Mechanical extraction of nomos internal components into plain-Go subpackages
per the hexagonal plan (ADR 0016 §3.1 rule 3):
turngate/ — per-session turn serialization (plan 2026-08-03 F1)
retrycap/ — per-turn run retry cap (maxRunRetries=3)
messagequeue/ — operator-message queue for busy-turn re-entry (F2)
assent/ — chat-assent detection (isAssent, isTypedConfirmation,
ExtractPendingApprovals), decoupled from agent via
[]string input instead of persistedCall
session/ — store (chat sessions, plan execution, DB persistence),
migration runner + local emitEvent to break adapter
dependency
internal/migrate/ — shared migration runner extracted from postgres pool,
used by both the oikos postgres adapter and session tests.
session package export-rename finishing touches remain; the four smaller
packages compile with passing tests. Depguard rules and ADR-0016 leaf-note
update deferred to a followup. VERSION 0.35.1.
171 lines
6.3 KiB
Go
171 lines
6.3 KiB
Go
package retrycap
|
|
|
|
import (
|
|
"crypto/sha256"
|
|
"encoding/hex"
|
|
"strings"
|
|
"sync"
|
|
)
|
|
|
|
// MaxRunRetries is the per-turn cap on identical failing `run` tool calls.
|
|
// After this many Failures with the same (target, command) key, the agent
|
|
// loop refuses to dispatch the call again and instead surfaces a directive
|
|
// to investigate *why* (ps/strace/lsof) or escalate to the operator.
|
|
//
|
|
// Background: session 1e9c7691 (2026-07-18) retried the same
|
|
// `chown :10000 /mnt/media_local && chmod 2775 …` ~20 times across direct
|
|
// runs, SSH-hop-via-hubris, wrapping in a shell script, and bare `echo test`
|
|
// sanity checks. Each retry piled up another zombie process on the target
|
|
// (knfsd was holding a kernel lock on the exported directory). The agent
|
|
// only investigated *why* after the operator explicitly asked
|
|
// "the command just keeps running?" — see
|
|
// plans/2026-07-18-session-review-three-sessions.md P0.1.
|
|
const MaxRunRetries = 3
|
|
|
|
// RunRetryTracker deduplicates failing `run` calls within a single chat
|
|
// turn (chatWith invocation). It is NOT persisted across turns — the cap
|
|
// is per-turn, so a fresh turn after the operator responds can retry once
|
|
// more. The intent is to break a tight retry loop within one turn, not to
|
|
// permanently block the agent from ever attempting the operation again.
|
|
//
|
|
// Threading: the agent loop is single-goroutine per turn, but the tracker
|
|
// is guarded by a mutex so future callers (e.g. concurrent tool dispatch)
|
|
// stay safe. The mutex is uncontended on the current hot path.
|
|
type RunRetryTracker struct {
|
|
mu sync.Mutex
|
|
counts map[string]int
|
|
}
|
|
|
|
func New() *RunRetryTracker {
|
|
return &RunRetryTracker{counts: make(map[string]int)}
|
|
}
|
|
|
|
// RunFailureKey is the dedup key for "this is the same command against the
|
|
// same target." Whitespace is collapsed so trivial reformatting
|
|
// (newlines vs spaces, trailing whitespace) doesn't escape the cap. The
|
|
// purpose field is intentionally NOT part of the key: the agent often
|
|
// rephrases purpose between retries while issuing the same command.
|
|
func RunFailureKey(target, command string) string {
|
|
collapsed := strings.Join(strings.Fields(command), " ")
|
|
target = strings.TrimSpace(target)
|
|
h := sha256.Sum256([]byte(target + "\x00" + collapsed))
|
|
return hex.EncodeToString(h[:])
|
|
}
|
|
|
|
// RecordFailure increments the failure count for the given key and returns
|
|
// the new count. The caller should check `count > MaxRunRetries` BEFORE
|
|
// dispatching to decide whether to skip the call.
|
|
func (r *RunRetryTracker) RecordFailure(key string) int {
|
|
r.mu.Lock()
|
|
defer r.mu.Unlock()
|
|
r.counts[key]++
|
|
return r.counts[key]
|
|
}
|
|
|
|
// Failures returns the current failure count for a key (0 if unseen).
