tool

package
v0.30.0 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Aug 31, 2026 License: MIT Imports: 38 Imported by: 0

Documentation

Index

Constants

View Source 
const (
	// MaxToolOutputBytes caps the byte length of any single tool result.
	MaxToolOutputBytes = 50 * 1024 // 50 KB
	// MaxToolOutputLines caps the line count of any single tool result.
	MaxToolOutputLines = 2000
	// MaxLineLength caps one very long line (e.g. minified JS, a base64 blob) so
	// a single line cannot consume the whole budget on its own.
	MaxLineLength = 2000
)

Tool-output size caps. Every tool result that would otherwise flood the model context is truncated to these limits. The values mirror opencode's shared truncation service (50 KB / 2000 lines): a single large tool output (a build log, a big file, a verbose test run) is the dominant source of wasted tokens in an agentic loop, because it is re-sent on every subsequent step of the turn until compaction. Capping it here bounds that cost at the source.

Variables

This section is empty.

Functions

func ParseCompactContextArgs added in v0.26.1 

func ParseCompactContextArgs(raw json.RawMessage) (string, error)

ParseCompactContextArgs extracts and validates the summary from a raw tool call. Exported so the agent loop reads the argument through exactly the same parser the tool validated it with, rather than a second, drifting copy.

func ToProviderTools 

func ToProviderTools(tools []ToolDef) []map[string]any

ToProviderTools converts tool definitions to provider format.

func TruncateOutput added in v0.21.0 

func TruncateOutput(s string, dir TruncateDirection) (string, bool)

TruncateOutput caps s to MaxToolOutputLines and MaxToolOutputBytes, keeping the requested end, and inserts a one-line notice describing what was dropped. It returns the (possibly unchanged) text and whether any truncation happened.

It is the shared backstop applied to every tool result that does not cap its own output. Tools that truncate themselves (read, bash, grep, glob) set Result.Truncated so the agent loop skips this pass.

Types

type BashTool 

type BashTool struct{}

func (BashTool) Description 

func (BashTool) Description() string

func (BashTool) Execute 

func (BashTool) Execute(ctx context.Context, args json.RawMessage, tctx Context) (Result, error)

func (BashTool) ID 

func (BashTool) ID() string

func (BashTool) Parameters 

func (BashTool) Parameters() json.RawMessage

type BreakdownInput 

type BreakdownInput struct {
	Tasks []struct {
		Title        string `json:"title"`
		Description  string `json:"description"`
		Dependencies []int  `json:"dependencies"`
		Effort       string `json:"effort"`
		Complexity   string `json:"complexity"`
		OrderIndex   int    `json:"orderIndex"`
	} `json:"tasks"`
}

BreakdownInput matches the tool's parameter schema.

type BreakdownTool 

type BreakdownTool struct{}

BreakdownTool receives a structured task breakdown from the breakdown agent. The LLM calls this tool with properly formatted JSON (guaranteed valid by the tool-calling system), eliminating free-text JSON parsing issues.

func (BreakdownTool) Description 

func (t BreakdownTool) Description() string

func (BreakdownTool) Execute 

func (t BreakdownTool) Execute(_ context.Context, args json.RawMessage, _ Context) (Result, error)

func (BreakdownTool) ID 

func (t BreakdownTool) ID() string

func (BreakdownTool) Parameters 

func (t BreakdownTool) Parameters() json.RawMessage

type CheckSyntaxTool added in v0.25.0 

type CheckSyntaxTool struct{}

CheckSyntaxTool parses a file with tree-sitter and reports its syntax errors.

The failure it catches is both common and quiet: a replaced block that drops a brace, an indentation slip in Python, a merge of two fragments that leaves a stray token. None of those announce themselves — the file writes fine, and the damage surfaces later, in a build the agent may not run for several turns, by which point it has stacked more edits on a broken parse.

write and edit call syntaxNote for exactly that reason, which leaves this tool the cases they cannot cover: a file changed by a shell command, a formatter, a patch or a generator, and the confirmation that a fix landed.

