5 Commits

Author SHA1 Message Date
chrome
612c59629f fix(plugin): don't record false success for manual plugin runs
Some checks failed
CI / Check for .beads changes (pull_request) Successful in 9s
CI / Check embedded formulas (pull_request) Successful in 32s
CI / Test (pull_request) Failing after 1m47s
CI / Lint (pull_request) Failing after 22s
CI / Integration Tests (pull_request) Successful in 1m35s
CI / Coverage Report (pull_request) Has been skipped
Windows CI / Windows Build and Unit Tests (pull_request) Has been cancelled
`gt plugin run` was recording ResultSuccess even though it only prints
instructions without executing them. This poisoned the cooldown gate,
blocking actual executions for 24h.

Changes:
- Record manual runs as ResultSkipped instead of ResultSuccess
- Add CountSuccessfulRunsSince() to only count successful runs for gate
- Gate check now uses CountSuccessfulRunsSince() so skipped/failed runs
  don't block future executions

Fixes: hq-2dis4c

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-24 01:20:12 -08:00
2a639ff999 fix(session): increase ClaudeStartTimeout from 60s to 120s
Some checks failed
CI / Check for .beads changes (push) Has been skipped
CI / Check embedded formulas (push) Successful in 22s
CI / Test (push) Failing after 1m23s
CI / Lint (push) Failing after 15s
CI / Integration Tests (push) Successful in 1m7s
CI / Coverage Report (push) Has been skipped
Windows CI / Windows Build and Unit Tests (push) Has been cancelled
Fixes intermittent 'timeout waiting for runtime prompt' errors that occur
when Claude takes longer than 60s to start under load or on slower machines.

Resolves: hq-j2wl

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-22 00:16:58 -08:00
eed8941126 feat(security): add GIT_AUTHOR_EMAIL per agent type
Phase 1 of agent security model: Set distinct email addresses for each
agent type to improve audit trail clarity.

Email format:
- Town-level: {role}@gastown.local (mayor, deacon, boot)
- Rig-level: {rig}-{role}@gastown.local (witness, refinery)
- Named agents: {rig}-{role}-{name}@gastown.local (polecat, crew)

This makes git log filtering by agent type trivial and provides a
foundation for per-agent key separation in future phases.

Refs: hq-biot
2026-01-22 00:16:58 -08:00
9f9b2376ea ci: disable block-internal-prs for fork workflow
We use PRs for human review before merging in our fork.
2026-01-22 00:16:58 -08:00
7fd073810d feat(mayor): add escalation check to startup protocol
Mayor now checks `gt escalate list` between hook and mail checks at startup.
This ensures pending escalations from other agents are handled promptly.

Other roles (witness, refinery, polecat, crew, deacon) are unaffected -
they create escalations but don't handle them at startup.
2026-01-22 00:16:58 -08:00
7 changed files with 48 additions and 61 deletions

View File

@@ -1,51 +0,0 @@
name: Block Internal PRs
on:
pull_request:
types: [opened, reopened]
jobs:
block-internal-prs:
name: Block Internal PRs
# Only run if PR is from the same repo (not a fork)
if: github.event.pull_request.head.repo.full_name == github.repository
runs-on: ubuntu-latest
steps:
- name: Close PR and comment
uses: actions/github-script@v7
with:
script: |
const prNumber = context.issue.number;
const branch = context.payload.pull_request.head.ref;
const body = [
'**Internal PRs are not allowed.**',
'',
'Gas Town agents push directly to main. PRs are for external contributors only.',
'',
'To land your changes:',
'```bash',
'git checkout main',
'git merge ' + branch,
'git push origin main',
'git push origin --delete ' + branch,
'```',
'',
'See CLAUDE.md: "Crew workers push directly to main. No feature branches. NEVER create PRs."'
].join('\n');
await github.rest.issues.createComment({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: prNumber,
body: body
});
await github.rest.pulls.update({
owner: context.repo.owner,
repo: context.repo.repo,
pull_number: prNumber,
state: 'closed'
});
core.setFailed('Internal PR blocked. Push directly to main instead.');

View File

@@ -392,7 +392,7 @@ func runPluginRun(cmd *cobra.Command, args []string) error {
if duration == "" {
duration = "1h" // default
}
count, err := recorder.CountRunsSince(p.Name, duration)
count, err := recorder.CountSuccessfulRunsSince(p.Name, duration)
if err != nil {
// Log warning but continue
fmt.Fprintf(os.Stderr, "Warning: checking gate status: %v\n", err)
@@ -433,13 +433,14 @@ func runPluginRun(cmd *cobra.Command, args []string) error {
fmt.Printf("%s\n", style.Bold.Render("Instructions:"))
fmt.Println(p.Instructions)
// Record the run
// Record the run as "skipped" - we only printed instructions, didn't execute
// Actual execution happens via Deacon patrol or an agent following the instructions
recorder := plugin.NewRecorder(townRoot)
beadID, err := recorder.RecordRun(plugin.PluginRunRecord{
PluginName: p.Name,
RigName: p.RigName,
Result: plugin.ResultSuccess, // Manual runs are marked success
Body: "Manual run via gt plugin run",
Result: plugin.ResultSkipped, // Instructions printed, not executed
Body: "Manual run via gt plugin run (instructions printed, not executed)",
})
if err != nil {
fmt.Fprintf(os.Stderr, "Warning: failed to record run: %v\n", err)