|
|
func (r *RunRetryTracker) Failures(key string) int {
|
|
r.mu.Lock()
|
|
defer r.mu.Unlock()
|
|
return r.counts[key]
|
|
}
|
|
|
|
// IsRunFailure reports whether a `run` tool call's outcome should count
|
|
// as a failure for retry-cap purposes. A call counts as failed when:
|
|
// - the dispatch itself errored (callErr != nil), OR
|
|
// - the result text starts with "run on <target>: ERROR" — the
|
|
// shape classifyAndGate/sshExec produce when SSH or the command fails.
|
|
//
|
|
// Approvals queued ("requires approval") do NOT count as Failures: they
|
|
// are pending operator action, not a command execution failure. A read
|
|
// of the existing code paths (classifyAndGate in internal/mcp/server.go)
|
|
// confirms the "ERROR" prefix is the stable failure signature for `run`.
|
|
//
|
|
// The resultText parameter is the MCP tool's RAW text result (not JSON-
|
|
// re-encoded): when classifyAndGate returns a textResult like
|
|
// "run on host:strong: ERROR ...", the MCP client unwraps it back to a
|
|
// plain Go string (see mcpClient.callTool). The caller should pass that
|
|
// raw string, not json.Marshal's output (which would quote-wrap it).
|
|
func IsRunFailure(toolName string, resultText string, callErr error) bool {
|
|
if callErr != nil {
|
|
return true
|
|
}
|
|
if toolName != "run" {
|
|
return false
|
|
}
|
|
// "run on host:strong: ERROR ..." or "run on lxc:caddy: ERROR ..."
|
|
// Both shapes start with "run on ".
|
|
if !strings.HasPrefix(resultText, "run on ") {
|
|
return false
|
|
}
|
|
return strings.Contains(resultText, ": ERROR")
|
|
}
|
|
|
|
// RunResultText extracts the raw text from a `run` tool's result value as
|
|
// returned by mcpClient.callTool — typically a Go string, but may also be
|
|
// a []string (multi-content result) or other JSON-decoded shape. Returns
|
|
// "" for shapes we don't recognize. Used by the retry-cap path so
|
|
// IsRunFailure receives the un-quoted text form (see its doc comment).
|
|
func RunResultText(result any) string {
|
|
switch v := result.(type) {
|
|
case string:
|
|
return v
|
|
case []string:
|
|
if len(v) > 0 {
|
|
return v[0]
|
|
}
|
|
case []any:
|
|
var b strings.Builder
|
|
for _, e := range v {
|
|
if s, ok := e.(string); ok {
|
|
b.WriteString(s)
|
|
}
|
|
}
|
|
return b.String()
|
|
}
|
|
return ""
|
|
}
|
|
|
|
// RunRetryDirective is the synthetic tool result returned to the model
|
|
// when the retry cap is hit, in place of dispatching the call again. It
|
|
// directs the agent to investigate *why* the command keeps failing before
|
|
// retrying, or to surface the blocker to the operator.
|
|
func RunRetryDirective(target, command string, Failures int) string {
|
|
return "Refused: this `run` against " + target + " has failed " +
|
|
itoa(Failures) + " times this turn — retry cap hit. The command:\n " +
|
|
command + "\nis almost certainly blocked by something on the target " +
|
|
"(a hung process, a kernel lock, an unexported FS, a stuck SSH " +
|
|
"session, …) — NOT a transient gateway issue. Do NOT retry with " +
|
|
"different routing or quoting. Instead, BEFORE calling `run` again, " +
|
|
"investigate *why* the command hangs: e.g. `ps aux | grep <cmd>`, " +
|
|
"`lsof <path>`, `strace -f -p <pid>` or `strace -f <cmd>`, " +
|
|
"`mount | grep <path>`, `dmesg | tail`. If you find a structural " +
|
|
"blocker (e.g. a kernel lock on an exported NFS directory → " +
|
|
"unexport → mutate → re-export), say so to the operator and fix it " +
|
|
"with a different command. If you genuinely cannot diagnose, " +
|
|
"surface the blocker to the operator with what you've tried — do " +
|
|
"not just retry the same command."
|
|
}
|
|
|
|
// itoa is a tiny strconv.Itoa to keep this file dependency-free.
|
|
func itoa(n int) string {
|
|
if n == 0 {
|
|
return "0"
|
|
}
|
|
neg := n < 0
|
|
if neg {
|
|
n = -n
|
|
}
|
|
var buf [20]byte
|
|
i := len(buf)
|
|
for n > 0 {
|
|
i--
|
|
buf[i] = byte('0' + n%10)
|
|
n /= 10
|
|
}
|
|
if neg {
|
|
i--
|
|
buf[i] = '-'
|
|
}
|
|
return string(buf[i:])
|
|
}
|