The check is deliberately narrow. It shares the parse file_map already relies on, costs single-digit milliseconds, and needs no toolchain, so it works in any project — but it validates grammar only. It is a cheap guard against having broken the file, not a substitute for the compiler.

func (CheckSyntaxTool) Description added in v0.25.0 

func (CheckSyntaxTool) Description() string

func (CheckSyntaxTool) Execute added in v0.25.0 

func (CheckSyntaxTool) Execute(_ context.Context, args json.RawMessage, tctx Context) (Result, error)

func (CheckSyntaxTool) ID added in v0.25.0 

func (CheckSyntaxTool) ID() string

func (CheckSyntaxTool) Parameters added in v0.25.0 

func (CheckSyntaxTool) Parameters() json.RawMessage

type CompactContextTool added in v0.26.1 

type CompactContextTool struct{}

CompactContextTool lets the agent reclaim its own context mid-turn on endpoints that do not cache a repeated prefix, where every step re-pays full price for the entire accumulated history.

The tool itself only validates. The agent loop does the work: seeing this call, it records a watermark at the assistant message that made it, and from the next step onward assembles the request as the summary plus everything after that watermark. Nothing is deleted — the session store keeps every message, so history and the UI are unaffected — only the model-facing slice narrows.

func NewCompactContextTool added in v0.26.1 

func NewCompactContextTool() CompactContextTool

func (CompactContextTool) Description added in v0.26.1 

func (CompactContextTool) Description() string

func (CompactContextTool) Execute added in v0.26.1 

func (CompactContextTool) Execute(ctx context.Context, args json.RawMessage, tctx Context) (Result, error)

func (CompactContextTool) ID added in v0.26.1 

func (CompactContextTool) ID() string

func (CompactContextTool) Parameters added in v0.26.1 

func (CompactContextTool) Parameters() json.RawMessage

type Context 

type Context struct {
	SessionID  session.SessionID
	MessageID  session.MessageID
	Agent      string
	CallID     string
	Ctx        context.Context
	SessionDir string
	Ask        func(req PermissionRequest) error
	Metadata   func(meta MetadataUpdate) error
	// ModelSupportsImages is true when the session's active model accepts image
	// input. Tools may use this to decide whether to return an image (e.g. a
	// rendered PDF page) instead of text.
	ModelSupportsImages bool
	// Model is the model ID the parent session is using. Tools that spawn child
	// sessions (e.g. deep_search) should inherit this so they run on the same model.
	Model string
}

Context is passed to every tool execution.

type DeepSearchFunc added in v0.8.0 

type DeepSearchFunc func(ctx context.Context, query, dir, model string) (string, error)

DeepSearchFunc is a function that runs a child search-agent session and returns the synthesised answer. Implemented by agent.LoopRunner.RunSearchSession and wired in from server.go to avoid the tool→agent import cycle.

type DeepSearchTool added in v0.8.0 

type DeepSearchTool struct {
	Run DeepSearchFunc
}

DeepSearchTool lets any agent delegate a research query to the SearchAgent. It creates an ephemeral child session, runs the full search loop, and returns the synthesised text as the tool result.

func (DeepSearchTool) Description added in v0.8.0 

func (DeepSearchTool) Description() string

func (DeepSearchTool) Execute added in v0.8.0 

func (t DeepSearchTool) Execute(ctx context.Context, args json.RawMessage, tctx Context) (Result, error)

func (DeepSearchTool) ID added in v0.8.0 

func (DeepSearchTool) ID() string

func (DeepSearchTool) Parameters added in v0.8.0 

func (DeepSearchTool) Parameters() json.RawMessage

type DocxIndexTool added in v0.13.6 

type DocxIndexTool struct {
	Store *docindex.Store
}

DocxIndexTool returns the stored semantic map for a DOCX file — pseudo-page labels — so the agent can decide which pages to read before calling read_docx_page.

func NewDocxIndexTool added in v0.13.6 

func NewDocxIndexTool(store *docindex.Store) DocxIndexTool

func (DocxIndexTool) Description added in v0.13.6 

func (DocxIndexTool) Description() string

func (DocxIndexTool) Execute added in v0.13.6 

func (t DocxIndexTool) Execute(_ context.Context, args json.RawMessage, tctx Context) (Result, error)

func (DocxIndexTool) ID added in v0.13.6 

func (DocxIndexTool) ID() string

func (DocxIndexTool) Parameters added in v0.13.6 

func (DocxIndexTool) Parameters() json.RawMessage

type EditTool 

type EditTool struct{}

func (EditTool) Description 

func (EditTool) Description() string

func (EditTool) Execute 

func (EditTool) Execute(ctx context.Context, args json.RawMessage, tctx Context) (Result, error)

func (EditTool) ID 

func (EditTool) ID() string

func (EditTool) Parameters 

func (EditTool) Parameters() json.RawMessage

type FetchPageTool added in v0.8.0 

type FetchPageTool struct {
	Bridge search.Backend
}

FetchPageTool retrieves the text content of a URL via the configured search backend.

