return app.IsBusy() }) {
t.Fatal("app never became busy after Run()")
}
errCh := make(chan error, 1)
go func() {
errCh <- app.WaitForIdle(5 * time.Second)
}()
// Should not return while the stub is blocked.
select {
case err := <-errCh:
t.Fatalf("WaitForIdle returned early (err=%v) while agent still busy", err)
case <-time.After(150 * time.Millisecond):
}
closeGate()
select {
case err := <-errCh:
if err != nil {
t.Fatalf("WaitForIdle: %v", err)
}
case <-time.After(3 * time.Second):
t.Fatal("WaitForIdle did not return after drain completed")
}
if app.IsBusy() {
t.Fatal("app still reports busy after WaitForIdle returned")
}
}
// TestWaitForIdle_TimeoutReturnsErrAgentBusy verifies that a slow turn yields
// ErrAgentBusy (detectable via errors.Is) when the deadline elapses.
func TestWaitForIdle_TimeoutReturnsErrAgentBusy(t *testing.T) {
gate := make(chan struct{})
stub := newStubWithFuncs(
func(ctx context.Context) (*kit.TurnResult, error) {
select {
case <-gate:
case <-ctx.Done():
return nil, ctx.Err()
}
return turnResult("done"), nil
},
)
app := newTestApp(stub)
// Release the stub before Close so wg.Wait() can return.
t.Cleanup(func() {
close(gate)
app.Close()
})
app.Run("hello")
if !waitForCondition(2*time.Second, func() bool { return app.IsBusy() }) {
t.Fatal("app never became busy after Run()")
}
err := app.WaitForIdle(50 * time.Millisecond)
if !errors.Is(err, ErrAgentBusy) {
t.Fatalf("expected ErrAgentBusy on timeout, got %v", err)
}
}
// TestWaitForIdle_ZeroTimeoutWaitsIndefinitely verifies that a non-positive
// timeout still blocks until idle (or shutdown) — not an instant ErrAgentBusy.
func TestWaitForIdle_ZeroTimeoutWaitsIndefinitely(t *testing.T) {
gate := make(chan struct{})
var gateOnce sync.Once
closeGate := func() { gateOnce.Do(func() { close(gate) }) }
stub := newStubWithFuncs(
func(ctx context.Context) (*kit.TurnResult, error) {
select {
case <-gate:
case <-ctx.Done():
return nil, ctx.Err()
}
return turnResult("done"), nil
},
)
app := newTestApp(stub)
t.Cleanup(func() {
closeGate()
app.Close()
})
app.Run("hello")
if !waitForCondition(2*time.Second, func() bool { return app.IsBusy() }) {
t.Fatal("app never became busy after Run()")
}
errCh := make(chan error, 1)
go func() { errCh <- app.WaitForIdle(0) }()
select {
case err := <-errCh:
t.Fatalf("WaitForIdle(0) returned early with %v while agent was busy", err)
case <-time.After(150 * time.Millisecond):
}
closeGate()
select {
case err := <-errCh:
if err != nil {
t.Fatalf("WaitForIdle(0) returned %v after idle", err)
}
case <-time.After(3 * time.Second):
t.Fatal("WaitForIdle(0) did not return after drain completed")
}
}
// TestWaitForIdle_AppClose verifies that shutting down the app while a
// caller is blocked in WaitForIdle releases the wait.
func TestWaitForIdle_AppClose(t *testing.T) {
gate := make(chan struct{})
stub := newStubWithFuncs(
func(ctx context.Context) (*kit.TurnResult, error) {
select {
case <-gate:
case <-ctx.Done():
return nil, ctx.Err()
}
return turnResult("done"), nil
},
)
app := newTestApp(stub)
app.Run("hello")
if !waitForCondition(2*time.Second, func() bool { return app.IsBusy() }) {
t.Fatal("app never became busy after Run()")
}
errCh := make(chan error, 1)
go func() { errCh <- app.WaitForIdle(5 * time.Second) }()
// Give the goroutine a moment to enter the wait.
time.Sleep(50 * time.Millisecond)
// rootCancel is called by Close, which should release the waiter
// before drainQueue itself observes the cancellation and clears busy.
go func() {
// Unblock the stub so Close() can proceed past wg.Wait().
close(gate)
}()
app.Close()
select {
case err := <-errCh:
// Either rootCtx cancellation propagated first (err = context.Canceled)
// or the drain finished cleanly first (err == nil); both are
// acceptable terminations. The key invariant is that WaitForIdle
// does not hang past Close.
if err != nil && !errors.Is(err, context.Canceled) {
t.Fatalf("WaitForIdle returned unexpected error: %v", err)
}
case <-time.After(3 * time.Second):
t.Fatal("WaitForIdle did not return after Close()")
}
}
// TestRequestNewSessionFromExtension_NoTUI verifies the headless guard: with
// no Bubble Tea program registered the call fails fast (no busy-wait).
func TestRequestNewSessionFromExtension_NoTUI(t *testing.T) {
app := newTestApp(newStub())
defer app.Close()
err := app.RequestNewSessionFromExtension("hello")
if err == nil {
t.Fatal("expected error in headless mode")
}
if !strings.Contains(err.Error(), "no interactive TUI") {
t.Fatalf("expected 'no interactive TUI' error, got %q", err.Error())
}
}
// TestBusyTransitionsSignalIdleCh exercises the setBusyLocked invariants
// directly: a fresh App is idle (closed channel); Run() opens a new channel
// that is then closed when drainQueue exits.