View File

@@ -49,36 +49,43 @@ func AgentEnv(cfg AgentEnvConfig) map[string]string {
case "mayor":
env["BD_ACTOR"] = "mayor"
env["GIT_AUTHOR_NAME"] = "mayor"
env["GIT_AUTHOR_EMAIL"] = "mayor@gastown.local"
case "deacon":
env["BD_ACTOR"] = "deacon"
env["GIT_AUTHOR_NAME"] = "deacon"
env["GIT_AUTHOR_EMAIL"] = "deacon@gastown.local"
case "boot":
env["BD_ACTOR"] = "deacon-boot"
env["GIT_AUTHOR_NAME"] = "boot"
env["GIT_AUTHOR_EMAIL"] = "boot@gastown.local"
case "witness":
env["GT_RIG"] = cfg.Rig
env["BD_ACTOR"] = fmt.Sprintf("%s/witness", cfg.Rig)
env["GIT_AUTHOR_NAME"] = fmt.Sprintf("%s/witness", cfg.Rig)
env["GIT_AUTHOR_EMAIL"] = fmt.Sprintf("%s-witness@gastown.local", cfg.Rig)
case "refinery":
env["GT_RIG"] = cfg.Rig
env["BD_ACTOR"] = fmt.Sprintf("%s/refinery", cfg.Rig)
env["GIT_AUTHOR_NAME"] = fmt.Sprintf("%s/refinery", cfg.Rig)
env["GIT_AUTHOR_EMAIL"] = fmt.Sprintf("%s-refinery@gastown.local", cfg.Rig)
case "polecat":
env["GT_RIG"] = cfg.Rig
env["GT_POLECAT"] = cfg.AgentName
env["BD_ACTOR"] = fmt.Sprintf("%s/polecats/%s", cfg.Rig, cfg.AgentName)
env["GIT_AUTHOR_NAME"] = cfg.AgentName
env["GIT_AUTHOR_EMAIL"] = fmt.Sprintf("%s-polecat-%s@gastown.local", cfg.Rig, cfg.AgentName)
case "crew":
env["GT_RIG"] = cfg.Rig
env["GT_CREW"] = cfg.AgentName
env["BD_ACTOR"] = fmt.Sprintf("%s/crew/%s", cfg.Rig, cfg.AgentName)
env["GIT_AUTHOR_NAME"] = cfg.AgentName
env["GIT_AUTHOR_EMAIL"] = fmt.Sprintf("%s-crew-%s@gastown.local", cfg.Rig, cfg.AgentName)
}
// Only set GT_ROOT if provided