func (FetchPageTool) Description added in v0.8.0 

func (FetchPageTool) Description() string

func (FetchPageTool) Execute added in v0.8.0 

func (t FetchPageTool) Execute(ctx context.Context, args json.RawMessage, _ Context) (Result, error)

func (FetchPageTool) ID added in v0.8.0 

func (FetchPageTool) ID() string

func (FetchPageTool) Parameters added in v0.8.0 

func (FetchPageTool) Parameters() json.RawMessage

type FileMapTool added in v0.24.0 

type FileMapTool struct{}

FileMapTool returns the structural outline of a single file — every declaration it makes and the line range that declaration occupies — so the agent can read the one region it needs instead of the whole file.

It pairs with the read tool the way pdf_index pairs with read_pdf_page: file_map to decide where to look, read(start_line, end_line) to look. Unlike that pair it consults no index — the outline is parsed from the file on every call, so its ranges always describe the file's current contents.

func (FileMapTool) Description added in v0.24.0 

func (FileMapTool) Description() string

Description carries the two limits an agent cannot recover from the output.

What the map omits is invisible by construction: a name that was never captured leaves no trace, so an agent hunting a struct field finds nothing and has no way to tell "not in this file" from "not the kind of thing this lists". And grammar coverage decides whether a range is exact or approximate, which changes how much slack to allow around it.

The runtime notes Render already emits — the symbol cap, a recovered parse error, the heuristic-scan warning — are deliberately not repeated here. They arrive attached to the map they describe, which beats a static sentence the agent has to remember applies.

func (FileMapTool) Execute added in v0.24.0 

func (FileMapTool) Execute(_ context.Context, args json.RawMessage, tctx Context) (Result, error)

func (FileMapTool) ID added in v0.24.0 

func (FileMapTool) ID() string

func (FileMapTool) Parameters added in v0.24.0 

func (FileMapTool) Parameters() json.RawMessage

type GlobTool 

type GlobTool struct{}

func (GlobTool) Description 

func (GlobTool) Description() string

func (GlobTool) Execute 

func (GlobTool) Execute(ctx context.Context, args json.RawMessage, tctx Context) (Result, error)

func (GlobTool) ID 

func (GlobTool) ID() string

func (GlobTool) Parameters 

func (GlobTool) Parameters() json.RawMessage

type GrepTool 

type GrepTool struct{}

func (GrepTool) Description 

func (GrepTool) Description() string

func (GrepTool) Execute 

func (GrepTool) Execute(ctx context.Context, args json.RawMessage, tctx Context) (Result, error)

func (GrepTool) ID 

func (GrepTool) ID() string

func (GrepTool) Parameters 

func (GrepTool) Parameters() json.RawMessage

type LatexToPdfTool added in v0.9.1 

type LatexToPdfTool struct{}

LatexToPdfTool compiles LaTeX source to PDF using pdflatex. It returns the path to the generated PDF file and, for vision-capable models, renders the first page as a JPEG image.

func (LatexToPdfTool) Description added in v0.9.1 

func (LatexToPdfTool) Description() string

func (LatexToPdfTool) Execute added in v0.9.1 

func (LatexToPdfTool) Execute(ctx context.Context, args json.RawMessage, tctx Context) (Result, error)

func (LatexToPdfTool) ID added in v0.9.1 

func (LatexToPdfTool) ID() string

func (LatexToPdfTool) Parameters added in v0.9.1 

func (LatexToPdfTool) Parameters() json.RawMessage

type MemoryRecallTool added in v0.2.1 

type MemoryRecallTool struct {
	Memory   *memory.Memory
	Registry *provider.Registry
}

MemoryRecallTool lets the LLM query the agentic knowledge graph on demand. Synthesis uses the session's currently selected model: the tool resolves the provider from the model ID via the registry and builds a per-call chat client.

func NewMemoryRecallTool added in v0.2.1 

func NewMemoryRecallTool(mem *memory.Memory, registry *provider.Registry) MemoryRecallTool

func (MemoryRecallTool) Description added in v0.2.1 

func (t MemoryRecallTool) Description() string

func (MemoryRecallTool) Execute added in v0.2.1 

func (t MemoryRecallTool) Execute(ctx context.Context, args json.RawMessage, tctx Context) (Result, error)

func (MemoryRecallTool) ID added in v0.2.1 

func (t MemoryRecallTool) ID() string

func (MemoryRecallTool) Parameters added in v0.2.1 

func (t MemoryRecallTool) Parameters() json.RawMessage

type MetadataUpdate 

type MetadataUpdate struct {
	Title    string         `json:"title,omitempty"`
	Metadata map[string]any `json:"metadata,omitempty"`
}