func TestBusyTransitionsSignalIdleCh(t *testing.T) {
app := newTestApp(newStub("ok"))
defer app.Close()
// Initial state: closed channel, busy==false.
busy, ch := app.idleSnapshot()
if busy {
t.Fatal("freshly constructed App should not be busy")
}
select {
case <-ch:
default:
t.Fatal("initial idleCh should already be closed")
}
gate := make(chan struct{})
var gateOnce sync.Once
closeGate := func() { gateOnce.Do(func() { close(gate) }) }
stub := newStubWithFuncs(func(ctx context.Context) (*kit.TurnResult, error) {
select {
case <-gate:
case <-ctx.Done():
return nil, ctx.Err()
}
return turnResult("ok"), nil
})
app2 := newTestApp(stub)
t.Cleanup(func() {
closeGate()
app2.Close()
})
app2.Run("hello")
if !waitForCondition(2*time.Second, func() bool { return app2.IsBusy() }) {
t.Fatal("app2 never became busy")
}
_, ch2 := app2.idleSnapshot()
select {
case <-ch2:
t.Fatal("idleCh should be open while busy")
default:
}
closeGate()
select {
case <-ch2:
case <-time.After(3 * time.Second):
t.Fatal("idleCh was never closed after drain completed")
}
}
+40 -5
View File
@@ -1,5 +1,24 @@
package extensions
import (
"errors"
)
// ErrAgentBusy is returned (wrapped) when an extension API call that requires
// the agent to be idle cannot proceed because the agent is still processing a
// turn or post-turn hooks. Most notably, ctx.NewSession waits for idle
// internally; if its wait deadline elapses it returns an error that wraps
// this sentinel.
//
// Extensions can detect the condition with errors.Is:
//
// if err := ctx.NewSession(prompt); err != nil {
// if errors.Is(err, ext.ErrAgentBusy) {
// // agent never settled — fall back to a queued message instead
// }
// }
var ErrAgentBusy = errors.New("agent is busy")
// ---------------------------------------------------------------------------
// Internal types (used by runner, NOT exposed to Yaegi)
// ---------------------------------------------------------------------------
@@ -130,10 +149,24 @@ type Context struct {
// expanded the same way they are for normal user input. Pass an empty
// string to start an empty session.
//
// Returns an error if the agent is currently busy, if a registered
// BeforeSessionSwitch handler cancels the switch, or if the new
// session file cannot be created. In non-interactive (ACP / headless)
// mode this is a no-op that returns an error.
// If the agent is currently busy when NewSession is called (for example,
// from an OnAgentEnd hook that fires before the agent fully settles, or
// while post-turn formatters/linters are still running), the call blocks
// until the agent transitions to idle. This avoids the v0.79.0
// phase-handoff race where NewSession from OnAgentEnd would fail with
// "agent is busy" because TurnEnd fires before the busy flag clears.
// The wait has a generous internal timeout; if it elapses the returned
// error wraps ErrAgentBusy (detectable with errors.Is).
//
// Returns an error if the agent does not become idle within the wait
// window, if a registered BeforeSessionSwitch handler cancels the
// switch, or if the new session file cannot be created. In
// non-interactive (ACP / headless) mode this is a no-op that returns
// an error.
//
// Because NewSession may block, call it from a goroutine — not
// directly from inside an event handler that the agent loop is waiting
// on.
//
// Typical pattern — start a fresh session at the end of a phase by
// reading a handoff file:
@@ -145,7 +178,9 @@ type Context struct {
// }
// last := msgs[len(msgs)-1].Content
// if strings.Contains(last, "<HANDOFF_READY>") {
// _ = ctx.NewSession("Read @HANDOFF.md and continue the next phase.")
// go func() {
// _ = ctx.NewSession("Read @HANDOFF.md and continue the next phase.")
// }()
// }
// })
NewSession func(prompt string) error
+5
View File
@@ -28,6 +28,11 @@ func Symbols() interp.Exports {
"CommandDef": reflect.ValueOf((*CommandDef)(nil)),
"PrintBlockOpts": reflect.ValueOf((*PrintBlockOpts)(nil)),
// Sentinel errors. Extensions detect them with errors.Is:
//
// if errors.Is(err, ext.ErrAgentBusy) { ... }
"ErrAgentBusy": reflect.ValueOf(&ErrAgentBusy).Elem(),
// Session types
"SessionMessage": reflect.ValueOf((*SessionMessage)(nil)),
"ExtensionEntry": reflect.ValueOf((*ExtensionEntry)(nil)),
+11 -1
View File
@@ -53,6 +53,11 @@ type AgentSetupOptions struct {
// Debug enables debug logging. When zero-value, viper is consulted.
// Only meaningful when ProviderConfig is also set.
Debug bool
// DebugLogger, if non-nil, is used directly as the engine/MCP debug
// logger — overriding the built-in SimpleDebugLogger / BufferedDebugLogger
// selected by Debug + UseBufferedLogger. Callers supply this when they
// want to route debug output into their own logging system.