View File

@@ -14,6 +14,7 @@ func TestAgentEnv_Mayor(t *testing.T) {
assertEnv(t, env, "GT_ROLE", "mayor")
assertEnv(t, env, "BD_ACTOR", "mayor")
assertEnv(t, env, "GIT_AUTHOR_NAME", "mayor")
assertEnv(t, env, "GIT_AUTHOR_EMAIL", "mayor@gastown.local")
assertEnv(t, env, "GT_ROOT", "/town")
assertNotSet(t, env, "GT_RIG")
assertNotSet(t, env, "BEADS_NO_DAEMON")
@@ -31,6 +32,7 @@ func TestAgentEnv_Witness(t *testing.T) {
assertEnv(t, env, "GT_RIG", "myrig")
assertEnv(t, env, "BD_ACTOR", "myrig/witness")
assertEnv(t, env, "GIT_AUTHOR_NAME", "myrig/witness")
assertEnv(t, env, "GIT_AUTHOR_EMAIL", "myrig-witness@gastown.local")
assertEnv(t, env, "GT_ROOT", "/town")
}
@@ -49,6 +51,7 @@ func TestAgentEnv_Polecat(t *testing.T) {
assertEnv(t, env, "GT_POLECAT", "Toast")
assertEnv(t, env, "BD_ACTOR", "myrig/polecats/Toast")
assertEnv(t, env, "GIT_AUTHOR_NAME", "Toast")
assertEnv(t, env, "GIT_AUTHOR_EMAIL", "myrig-polecat-Toast@gastown.local")
assertEnv(t, env, "BEADS_AGENT_NAME", "myrig/Toast")
assertEnv(t, env, "BEADS_NO_DAEMON", "1")
}
@@ -68,6 +71,7 @@ func TestAgentEnv_Crew(t *testing.T) {
assertEnv(t, env, "GT_CREW", "emma")
assertEnv(t, env, "BD_ACTOR", "myrig/crew/emma")
assertEnv(t, env, "GIT_AUTHOR_NAME", "emma")
assertEnv(t, env, "GIT_AUTHOR_EMAIL", "myrig-crew-emma@gastown.local")
assertEnv(t, env, "BEADS_AGENT_NAME", "myrig/emma")
assertEnv(t, env, "BEADS_NO_DAEMON", "1")
}
@@ -85,6 +89,7 @@ func TestAgentEnv_Refinery(t *testing.T) {
assertEnv(t, env, "GT_RIG", "myrig")
assertEnv(t, env, "BD_ACTOR", "myrig/refinery")
assertEnv(t, env, "GIT_AUTHOR_NAME", "myrig/refinery")
assertEnv(t, env, "GIT_AUTHOR_EMAIL", "myrig-refinery@gastown.local")
assertEnv(t, env, "BEADS_NO_DAEMON", "1")
}
@@ -98,6 +103,7 @@ func TestAgentEnv_Deacon(t *testing.T) {
assertEnv(t, env, "GT_ROLE", "deacon")
assertEnv(t, env, "BD_ACTOR", "deacon")
assertEnv(t, env, "GIT_AUTHOR_NAME", "deacon")
assertEnv(t, env, "GIT_AUTHOR_EMAIL", "deacon@gastown.local")
assertEnv(t, env, "GT_ROOT", "/town")
assertNotSet(t, env, "GT_RIG")
assertNotSet(t, env, "BEADS_NO_DAEMON")
@@ -113,6 +119,7 @@ func TestAgentEnv_Boot(t *testing.T) {
assertEnv(t, env, "GT_ROLE", "boot")
assertEnv(t, env, "BD_ACTOR", "deacon-boot")
assertEnv(t, env, "GIT_AUTHOR_NAME", "boot")
assertEnv(t, env, "GIT_AUTHOR_EMAIL", "boot@gastown.local")
assertEnv(t, env, "GT_ROOT", "/town")
assertNotSet(t, env, "GT_RIG")
assertNotSet(t, env, "BEADS_NO_DAEMON")

View File

@@ -10,8 +10,8 @@ const (
ShutdownNotifyDelay = 500 * time.Millisecond
// ClaudeStartTimeout is how long to wait for Claude to start in a session.
// Increased to 60s because Claude can take 30s+ on slower machines.
ClaudeStartTimeout = 60 * time.Second
// Increased to 120s because Claude can take 60s+ on slower machines or under load.
ClaudeStartTimeout = 120 * time.Second
// ShellReadyTimeout is how long to wait for shell prompt after command.
ShellReadyTimeout = 5 * time.Second

View File

@@ -213,3 +213,19 @@ func (r *Recorder) CountRunsSince(pluginName string, since string) (int, error)
}
return len(runs), nil
}
// CountSuccessfulRunsSince returns the count of successful runs for a plugin since the given duration.
// Only successful runs count for cooldown gate evaluation - skipped/failed runs don't reset the cooldown.
func (r *Recorder) CountSuccessfulRunsSince(pluginName string, since string) (int, error) {
runs, err := r.GetRunsSince(pluginName, since)
if err != nil {
return 0, err
}
count := 0
for _, run := range runs {
if run.Result == ResultSuccess {
count++
}
}
return count, nil
}

View File

@@ -35,7 +35,9 @@ drive shaft - if you stall, the whole town stalls.
**Your startup behavior:**
1. Check hook (`gt hook`)
2. If work is hooked → EXECUTE (no announcement beyond one line, no waiting)
3. If hook empty → Check mail, then wait for user instructions
3. If hook empty → Check escalations (`gt escalate list`)
4. Handle any pending escalations (these are urgent items from other agents)
5. Check mail, then wait for user instructions
**Note:** "Hooked" means work assigned to you. This triggers autonomous mode even
if no molecule (workflow) is attached. Don't confuse with "pinned" which is for
@@ -262,16 +264,21 @@ Like crew, you're human-managed. But the hook protocol still applies:
gt hook # Shows hooked work (if any)
# Step 2: Work hooked? → RUN IT
# Hook empty? → Check mail for attached work
# Step 3: Hook empty? → Check escalations (mayor-specific)
gt escalate list # Shows pending escalations from other agents
# Handle any pending escalations - these are urgent items requiring your attention
# Step 4: Check mail for attached work
gt mail inbox
# If mail contains attached work, hook it:
gt mol attach-from-mail <mail-id>
# Step 3: Still nothing? Wait for user instructions
# Step 5: Still nothing? Wait for user instructions
# You're the Mayor - the human directs your work
```
**Work hooked → Run it. Hook empty → Check mail. Nothing anywhere → Wait for user.**
**Work hooked → Run it. Hook empty → Check escalations → Check mail. Nothing anywhere → Wait for user.**
Your hooked work persists across sessions. Handoff mail (🤝 HANDOFF subject) provides context notes.