MetadataUpdate updates the running tool call's display metadata.

type PdfIndexTool added in v0.6.0 

type PdfIndexTool struct {
	Store *docindex.Store
}

PdfIndexTool returns the stored semantic map for a PDF — page labels — so the agent can decide which pages to read before calling read_pdf_page.

func NewPdfIndexTool added in v0.6.0 

func NewPdfIndexTool(store *docindex.Store) PdfIndexTool

func (PdfIndexTool) Description added in v0.6.0 

func (PdfIndexTool) Description() string

func (PdfIndexTool) Execute added in v0.6.0 

func (t PdfIndexTool) Execute(_ context.Context, args json.RawMessage, tctx Context) (Result, error)

func (PdfIndexTool) ID added in v0.6.0 

func (PdfIndexTool) ID() string

func (PdfIndexTool) Parameters added in v0.6.0 

func (PdfIndexTool) Parameters() json.RawMessage

type PermissionRequest 

type PermissionRequest struct {
	ID        session.PermissionID
	SessionID session.SessionID
	Tool      string
	Input     string
}

PermissionRequest is sent when a tool needs user approval.

type ProjectIndexTool added in v0.7.0 

type ProjectIndexTool struct {
	Store *docindex.Store
}

ProjectIndexTool returns a labeled tree of all indexed files in the session directory — text/code files, PDF documents, and DOCX documents alike — so the agent can navigate the project by topic without knowing file paths upfront.

Every file — text, code, PDF, or DOCX — appears as a leaf holding a flat topic-label array. For PDFs and DOCX files a concise subset of labels (capped at 15) is aggregated and de-duplicated across all pages, giving the agent a quick overview of what the document covers without the per-page breakdown. The dedicated pdf_index and docx_index tools provide the full per-page detail when the agent needs to decide which page to read.

func NewProjectIndexTool added in v0.7.0 

func NewProjectIndexTool(store *docindex.Store) ProjectIndexTool

func (ProjectIndexTool) Description added in v0.7.0 

func (ProjectIndexTool) Description() string

func (ProjectIndexTool) Execute added in v0.7.0 

func (t ProjectIndexTool) Execute(_ context.Context, args json.RawMessage, tctx Context) (Result, error)

func (ProjectIndexTool) ID added in v0.7.0 

func (ProjectIndexTool) ID() string

func (ProjectIndexTool) Parameters added in v0.7.0 

func (ProjectIndexTool) Parameters() json.RawMessage

type ProjectMemoryRecallTool added in v0.23.0 

type ProjectMemoryRecallTool struct {
	Memory   *memory.Memory
	Registry *provider.Registry
}

ProjectMemoryRecallTool queries the agentic knowledge graph across every conversation ever held in this workspace, where memory_recall only sees the current session. Synthesis uses the session's selected model, resolved per call from the registry — same contract as MemoryRecallTool.

func NewProjectMemoryRecallTool added in v0.23.0 

func NewProjectMemoryRecallTool(mem *memory.Memory, registry *provider.Registry) ProjectMemoryRecallTool

func (ProjectMemoryRecallTool) Description added in v0.23.0 

func (t ProjectMemoryRecallTool) Description() string

func (ProjectMemoryRecallTool) Execute added in v0.23.0 

func (t ProjectMemoryRecallTool) Execute(ctx context.Context, args json.RawMessage, tctx Context) (Result, error)

func (ProjectMemoryRecallTool) ID added in v0.23.0 

func (t ProjectMemoryRecallTool) ID() string

func (ProjectMemoryRecallTool) Parameters added in v0.23.0 

func (t ProjectMemoryRecallTool) Parameters() json.RawMessage

type ReadDocxPageTool added in v0.13.6 

type ReadDocxPageTool struct{}

ReadDocxPageTool extracts the text of a single pseudo-page from a DOCX file for the agent to read. Use docx_index first to identify which pages are relevant, then call this tool to read their content.

func (ReadDocxPageTool) Description added in v0.13.6 

func (ReadDocxPageTool) Description() string

func (ReadDocxPageTool) Execute added in v0.13.6 

func (ReadDocxPageTool) Execute(_ context.Context, args json.RawMessage, tctx Context) (Result, error)

func (ReadDocxPageTool) ID added in v0.13.6 

func (ReadDocxPageTool) ID() string

func (ReadDocxPageTool) Parameters added in v0.13.6 

func (ReadDocxPageTool) Parameters() json.RawMessage

type ReadPdfPageTool added in v0.6.0 

type ReadPdfPageTool struct{}

ReadPdfPageTool extracts the text of a single PDF page for the agent to read.