DebugLogger tools.DebugLogger
// NoExtensions skips extension loading. When false, viper is consulted.
// Only meaningful when ProviderConfig is also set.
NoExtensions bool
@@ -192,7 +197,12 @@ func SetupAgent(ctx context.Context, opts AgentSetupOptions) (*AgentSetupResult,
// Create the appropriate debug logger.
var debugLogger tools.DebugLogger
var bufferedLogger *tools.BufferedDebugLogger
if debugEnabled {
switch {
case opts.DebugLogger != nil:
// Caller-supplied logger wins unconditionally. Its IsDebugEnabled()
// is the source of truth for whether downstream code emits messages.
debugLogger = opts.DebugLogger
case debugEnabled:
if opts.UseBufferedLogger {
bufferedLogger = tools.NewBufferedDebugLogger(true)
debugLogger = bufferedLogger
File diff suppressed because one or more lines are too long
+4 -3
View File
@@ -74,7 +74,8 @@ host, err := kit.NewAgent(ctx,
Helpers: `WithModel`, `WithSystemPrompt`, `WithStreaming`, `WithMaxTokens`,
`WithThinkingLevel`, `WithTools`, `WithExtraTools`, `WithProviderAPIKey`,
`WithProviderURL`, `WithConfigFile`, `WithDebug`, and `Ephemeral`. `Option` is
`WithProviderURL`, `WithConfigFile`, `WithDebug`, `WithDebugLogger`, and
`Ephemeral`. `Option` is
a plain `func(*Options)`, so you can define your own. For fields without a
`With*` helper (`MCPConfig`, `InProcessMCPServers`, `SessionManager`, MCP task
tuning) construct an `Options` value and call `kit.New`.
@@ -329,7 +330,6 @@ kit.LLMFilePart // {Filename, Data []byte, MediaType}
// Agent configuration — concrete Kit-owned structs and function types.
// All fields use SDK types (e.g. `[]kit.Tool`), so consumers can construct
// these without importing any LLM-provider package.
kit.AgentConfig // Lower-level agent config — prefer Options unless you need direct control
kit.DebugLogger // Interface: LogDebug(string) / IsDebugEnabled() bool
kit.MCPTaskConfig // Task-aware MCP tools/call config (modes, polling, progress)
kit.ToolCallHandler // func(toolCallID, toolName, toolArgs string)
@@ -403,7 +403,8 @@ Key `Options` fields for SDK usage:
| `SessionPath` | Open specific session file |
| `Continue` | Resume most recent session |
| `InProcessMCPServers` | Map of name → `*kit.MCPServer` for in-process MCP servers |
| `Debug` | Enable debug logging |
| `Debug` | Enable debug logging via the built-in console logger (ignored when `DebugLogger` is set) |
| `DebugLogger` | Custom `DebugLogger` implementation — routes engine + MCP debug output into your own logging system |
## Environment Variables
-208
View File
@@ -1,208 +0,0 @@
package kit
import (
"context"
"errors"
"testing"
"time"
"github.com/mark3labs/kit/internal/agent"
)
// TestAgentConfigToInternal verifies that the SDK-side AgentConfig converts
// faithfully to the internal agent.AgentConfig representation, preserving
// every field consumed by the internal agent layer.
//
// Regression test for https://github.com/mark3labs/kit/issues/30.
func TestAgentConfigToInternal(t *testing.T) {
t.Run("nil receiver returns nil", func(t *testing.T) {
var c *AgentConfig
if got := c.toInternal(); got != nil {
t.Errorf("nil.toInternal() = %v, want nil", got)
}
})
t.Run("scalar fields round-trip", func(t *testing.T) {
c := &AgentConfig{
SystemPrompt: "sys",
MaxSteps: 7,
StreamingEnabled: true,
DisableCoreTools: true,
}
got := c.toInternal()
if got == nil {
t.Fatal("toInternal() = nil")
}
if got.SystemPrompt != "sys" {
t.Errorf("SystemPrompt = %q, want %q", got.SystemPrompt, "sys")
}
if got.MaxSteps != 7 {
t.Errorf("MaxSteps = %d, want 7", got.MaxSteps)
}
if !got.StreamingEnabled {
t.Error("StreamingEnabled = false, want true")
}
if !got.DisableCoreTools {
t.Error("DisableCoreTools = false, want true")
}
})
t.Run("tool slices propagate without conversion", func(t *testing.T) {
// Tool is a type alias for the underlying LLM-tool type, so the
// SDK []Tool and internal []fantasy.AgentTool slices share the
// same backing array after conversion.
