Algis DumbrisandClaude Opus 4.6
ff5d0c49f4
Ships the MVP slice of spec 018 (dynamic agent spawning):
- 5 new SQLite migrations (021-025): goals + goal_tasks + agent_proposals
+ reputation_evidence + secrets + harness_runs.task_id. The legacy
`tasks` table (channel auctions) and `agent_trust` table (reactions
workflow) are left untouched — the new schema coexists.
- 4 new internal packages, fully tested:
- internal/goals: Goal struct + store + service, slug collision dedup,
backing-channel auto-create via ChannelCreator adapter
- internal/goaltasks: goal_tasks table with denormalized 16 KB
ancestry snapshots, single-statement optimistic-lock atomic claim,
recursive-CTE cost rollup, state machine, per-billing-code rollup
- internal/secrets: NaCl-secretbox encrypted blobs, user/agent/task
scope precedence, sanitized env injection, master-key bootstrap
- internal/trust additions: ConfigHash (deterministic SHA-256 of
model + prompt + tools + skills + mcp + subagents, sorted),
DelegationCap (tier + tool-scope + budget + depth enforcement),
append-only Ledger with exponential time-decay rolling score and
70%-of-parent child seeding. Existing trust package unchanged.
- Critical invariants under test:
- 50-goroutine concurrent claim race → exactly one winner per round
- ConfigHash stable under shuffled array inputs, sensitive to
capability changes
- DelegationCap full tier × tool-scope matrix
- Ledger time-decay + parent seed at 70 % ± 1 %
- Secret name sanitization, scope precedence, plaintext never
returned via MCP-equivalent paths
- internal/agents/types.go extended with dynamic-spawning columns
(config_hash, parent_agent_id, spawn_depth, system_prompt,
autonomy_tier, tool_scope_json, quarantined_at). Existing tests
still pass.
- cmd/docgardener: self-contained demo binary driving the end-to-end
flow. `docgardener run` creates a goal, builds a task tree with
denormalized ancestry, spawns 3 specialists (each going through
real delegation-cap validation and config-hash computation and
70 %-of-parent reputation seeding), claims tasks atomically, runs
them through the state machine, records reputation evidence.
`docgardener report` queries all of that back out and renders a
rich dark-mode HTML report (header, spend metrics, task tree,
spawned-agent cards with reputation bars, cost breakdown, artifacts,
timeline).
- examples/doc-gardener: start.sh / run_task.sh / report.sh / stop.sh
mirroring the cold-topic-explainer pattern. Launches an isolated
synapbus instance on port 18089, drives the demo, renders
report.html, cleans up. Full README documenting what's real vs
deferred, plus examples/README.md listing both examples.
- specs/018: tasks.md updated with MVP completion status; legacy tasks
naming collision noted.
Deferred (marked explicitly in example README):
- Real LLM-driven coordinator (needs MCP tool wiring + prompt
iteration)
- Real subprocess runs (needs reactor integration with task_id on
ExecRequest)
- Full MCP tool surface (contracts are written at
specs/018-dynamic-agent-spawning/contracts/mcp-tools.md)
- Svelte /goals UI (REST endpoints remain a follow-up)
- Full budget race + quarantine auto-trigger wiring
- Full resource-request → secrets fulfill reaction-workflow path
Cross-compiles clean for linux/amd64 and darwin/arm64 with no CGO
(SC-010). All new package tests pass (SC-004, SC-005, SC-007).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
60 lines
2.3 KiB
Go
60 lines
2.3 KiB
Go
// Package agents provides agent registry and authentication for SynapBus.
|
|
package agents
|
|
|
|
import (
|
|
"encoding/json"
|
|
"time"
|
|
)
|
|
|
|
// Agent status constants.
|
|
const (
|
|
AgentStatusActive = "active"
|
|
AgentStatusInactive = "inactive"
|
|
)
|
|
|
|
// Trigger mode constants.
|
|
const (
|
|
TriggerModePassive = "passive"
|
|
TriggerModeReactive = "reactive"
|
|
TriggerModeDisabled = "disabled"
|
|
)
|
|
|
|
// Agent represents a registered entity that can send/receive messages.
|
|
type Agent struct {
|
|
ID int64 `json:"id"`
|
|
Name string `json:"name"`
|
|
DisplayName string `json:"display_name"`
|
|
Type string `json:"type"`
|
|
Capabilities json.RawMessage `json:"capabilities"`
|
|
OwnerID int64 `json:"owner_id"`
|
|
APIKeyHash string `json:"-"`
|
|
Status string `json:"status"`
|
|
CreatedAt time.Time `json:"created_at"`
|
|
UpdatedAt time.Time `json:"updated_at"`
|
|
|
|
// Reactive trigger fields
|
|
TriggerMode string `json:"trigger_mode"`
|
|
CooldownSeconds int `json:"cooldown_seconds"`
|
|
DailyTriggerBudget int `json:"daily_trigger_budget"`
|
|
MaxTriggerDepth int `json:"max_trigger_depth"`
|
|
K8sImage string `json:"k8s_image,omitempty"`
|
|
K8sEnvJSON string `json:"k8s_env_json,omitempty"`
|
|
K8sResourcePreset string `json:"k8s_resource_preset"`
|
|
PendingWork bool `json:"pending_work"`
|
|
|
|
// Harness-agnostic execution fields (migration 019).
|
|
HarnessName string `json:"harness_name,omitempty"` // explicit backend; empty = auto-resolve
|
|
LocalCommand string `json:"local_command,omitempty"` // JSON-encoded argv for subprocess backend
|
|
HarnessConfigJSON string `json:"harness_config_json,omitempty"` // opaque per-backend config
|
|
|
|
// Dynamic-spawning trust fields (migration 023).
|
|
ConfigHash string `json:"config_hash,omitempty"`
|
|
ParentAgentID *int64 `json:"parent_agent_id,omitempty"`
|
|
SpawnDepth int `json:"spawn_depth"`
|
|
SystemPrompt string `json:"system_prompt,omitempty"`
|
|
AutonomyTier string `json:"autonomy_tier,omitempty"`
|
|
ToolScopeJSON string `json:"tool_scope_json,omitempty"`
|
|
QuarantinedAt *time.Time `json:"quarantined_at,omitempty"`
|
|
QuarantineReason string `json:"quarantine_reason,omitempty"`
|
|
}
|