func (ReadPdfPageTool) Description added in v0.6.0 

func (ReadPdfPageTool) Description() string

func (ReadPdfPageTool) Execute added in v0.6.0 

func (ReadPdfPageTool) Execute(_ context.Context, args json.RawMessage, tctx Context) (Result, error)

func (ReadPdfPageTool) ID added in v0.6.0 

func (ReadPdfPageTool) ID() string

func (ReadPdfPageTool) Parameters added in v0.6.0 

func (ReadPdfPageTool) Parameters() json.RawMessage

type ReadTool 

type ReadTool struct{}

func (ReadTool) Description 

func (ReadTool) Description() string

func (ReadTool) Execute 

func (ReadTool) Execute(ctx context.Context, args json.RawMessage, tctx Context) (Result, error)

func (ReadTool) ID 

func (ReadTool) ID() string

func (ReadTool) Parameters 

func (ReadTool) Parameters() json.RawMessage

type Registry 

type Registry struct {
	// contains filtered or unexported fields
}

Registry holds all registered tools.

A mutex guards the map because MCP server connections are established lazily in a background goroutine (after the HTTP server starts) and register their tools into the same registry the agent loop reads each step via ForAgent/Get. Without the lock that concurrent Register+read is a data race.

func NewRegistry 

func NewRegistry() *Registry

func (*Registry) ForAgent 

func (r *Registry) ForAgent(toolIDs []string) []ToolDef

ForAgent resolves the requested tool ids against the registry. An id is matched exactly first; if that fails it is treated as a glob ("*" wildcard) and expanded against every registered id, so "mcp_*" selects all MCP tools whatever servers expose them. Each matched tool appears once even if two patterns overlap.

func (*Registry) Get 

func (r *Registry) Get(id string) ToolDef

func (*Registry) List 

func (r *Registry) List() []ToolDef

func (*Registry) Register 

func (r *Registry) Register(t ToolDef)

type Result 

type Result struct {
	Title    string         `json:"title"`
	Metadata map[string]any `json:"metadata,omitempty"`
	Output   string         `json:"output"`
	// Image, when non-nil, is an image the tool wants the model to see (e.g. a
	// rendered PDF page). It is delivered to the model alongside Output, in a
	// provider-appropriate way. Only honored for vision-capable models.
	Image *ResultImage `json:"image,omitempty"`
	// Truncated marks that the tool already capped its own Output to a safe size.
	// The agent loop's global truncation backstop leaves such results untouched;
	// results without this flag are capped to MaxToolOutputBytes/MaxToolOutputLines
	// before they enter the model context.
	Truncated bool `json:"truncated,omitempty"`
	// Denied marks that the tool call was rejected by the permission gate and was
	// never executed. The loop uses it to record a ToolDenied status (distinct
	// from ToolCompleted/ToolError) so the UI and DB reflect that the call was
	// blocked rather than run.
	Denied bool `json:"-"`
}

Result is returned from tool execution.

type ResultImage added in v0.6.0 

type ResultImage struct {
	MediaType string `json:"mediaType"`
	Data      string `json:"data"`
}

ResultImage is an image attachment on a tool Result. Data is base64-encoded image bytes; MediaType is e.g. "image/jpeg".

type SkillTool added in v0.27.0 

type SkillTool struct {
	Loader *skill.Loader
}

SkillTool loads one skill's instructions into the agent's context.

The system prompt lists every available skill by name and description; this tool is how the agent gets from that listing to the actual instructions. The separation is the whole point of the feature: descriptions are cheap enough to re-send on every step, bodies are not.

func NewSkillTool added in v0.27.0 

func NewSkillTool(l *skill.Loader) SkillTool

func (SkillTool) Description added in v0.27.0 

func (SkillTool) Description() string

func (SkillTool) Execute added in v0.27.0 

func (t SkillTool) Execute(ctx context.Context, args json.RawMessage, tctx Context) (Result, error)

func (SkillTool) ID added in v0.27.0 

func (SkillTool) ID() string

func (SkillTool) Parameters added in v0.27.0 

func (SkillTool) Parameters() json.RawMessage

type SubmitDocIndexTool added in v0.6.0 

type SubmitDocIndexTool struct {
	Store *docindex.Store
}

SubmitDocIndexTool allows the index agent to store semantic page labels.