tool := NewTool[struct{}]("noop", "noop", nil)
c := &AgentConfig{
CoreTools: []Tool{tool},
ExtraTools: []Tool{tool, tool},
}
got := c.toInternal()
if len(got.CoreTools) != 1 {
t.Errorf("CoreTools len = %d, want 1", len(got.CoreTools))
}
if len(got.ExtraTools) != 2 {
t.Errorf("ExtraTools len = %d, want 2", len(got.ExtraTools))
}
})
t.Run("tool wrapper is invoked through internal config", func(t *testing.T) {
called := false
c := &AgentConfig{
ToolWrapper: func(in []Tool) []Tool {
called = true
return in
},
}
got := c.toInternal()
if got.ToolWrapper == nil {
t.Fatal("internal ToolWrapper is nil")
}
_ = got.ToolWrapper(nil)
if !called {
t.Error("SDK ToolWrapper was not invoked through the internal config")
}
})
t.Run("OnMCPServerLoaded propagates", func(t *testing.T) {
var captured string
wantErr := errors.New("boom")
c := &AgentConfig{
OnMCPServerLoaded: func(name string, _ int, _ error) {
captured = name
},
}
got := c.toInternal()
got.OnMCPServerLoaded("svr", 3, wantErr)
if captured != "svr" {
t.Errorf("OnMCPServerLoaded captured = %q, want %q", captured, "svr")
}
})
t.Run("DebugLogger propagates", func(t *testing.T) {
dl := &fakeDebugLogger{enabled: true}
c := &AgentConfig{DebugLogger: dl}
got := c.toInternal()
if got.DebugLogger == nil {
t.Fatal("internal DebugLogger is nil")
}
if !got.DebugLogger.IsDebugEnabled() {
t.Error("IsDebugEnabled = false, want true")
}
got.DebugLogger.LogDebug("hello")
if len(dl.messages) != 1 || dl.messages[0] != "hello" {
t.Errorf("messages = %v, want [hello]", dl.messages)
}
})
t.Run("MCPTaskConfig propagates with mode + progress", func(t *testing.T) {
c := &AgentConfig{
MCPTaskConfig: MCPTaskConfig{
PerServerMode: map[string]MCPTaskMode{
"build-svr": MCPTaskModeAlways,
},
DefaultTTL: 30 * time.Second,
PollInterval: 250 * time.Millisecond,
MaxPollInterval: 2 * time.Second,
Timeout: 5 * time.Minute,
Progress: func(_ MCPTaskProgress) {},
},
}
got := c.toInternal()
if got.MCPTaskConfig.DefaultTTL != 30*time.Second {
t.Errorf("DefaultTTL = %v, want 30s", got.MCPTaskConfig.DefaultTTL)
}
if got.MCPTaskConfig.PollInterval != 250*time.Millisecond {
t.Errorf("PollInterval = %v, want 250ms", got.MCPTaskConfig.PollInterval)
}
if got.MCPTaskConfig.MaxPollInterval != 2*time.Second {
t.Errorf("MaxPollInterval = %v, want 2s", got.MCPTaskConfig.MaxPollInterval)
}
if got.MCPTaskConfig.Timeout != 5*time.Minute {
t.Errorf("Timeout = %v, want 5m", got.MCPTaskConfig.Timeout)
}
mode, ok := got.MCPTaskConfig.PerServerMode["build-svr"]
if !ok {
t.Fatal("PerServerMode missing 'build-svr'")
}
if string(mode) != string(MCPTaskModeAlways) {
t.Errorf("mode = %q, want %q", mode, MCPTaskModeAlways)
}
if got.MCPTaskConfig.Progress == nil {
t.Fatal("internal Progress handler is nil")
}
})
t.Run("auth and token store factories are wired", func(t *testing.T) {
auth := &fakeAuthHandler{}
tokenCalls := 0
var tokenServer string
factory := MCPTokenStoreFactory(func(server string) (MCPTokenStore, error) {
tokenCalls++
tokenServer = server
return nil, nil
})
c := &AgentConfig{
AuthHandler: auth,
TokenStoreFactory: factory,
}
got := c.toInternal()
if got.AuthHandler == nil {
t.Fatal("internal AuthHandler is nil")
}
if got.TokenStoreFactory == nil {
t.Fatal("internal TokenStoreFactory is nil")
}
_, _ = got.TokenStoreFactory("https://example.test")
if tokenCalls != 1 {
t.Errorf("token factory call count = %d, want 1", tokenCalls)
}
if tokenServer != "https://example.test" {
t.Errorf("token factory server arg = %q", tokenServer)
}
if got.AuthHandler.RedirectURI() != "redirect" {
t.Errorf("RedirectURI = %q, want %q", got.AuthHandler.RedirectURI(), "redirect")
}
})
// Compile-time check that the internal type is what we expect.
//nolint:staticcheck // QF1011: explicit type asserts the conversion target.
var _ *agent.AgentConfig = (&AgentConfig{}).toInternal()
}
// fakeAuthHandler implements both kit.MCPAuthHandler and the structurally
// identical tools.MCPAuthHandler used by the internal layer.
type fakeAuthHandler struct{}
func (f *fakeAuthHandler) RedirectURI() string { return "redirect" }
func (f *fakeAuthHandler) HandleAuth(_ context.Context, _ string, _ string) (string, error) {
return "", nil
}
// fakeDebugLogger implements kit.DebugLogger for tests.
type fakeDebugLogger struct {
enabled bool
messages []string
}
func (f *fakeDebugLogger) LogDebug(m string) { f.messages = append(f.messages, m) }
func (f *fakeDebugLogger) IsDebugEnabled() bool { return f.enabled }
+18 -1
View File
@@ -1047,9 +1047,25 @@ type Options struct {
AutoCompact bool // Auto-compact when near context limit
CompactionOptions *CompactionOptions // Config for auto-compaction (nil = defaults)
// Debug enables debug logging for the SDK.
