steve
89f3334512
Grow executus/tools into a real generic tool library: - Register(reg): the always-available, zero-config tools — think, now (UTC unless a CurrentTimeProvider is wired), cite (inert unless a CitationStorage is wired). All nil-safe; a light host calls Register and is useful. - RegisterMeta(reg, MetaDeps): the LLM-backed meta tools — classify, extract_entities, summarize — over the llmmeta helper. Budget defaults to the shipped in-memory per-run cap; Files optional; caps default. - Seams moved (interface/type-only, no host coupling): research_providers.go (CurrentTimeProvider/CitationStorage/SearchBudget/PageExtractor/PDFFetcher/…) and file_storage.go (FileStorage + FileDomainMeta). Plus the in-memory budget default (research_defaults.go) and scope_validate.go. calculate deferred (drags github.com/Krognol/go-wolfram + a module-path replace — not worth it in the lean core for one tool). Core go.sum still free of gorm/redis/discordgo/sqlite/wolfram. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
98 lines
3.7 KiB
Go
98 lines
3.7 KiB
Go
package tools
|
|
|
|
import (
|
|
"context"
|
|
"sync"
|
|
)
|
|
|
|
// DefaultResearchConfig returns a ResearchConfig pinned to the v11
|
|
// design defaults. Production wiring overrides via a convar-aware
|
|
// adapter; tests use the defaults directly.
|
|
func DefaultResearchConfig() ResearchConfig {
|
|
return defaultResearchConfig{}
|
|
}
|
|
|
|
type defaultResearchConfig struct{}
|
|
|
|
func (defaultResearchConfig) MaxInlineBytes(_ context.Context) int { return 12 * 1024 }
|
|
func (defaultResearchConfig) PDFMaxPages(_ context.Context) int { return 50 }
|
|
func (defaultResearchConfig) WebSearchEnabled(_ context.Context) bool { return true }
|
|
func (defaultResearchConfig) WebSearchMaxPerRun(_ context.Context) int { return 10 }
|
|
func (defaultResearchConfig) ReadPageMaxPerRun(_ context.Context) int { return 10 }
|
|
func (defaultResearchConfig) VideoMaxPerRun(_ context.Context) int { return 5 }
|
|
func (defaultResearchConfig) VerifyURLMaxPerRun(_ context.Context) int { return 20 }
|
|
func (defaultResearchConfig) ReadPDFMaxPerRun(_ context.Context) int { return 5 }
|
|
func (defaultResearchConfig) HTTPGetMaxPerRun(_ context.Context) int { return 20 }
|
|
func (defaultResearchConfig) HTTPPostMaxPerRun(_ context.Context) int { return 20 }
|
|
func (defaultResearchConfig) WebSearchAugmentThreshold(_ context.Context) int { return 5 }
|
|
|
|
// InMemorySearchBudget is the package-default SearchBudget — a
|
|
// simple per-(run,kind) counter held in a map. NOT
|
|
// production-correct because the map persists across the process
|
|
// lifetime; production wiring MUST plug a per-run reset.
|
|
//
|
|
// Why a default at all: tests want a working SearchBudget without
|
|
// rolling their own. Documenting the production-correctness gap
|
|
// here keeps the production adapter (in mort.go) honest.
|
|
type InMemorySearchBudget struct {
|
|
cap map[string]int // by kind; "" means "use Default"
|
|
|
|
mu sync.Mutex
|
|
counts map[string]int // key = runID+"|"+kind
|
|
}
|
|
|
|
// NewInMemorySearchBudget constructs a default SearchBudget. Pass a
|
|
// per-kind cap map (e.g. {"web_search": 10, "read_page": 10}); kinds
|
|
// missing from the map fall back to maxPerKindDefault.
|
|
func NewInMemorySearchBudget(caps map[string]int) *InMemorySearchBudget {
|
|
if caps == nil {
|
|
caps = map[string]int{}
|
|
}
|
|
return &InMemorySearchBudget{
|
|
cap: caps,
|
|
counts: make(map[string]int),
|
|
}
|
|
}
|
|
|
|
// CheckAndIncrement implements SearchBudget. Returns the count AFTER
|
|
// incrementing on success; the counter is NOT incremented when the
|
|
// call would exceed the cap (so a "search_budget_exceeded" rejection
|
|
// doesn't burn budget on retry).
|
|
func (b *InMemorySearchBudget) CheckAndIncrement(_ context.Context, runID, kind string) (int, int, bool) {
|
|
max := b.cap[kind]
|
|
if max <= 0 {
|
|
max = 10 // safe default
|
|
}
|
|
b.mu.Lock()
|
|
defer b.mu.Unlock()
|
|
key := runID + "|" + kind
|
|
cur := b.counts[key]
|
|
if cur >= max {
|
|
return cur, max, true
|
|
}
|
|
b.counts[key] = cur + 1
|
|
return cur + 1, max, false
|
|
}
|
|
|
|
// ResetRun is a test helper: clears the counters for a single run
|
|
// across all kinds. Production wiring uses its own per-run lifecycle
|
|
// (the executor's RunFinalizer interface).
|
|
func (b *InMemorySearchBudget) ResetRun(runID string) {
|
|
b.mu.Lock()
|
|
defer b.mu.Unlock()
|
|
prefix := runID + "|"
|
|
for k := range b.counts {
|
|
if len(k) > len(prefix) && k[:len(prefix)] == prefix {
|
|
delete(b.counts, k)
|
|
}
|
|
}
|
|
}
|
|
|
|
// StaticTimeProvider is the package-default CurrentTimeProvider —
|
|
// returns "" for every member (the tool then falls back to UTC).
|
|
// Tests that need a specific timezone wire a one-line struct.
|
|
type StaticTimeProvider struct{}
|
|
|
|
// UserTimezone implements CurrentTimeProvider with a flat fallback to "".
|
|
func (StaticTimeProvider) UserTimezone(_ context.Context, _ string) string { return "" }
|