func NewSubmitDocIndexTool added in v0.6.0 

func NewSubmitDocIndexTool(store *docindex.Store) SubmitDocIndexTool

NewSubmitDocIndexTool creates a new SubmitDocIndexTool.

func (SubmitDocIndexTool) Description added in v0.6.0 

func (SubmitDocIndexTool) Description() string

func (SubmitDocIndexTool) Execute added in v0.6.0 

func (t SubmitDocIndexTool) Execute(_ context.Context, args json.RawMessage, _ Context) (Result, error)

func (SubmitDocIndexTool) ID added in v0.6.0 

func (SubmitDocIndexTool) ID() string

func (SubmitDocIndexTool) Parameters added in v0.6.0 

func (SubmitDocIndexTool) Parameters() json.RawMessage

type TaskFunc added in v0.21.0 

type TaskFunc func(ctx context.Context, description, prompt, dir, model string) (string, error)

TaskFunc runs a read-only sub-agent session for a delegated investigation and returns its final written answer. Implemented by agent.LoopRunner.RunTaskSession and wired in from server.go/cli to avoid the tool→agent import cycle.

type TaskTool added in v0.21.0 

type TaskTool struct {
	Run TaskFunc
}

TaskTool lets a coding/planning agent delegate a focused, self-contained investigation to an autonomous read-only sub-agent. The sub-agent explores the codebase (read/glob/grep/codebase_map) and, if needed, the web (deep_search), then returns a concise written answer as the tool result. It cannot edit files or run shell commands, and it cannot spawn further sub-agents (depth-1).

func (TaskTool) Description added in v0.21.0 

func (TaskTool) Description() string

func (TaskTool) Execute added in v0.21.0 

func (t TaskTool) Execute(ctx context.Context, args json.RawMessage, tctx Context) (Result, error)

func (TaskTool) ID added in v0.21.0 

func (TaskTool) ID() string

func (TaskTool) Parameters added in v0.21.0 

func (TaskTool) Parameters() json.RawMessage

type ToolDef 

type ToolDef interface {
	ID() string
	Description() string
	Parameters() json.RawMessage
	Execute(ctx context.Context, args json.RawMessage, tctx Context) (Result, error)
}

ToolDef is the interface every tool must implement.

type TruncateDirection added in v0.21.0 

type TruncateDirection int

TruncateDirection selects which end of the output to keep when it exceeds the caps. Most tools keep the head — the start of a file or listing is usually the useful part. Shell keeps the tail, because the end of a build/test log is where the error and summary live. 

const (
	KeepHead TruncateDirection = iota
	KeepTail
)

type ViewImageTool added in v0.15.0 

type ViewImageTool struct{}

ViewImageTool lets the agent view an image file (PNG, JPEG, GIF, BMP, WebP) on disk. For vision-capable models the decoded image is returned as a ResultImage; otherwise a textual description is returned.

func (ViewImageTool) Description added in v0.15.0 

func (ViewImageTool) Description() string

func (ViewImageTool) Execute added in v0.15.0 

func (ViewImageTool) Execute(_ context.Context, args json.RawMessage, tctx Context) (Result, error)

func (ViewImageTool) ID added in v0.15.0 

func (ViewImageTool) ID() string

func (ViewImageTool) Parameters added in v0.15.0 

func (ViewImageTool) Parameters() json.RawMessage

type WebSearchTool added in v0.8.0 

type WebSearchTool struct {
	Bridge search.Backend
}

WebSearchTool searches the web via the configured search backend and returns a markdown list of results.

func (WebSearchTool) Description added in v0.8.0 

func (WebSearchTool) Description() string

func (WebSearchTool) Execute added in v0.8.0 

func (t WebSearchTool) Execute(ctx context.Context, args json.RawMessage, _ Context) (Result, error)

func (WebSearchTool) ID added in v0.8.0 

func (WebSearchTool) ID() string

func (WebSearchTool) Parameters added in v0.8.0 

func (WebSearchTool) Parameters() json.RawMessage

type WriteTool 

type WriteTool struct{}

func (WriteTool) Description 

func (WriteTool) Description() string

func (WriteTool) Execute 

func (WriteTool) Execute(ctx context.Context, args json.RawMessage, tctx Context) (Result, error)

func (WriteTool) ID 

func (WriteTool) ID() string

func (WriteTool) Parameters 

func (WriteTool) Parameters() json.RawMessage

Source Files

View all Source files

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.