// Debug enables debug logging for the SDK. When DebugLogger is nil this
// flag selects between the default no-op SimpleDebugLogger (Debug=false)
// and the built-in console/buffered logger (Debug=true). When DebugLogger
// is non-nil this flag is ignored — the supplied logger's
// IsDebugEnabled() controls whether downstream code emits messages.
Debug bool
// DebugLogger, if non-nil, routes low-level debug output from the engine
// and the MCP tool plumbing to a caller-supplied implementation. This is
// the SDK escape hatch for embedders that want to forward debug output
// into their own logging system (zap, slog, log/charm, an in-app TUI
// panel, etc.) instead of the built-in console logger.
//
// When nil (default) the Debug bool controls whether the built-in logger
// is installed. When non-nil this logger is used unconditionally and the
// Debug bool is ignored; the supplied logger's IsDebugEnabled() reports
// whether downstream code should bother formatting messages.
DebugLogger DebugLogger
// MCPAuthHandler handles OAuth authorization for remote MCP servers.
// When set, remote transports (streamable HTTP, SSE) are configured
// with OAuth support. If the server returns a 401, the handler is
@@ -1514,6 +1530,7 @@ func New(ctx context.Context, opts *Options) (*Kit, error) {
ToolWrapper: hookToolWrapper(beforeToolCall, afterToolResult),
ProviderConfig: providerConfig,
Debug: debug,
DebugLogger: opts.DebugLogger,
NoExtensions: noExtensions,
MaxSteps: maxSteps,
StreamingEnabled: streaming,
+5 -33
View File
@@ -102,10 +102,11 @@ type MCPTaskProgressHandler func(MCPTaskProgress)
// are optional; the zero value disables progress callbacks and applies
// sensible polling defaults inside the engine.
//
// For most consumers, the flat [Options] fields (`MCPTaskMode`,
// `MCPTaskTTL`, `MCPTaskPollInterval`, `MCPTaskMaxPollInterval`,
// `MCPTaskTimeout`, `MCPTaskProgress`) are the preferred entry point.
// MCPTaskConfig is exposed for the low-level [AgentConfig] path.
// Most consumers configure these via the flat [Options] fields
// (`MCPTaskMode`, `MCPTaskTTL`, `MCPTaskPollInterval`,
// `MCPTaskMaxPollInterval`, `MCPTaskTimeout`, `MCPTaskProgress`). The
// MCPTaskConfig type itself is retained for downstream consumers that
// receive it on engine-facing call sites.
type MCPTaskConfig struct {
// PerServerMode overrides the per-server task mode resolved from
// [MCPServerConfig]. Keys are server names. Missing entries fall back
@@ -133,35 +134,6 @@ type MCPTaskConfig struct {
Progress MCPTaskProgressHandler
}
// toToolsConfig converts the SDK-level [MCPTaskConfig] to the internal
// tools-package representation. Keeps the dependency arrow internal-only.
func (c MCPTaskConfig) toToolsConfig() tools.MCPTaskConfig {
cfg := tools.MCPTaskConfig{
DefaultTTL: c.DefaultTTL,
PollInterval: c.PollInterval,
MaxPollInterval: c.MaxPollInterval,
Timeout: c.Timeout,
}
if len(c.PerServerMode) > 0 {
cfg.PerServerMode = make(map[string]tools.MCPTaskMode, len(c.PerServerMode))
for k, v := range c.PerServerMode {
cfg.PerServerMode[k] = tools.MCPTaskMode(v)
}
}
if c.Progress != nil {
h := c.Progress
cfg.Progress = func(p tools.MCPTaskProgress) {
h(MCPTaskProgress{
Server: p.Server,
TaskID: p.TaskID,
Status: MCPTaskStatus(p.Status),
Message: p.Message,
})
}
}
return cfg
}
// mcpTaskOptions carries SDK consumer configuration into the agent setup.
// Stored on Options as a single value so the public surface stays compact;
// individual fields are exposed via WithMCP* builder functions.
+11
View File
@@ -83,6 +83,17 @@ func WithConfigFile(path string) Option { return func(o *Options) { o.ConfigFile
// WithDebug enables SDK debug logging.
func WithDebug() Option { return func(o *Options) { o.Debug = true } }
// WithDebugLogger installs a caller-supplied [DebugLogger] for low-level
// engine and MCP tool plumbing output. When set this overrides the built-in
// logger selected by [WithDebug] — messages flow into the supplied logger
// unconditionally, and the logger's IsDebugEnabled reports whether downstream
// code should bother formatting them. Use this to forward Kit's debug output
// into your application's logging system (slog, zap, charm/log, an in-app
// panel, etc.).
func WithDebugLogger(l DebugLogger) Option {
return func(o *Options) { o.DebugLogger = l }
}
// Ephemeral configures an in-memory session with no persistence (equivalent to
// Options.NoSession = true).
func Ephemeral() Option { return func(o *Options) { o.NoSession = true } }
+4 -108
View File
@@ -5,13 +5,11 @@ import (
"charm.land/fantasy"
"github.com/mark3labs/kit/internal/agent"
"github.com/mark3labs/kit/internal/compaction"
"github.com/mark3labs/kit/internal/config"
"github.com/mark3labs/kit/internal/message"
"github.com/mark3labs/kit/internal/models"
"github.com/mark3labs/kit/internal/session"
"github.com/mark3labs/kit/internal/tools"
"github.com/mark3labs/mcp-go/client/transport"
"github.com/mark3labs/mcp-go/server"
)
@@ -83,9 +81,10 @@ type MCPServerConfig = config.MCPServerConfig
// concurrent use.
