summaryrefslogtreecommitdiff
path: root/internal/executor/agentmcp_test.go
diff options
context:
space:
mode:
authorClaude Sonnet 5 <noreply@anthropic.com>2026-07-04 05:05:36 +0000
committerClaude Sonnet 5 <noreply@anthropic.com>2026-07-04 05:05:36 +0000
commit8cb291ad7cdb317ff80947278ee055b1a4925b41 (patch)
treed9719ae8982a9d7cc3482a71a87d003cdb7e0dfd /internal/executor/agentmcp_test.go
parent04b6e7eef473cb6eb69e345a4ea08243a8713077 (diff)
feat(story,role): add retro ceremony -- closes the self-improvement loop (Phase 8)
The final mechanism the versioned role-config model (Phase 5) was built for: when a story reaches DONE, StoryOrchestrator spawns a retro-role task that reflects on the story's full history and proposes draft role_configs versions for a human to review and activate via the existing (unchanged) POST /api/roles/{role}/activate. - AgentChannel gains a 6th method, ProposeRoleConfig(ctx, role.RoleConfig) (version, err), following ProposeEpic's precedent (Phase 7c): a structured tool call, not summary-parsing. storeChannel.ProposeRoleConfig calls the same Store.CreateRoleConfig the human-facing POST /api/roles/{role}/versions endpoint already uses (proposed_by: "retro"), landing a new draft row without touching whatever's currently active. Wired through both transports exactly like ProposeEpic: internal/agentloop/tools.go (native loop) and internal/executor/agentmcp.go (MCP). - StoryOrchestrator.Tick now routes a story at status DONE to a new processRetro stage instead of processStory -- a sibling stage, not a continuation, since the Builder->Evaluators->Arbitration chain is long settled by then. processRetro only *reads* that settled pipeline (read-only findEvaluators/findArbitration counterparts to ensureEvaluators/ensureArbitration -- it never spawns/mutates Builder-pipeline tasks) to locate the Arbitration task the retro task depends on, then spawns (idempotently -- checks for an existing retro-role dependent first) one retro-role task with instructions assembled from the story's spec/acceptance-criteria, full task tree, per- task cost/escalation history, active role_configs per role encountered, and the story's own event stream (evaluator verdicts, arbitration decision). - event.KindRetroCaptured (attached to the story's ID, matching KindEvalVerdict/KindArbitrationDecided's convention) fires once the retro task completes (auto-accepted like every other pipeline task), aggregating every event.KindRoleConfigProposed the retro task recorded (one per propose_role_config call) into {task_id, proposals: [{role, version}], summary} -- the summary is the "capturing lessons" half of this ceremony, the proposals are the versioned-config half. - Human activation is completely untouched: drafts land through the identical CreateRoleConfig/config_json path Phase 5's endpoints already handle, confirmed via existing role-endpoint tests passing unmodified. go build/vet/test -race -count=1 all pass, full suite (20 packages) -- one run hit a known, pre-existing, intermittent flake under full-suite load (unrelated to this phase's files) that did not reproduce on two immediate reruns, both in isolation and full-suite. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01V1moSNCJRcP6kykA4tyUSs
Diffstat (limited to 'internal/executor/agentmcp_test.go')
-rw-r--r--internal/executor/agentmcp_test.go60
1 files changed, 53 insertions, 7 deletions
diff --git a/internal/executor/agentmcp_test.go b/internal/executor/agentmcp_test.go
index c73d6db..18299e8 100644
--- a/internal/executor/agentmcp_test.go
+++ b/internal/executor/agentmcp_test.go
@@ -8,17 +8,20 @@ import (
"testing"
"github.com/modelcontextprotocol/go-sdk/mcp"
+ "github.com/thepeterstone/claudomator/internal/role"
)
// recordingChannel is a fake AgentChannel that records tool invocations.
type recordingChannel struct {
- asked string
- summary string
- spawned []SubtaskSpec
- progress []string
- spawnID string
- proposedEpics []EpicProposal
- epicID string
+ asked string
+ summary string
+ spawned []SubtaskSpec
+ progress []string
+ spawnID string
+ proposedEpics []EpicProposal
+ epicID string
+ proposedRoleConfigs []role.RoleConfig
+ roleConfigVersion int
}
func (c *recordingChannel) AskUser(_ context.Context, q string) (string, error) {
@@ -41,6 +44,10 @@ func (c *recordingChannel) ProposeEpic(_ context.Context, spec EpicProposal) (st
c.proposedEpics = append(c.proposedEpics, spec)
return c.epicID, nil
}
+func (c *recordingChannel) ProposeRoleConfig(_ context.Context, cfg role.RoleConfig) (int, error) {
+ c.proposedRoleConfigs = append(c.proposedRoleConfigs, cfg)
+ return c.roleConfigVersion, nil
+}
func resultText(t *testing.T, res *mcp.CallToolResult) string {
t.Helper()
@@ -209,6 +216,45 @@ func TestAgentServer_ProposeEpic(t *testing.T) {
}
}
+// TestAgentServer_ProposeRoleConfig proves the propose_role_config MCP tool
+// reaches AgentChannel.ProposeRoleConfig with the full role.RoleConfig shape
+// decoded correctly, including a nested escalation_ladder tier -- mirroring
+// TestAgentServer_ProposeEpic's coverage above for this phase's new tool.
+func TestAgentServer_ProposeRoleConfig(t *testing.T) {
+ ch := &recordingChannel{roleConfigVersion: 3}
+ cs := connectInMemory(t, newAgentServer(ch))
+ res, err := cs.CallTool(context.Background(), &mcp.CallToolParams{
+ Name: "propose_role_config",
+ Arguments: map[string]any{
+ "role": "builder",
+ "system_prompt": "Double-check edge cases before finishing.",
+ "escalation_ladder": []map[string]any{
+ {
+ "candidates": []map[string]any{{"provider": "anthropic", "model": "claude-sonnet-4-6"}},
+ "max_retries": 1,
+ },
+ },
+ },
+ })
+ if err != nil {
+ t.Fatalf("CallTool: %v", err)
+ }
+ if len(ch.proposedRoleConfigs) != 1 {
+ t.Fatalf("expected 1 proposed role config, got %d", len(ch.proposedRoleConfigs))
+ }
+ cfg := ch.proposedRoleConfigs[0]
+ if cfg.Role != "builder" || cfg.SystemPrompt != "Double-check edge cases before finishing." {
+ t.Errorf("role config not propagated: %+v", cfg)
+ }
+ if len(cfg.EscalationLadder) != 1 || len(cfg.EscalationLadder[0].Candidates) != 1 ||
+ cfg.EscalationLadder[0].Candidates[0].Provider != "anthropic" || cfg.EscalationLadder[0].Candidates[0].Model != "claude-sonnet-4-6" {
+ t.Errorf("escalation_ladder not propagated: %+v", cfg.EscalationLadder)
+ }
+ if txt := resultText(t, res); !strings.Contains(txt, "builder") || !strings.Contains(txt, "3") {
+ t.Errorf("expected role name and version in result, got %q", txt)
+ }
+}
+
type bearerRT struct {
token string
base http.RoundTripper