//
// Most consumers do not need to provide one; pass [Options.Debug] = true
// to use the default logger. DebugLogger is exposed for the low-level
// [AgentConfig] path and for embedders that want to route debug output
// into their own logging system.
// (or use [WithDebug]) to install the built-in console logger. DebugLogger
// is the escape hatch for embedders that want to route debug output into
// their own logging system — install one via [Options.DebugLogger] or
// [WithDebugLogger].
type DebugLogger interface {
// LogDebug records a single debug message. Implementations may drop,
// buffer, or render the message however they choose.
@@ -95,109 +94,6 @@ type DebugLogger interface {
IsDebugEnabled() bool
}
// AgentConfig holds configuration options for constructing an agent at the
// SDK boundary. All fields use SDK-owned types, so consumers can populate
// this struct without importing any underlying LLM-provider package.
//
// For most use cases, prefer the high-level [New] entry point with
// [Options]. AgentConfig is exposed for advanced consumers that need
// direct access to the lower-level agent configuration shape.
type AgentConfig struct {
// ModelConfig holds the LLM provider configuration. A nil value means
// that the default provider/model resolution will be used.
ModelConfig *ProviderConfig
// MCPConfig describes any MCP servers whose tools should be loaded
// alongside core tools.
MCPConfig *Config
// SystemPrompt is the system prompt sent to the LLM.
SystemPrompt string
// MaxSteps caps the number of LLM iterations per turn. A value of
// zero means no cap is applied at this layer.
MaxSteps int
// StreamingEnabled controls whether the agent streams responses.
StreamingEnabled bool
// AuthHandler handles OAuth authorization for remote MCP servers.
// When nil, remote MCP servers requiring OAuth will fail to connect.
AuthHandler MCPAuthHandler
// TokenStoreFactory, if non-nil, creates a custom token store for each
// remote MCP server's OAuth tokens. When nil, the default file-based
// token store is used.
TokenStoreFactory MCPTokenStoreFactory
// CoreTools overrides the default core tool set. If empty, [AllTools]
// is used. Provide a custom tool set (e.g. [CodingTools] or tools
// built with a custom WorkDir) to scope agent capabilities.
CoreTools []Tool
// DisableCoreTools, when true, prevents loading any core tools.
// Combined with empty CoreTools this yields a chat-only agent with
// no built-in tools.
DisableCoreTools bool
// ExtraTools are additional tools loaded alongside core and MCP tools.
ExtraTools []Tool
// ToolWrapper, if non-nil, wraps the combined tool list before it is
// handed to the LLM. Used to intercept tool calls or results.
ToolWrapper func([]Tool) []Tool
// OnMCPServerLoaded, if non-nil, is invoked once for each MCP server
// when its tools have finished loading (or failed). Called from a
// background goroutine.
OnMCPServerLoaded func(serverName string, toolCount int, err error)
// DebugLogger receives low-level debug output from the engine and the
// MCP tool plumbing. Nil means no debug output is emitted at this
// layer (regardless of [Options.Debug], which feeds the higher-level
// [New] entry point). Pass an implementation here when wiring a custom
// logger through the lower-level AgentConfig path.
DebugLogger DebugLogger
// MCPTaskConfig configures task-aware MCP tools/call execution — mode
// overrides, polling intervals, timeouts, and the progress handler.
// The zero value preserves historical synchronous-only behaviour for
// any server that didn't advertise task support during initialize.
MCPTaskConfig MCPTaskConfig
}
// toInternal converts an AgentConfig to its internal representation.
// Slice and function fields convert without allocation because [Tool]
// is a type alias for the underlying LLM-tool type.
func (c *AgentConfig) toInternal() *agent.AgentConfig {
if c == nil {
return nil
}
out := &agent.AgentConfig{
ModelConfig: c.ModelConfig,
MCPConfig: c.MCPConfig,
SystemPrompt: c.SystemPrompt,
MaxSteps: c.MaxSteps,
StreamingEnabled: c.StreamingEnabled,
CoreTools: c.CoreTools,
DisableCoreTools: c.DisableCoreTools,
ExtraTools: c.ExtraTools,
ToolWrapper: c.ToolWrapper,
OnMCPServerLoaded: c.OnMCPServerLoaded,
}
if c.AuthHandler != nil {
out.AuthHandler = c.AuthHandler
}
if c.TokenStoreFactory != nil {
out.TokenStoreFactory = tools.TokenStoreFactory(c.TokenStoreFactory)
}
if c.DebugLogger != nil {
out.DebugLogger = c.DebugLogger
}
out.MCPTaskConfig = c.MCPTaskConfig.toToolsConfig()
return out
}
// ToolCallHandler is invoked when the LLM produces a tool call. It receives
// the call ID, tool name, and the JSON-encoded input arguments.
type ToolCallHandler func(toolCallID, toolName, toolArgs string)
+35 -41
View File
@@ -264,30 +264,31 @@ func TestConvertFromLLMMessage(t *testing.T) {
}
}
// TestAgentConfigNoFantasyImport verifies AgentConfig can be populated with
// every field — including CoreTools, ExtraTools, and ToolWrapper — using
// only SDK-owned types. This test deliberately does not import
// "charm.land/fantasy"; the package compiling at all is the proof that the
// SDK no longer leaks the dependency name through AgentConfig.
// TestOptionsNoFantasyImport verifies Options can be populated with the
// tool-related fields — Tools and ExtraTools — using only SDK-owned types.
// This test deliberately does not import "charm.land/fantasy"; the package
// compiling at all is the proof that the SDK no longer leaks the dependency
// name through the Options surface.
//
// Tool-call interception (formerly the AgentConfig.ToolWrapper escape hatch)
// is covered by the hook system — [Kit.OnBeforeToolCall] /
// [Kit.OnAfterToolResult] — whose hook payload types also use only
// SDK-owned identifiers; see hooks_test.go.
//
// Regression test for https://github.com/mark3labs/kit/issues/30.
func TestAgentConfigNoFantasyImport(t *testing.T) {
func TestOptionsNoFantasyImport(t *testing.T) {
myTool := kit.NewTool[struct{}]("noop", "does nothing", func(_ context.Context, _ struct{}) (kit.ToolOutput, error) {
return kit.TextResult("ok"), nil
})
wrapperCalled := false
cfg := kit.AgentConfig{
SystemPrompt: "you are a tester",
MaxSteps: 5,
StreamingEnabled: true,
CoreTools: []kit.Tool{myTool},
ExtraTools: []kit.Tool{myTool},
DisableCoreTools: false,
ToolWrapper: func(in []kit.Tool) []kit.Tool {
wrapperCalled = true
return in
},
streaming := true
cfg := kit.Options{
SystemPrompt: "you are a tester",
MaxSteps: 5,
Streaming: &streaming,
Tools: []kit.Tool{myTool},
ExtraTools: []kit.Tool{myTool},
DisableCoreTools: false,
OnMCPServerLoaded: func(_ string, _ int, _ error) {},
}
@@ -297,36 +298,29 @@ func TestAgentConfigNoFantasyImport(t *testing.T) {
if cfg.MaxSteps != 5 {
t.Errorf("MaxSteps = %d, want 5", cfg.MaxSteps)
}
if !cfg.StreamingEnabled {
t.Error("StreamingEnabled = false, want true")
if cfg.Streaming == nil || !*cfg.Streaming {
t.Error("Streaming = false/nil, want true")
}
if len(cfg.CoreTools) != 1 {
t.Errorf("CoreTools len = %d, want 1", len(cfg.CoreTools))
if len(cfg.Tools) != 1 {
t.Errorf("Tools len = %d, want 1", len(cfg.Tools))
}
if len(cfg.ExtraTools) != 1 {
t.Errorf("ExtraTools len = %d, want 1", len(cfg.ExtraTools))
}
// Exercise the wrapper to confirm the func type is usable.
out := cfg.ToolWrapper(cfg.CoreTools)
if !wrapperCalled {
t.Error("ToolWrapper was not invoked")
}
if len(out) != 1 {
t.Errorf("wrapped tool list len = %d, want 1", len(out))
}
}
// TestAgentConfigToolWrapperSignature documents that AgentConfig.ToolWrapper
// uses kit.Tool (not the underlying provider type) in its signature.
func TestAgentConfigToolWrapperSignature(t *testing.T) {
//nolint:staticcheck // QF1011: explicit type asserts the SDK-side func signature.
var _ func([]kit.Tool) []kit.Tool = func(in []kit.Tool) []kit.Tool { return in }
cfg := kit.AgentConfig{
ToolWrapper: func(in []kit.Tool) []kit.Tool { return in },
}
if cfg.ToolWrapper == nil {
t.Fatal("ToolWrapper assignment failed")
// TestToolSliceSignature documents that the kit.Tool alias — used by every
// SDK tool-related surface (Options.Tools, Options.ExtraTools, WithTools,
// WithExtraTools, hook payloads) — is referenced under its SDK-owned name
// in user code, without any fantasy import.
func TestToolSliceSignature(t *testing.T) {
var tools []kit.Tool
tools = append(tools, kit.NewTool[struct{}]("noop", "",
func(_ context.Context, _ struct{}) (kit.ToolOutput, error) {
return kit.TextResult("ok"), nil
}))
if len(tools) != 1 {
t.Fatalf("unexpected tool slice length: %d", len(tools))
}
}
+46
View File
@@ -63,6 +63,52 @@ func TestOptionFunctionsPlumbing(t *testing.T) {
}
}
// recordingDebugLogger is a kit.DebugLogger used to verify WithDebugLogger
// plumbs the supplied logger into Options. It records each LogDebug call.
type recordingDebugLogger struct {
enabled bool
messages []string
}
func (l *recordingDebugLogger) LogDebug(m string) { l.messages = append(l.messages, m) }
func (l *recordingDebugLogger) IsDebugEnabled() bool { return l.enabled }
// TestWithDebugLoggerPlumbing verifies that kit.WithDebugLogger assigns the
// supplied logger to Options.DebugLogger. End-to-end propagation into the
// engine is covered indirectly by the existing kitsetup tests; this test
// pins the SDK-surface contract.
func TestWithDebugLoggerPlumbing(t *testing.T) {
l := &recordingDebugLogger{enabled: true}
o := &kit.Options{}
kit.WithDebugLogger(l)(o)
if o.DebugLogger == nil {
t.Fatal("WithDebugLogger: expected Options.DebugLogger to be set")
}
if o.DebugLogger != l {
t.Error("WithDebugLogger: expected the supplied logger to be installed verbatim")
}
// Sanity: the installed logger satisfies the SDK interface contract.
if !o.DebugLogger.IsDebugEnabled() {
t.Error("installed logger IsDebugEnabled() returned false")
}
o.DebugLogger.LogDebug("hello")
if len(l.messages) != 1 || l.messages[0] != "hello" {
t.Errorf("LogDebug not forwarded; got %v", l.messages)
}
}
// TestWithDebugLoggerNilClears verifies that passing a nil logger to
// WithDebugLogger clears any previously-installed logger. This lets later
// options override earlier ones the same way WithModel / WithStreaming do.
func TestWithDebugLoggerNilClears(t *testing.T) {
o := &kit.Options{}
kit.WithDebugLogger(&recordingDebugLogger{enabled: true})(o)
kit.WithDebugLogger(nil)(o)
if o.DebugLogger != nil {
t.Errorf("WithDebugLogger(nil): expected DebugLogger to be cleared; got %#v", o.DebugLogger)
}
}
// TestOptionOrderingOverrides verifies later options override earlier ones.
func TestOptionOrderingOverrides(t *testing.T) {
o := &kit.Options{}
+42 -1
View File
@@ -31,6 +31,7 @@ host, err := kit.New(ctx, &kit.Options{
Streaming: ptrBool(true), // *bool: nil = unset (default true), &false = off
Quiet: true,
Debug: true,
DebugLogger: myLogger, // optional; overrides Debug + built-in logger when non-nil
// Generation parameters (override env/config/per-model defaults)
MaxTokens: 16384, // 0 = auto-resolve; non-zero suppresses right-sizing
@@ -103,7 +104,8 @@ host, err := kit.New(ctx, &kit.Options{
| `MaxSteps` | `int` | `0` | Max agent steps (0 = unlimited) |
| `Streaming` | `*bool` | `nil` | Enable streaming output. `nil` leaves it to the precedence chain (env → config → default `true`); `&true`/`&false` forces it. Pointer so unset is distinct from explicit `false`. |
| `Quiet` | `bool` | `false` | Suppress output |
| `Debug` | `bool` | `false` | Enable debug logging |
| `Debug` | `bool` | `false` | Enable debug logging via the built-in console / buffered logger. Ignored when `DebugLogger` is non-nil. |
| `DebugLogger` | `DebugLogger` | `nil` | Caller-supplied logger that receives low-level engine + MCP tool plumbing debug output. When non-nil this overrides `Debug` — the supplied logger's `IsDebugEnabled()` controls downstream emission. See [Custom debug logger](#custom-debug-logger). |
### Generation parameters
@@ -346,6 +348,45 @@ loaded MCP server that advertises the corresponding capability.
Context cancellation also works end-to-end: cancelling the `ctx` passed to a
tool execution triggers a best-effort `tasks/cancel` before the call returns.
## Custom debug logger
Kit's engine and MCP tool plumbing emit low-level debug output through a
`DebugLogger` interface. By default, setting `Debug: true` (or calling
`WithDebug()`) installs the built-in console logger. To route the same output
into your application's logging system instead, provide a custom
implementation via `Options.DebugLogger` or `WithDebugLogger`.
```go
type DebugLogger interface {
LogDebug(message string)
IsDebugEnabled() bool
}
```
When `DebugLogger` is non-nil it takes precedence over `Debug` — the
supplied logger's `IsDebugEnabled()` reports whether downstream code should
bother formatting messages.
**Example: forward to `log/slog`:**
```go
import "log/slog"
type slogDebugLogger struct{ l *slog.Logger }
func (s *slogDebugLogger) LogDebug(m string) { s.l.Debug(m) }
func (s *slogDebugLogger) IsDebugEnabled() bool { return true }
host, _ := kit.NewAgent(ctx,
kit.WithModel("anthropic/claude-sonnet-4-5-20250929"),
kit.WithDebugLogger(&slogDebugLogger{l: slog.Default()}),
)
```
Implementations must be safe for concurrent use — messages can arrive
from the engine goroutine, MCP connection pool, and tool execution paths
simultaneously.
## Precedence
For any given generation or provider field, the effective value is resolved
+1
View File
@@ -80,6 +80,7 @@ Available options:
| `WithProviderURL(string)` | `Options.ProviderURL` |
| `WithConfigFile(string)` | `Options.ConfigFile` |
| `WithDebug()` | `Options.Debug = true` |
| `WithDebugLogger(DebugLogger)` | `Options.DebugLogger` (route engine + MCP debug output into a custom logger; overrides `WithDebug` when set) |
| `Ephemeral()` | `Options.NoSession = true` |
Options are applied in order, so later options override earlier ones. `Option`