fix(project_create): commit staging namespace directly to infra main

Drops the intermediate `staging/<name>` branch so Flux begins reconciling the
namespace within ~60s of `project_create` instead of waiting on a human PR
merge. Consistent with project-wide trunk-based development.

Rationale: ADR 2026-05-18 in DECISIONS.md.

Closes hyperguild#14 (item 1). Item 2 (GITEA_MCP_TOKEN in SOPS) verified
already-present in infra@408a527 secrets.enc.yaml.

Note: TestRoutingPodEndToEnd is failing on main pre-existing this commit
(context deadline waiting for port 33310 in <5s). Not caused by this change;
project skill tests pass. To track in a separate issue.

DECISIONS.md

@@ -118,3 +118,24 @@ When berget.ai tokens run out, flip `BRAIN_LLM_PRIMARY_URL` to iguana.
 **Decision**: The root context-sync generates a `mathias.md` prompt and `mathias.toml` agent config in `~/.vibe/`. This is the one tool that needs a custom adapter path.
 
 **Consequences**: Run `vibe --agent mathias` to use your conventions. Other Vibe users on the machine aren't affected.
+
+---
+
+## 2026-05-18 — project_create commits staging namespace directly to infra main
+
+**Context:** `project_create` writes a k8s namespace manifest into the infra
+repo so Flux brings up a staging environment for the new project. Initial
+implementation pushed to a `staging/<name>` branch, which required manual PR
+merge before Flux saw the namespace — defeating the "one tool call, project
+exists, staging reconciling within 60s" goal.
+
+**Decision:** Option A — commit directly to `main`. `callInfraCommit` passes
+`branch: "main"` to gitea-mcp's `file_write_branch`; no PR, no merge step.
+
+**Consequences:** Staging namespace appears in cluster within ~60s of the
+`project_create` call. Consistent with project-wide TBD policy (CLAUDE.md):
+commit directly to main, every commit deployable. Acceptable because the
+manifest is a fresh namespace under `k3s/staging/<name>/` — isolated, low
+blast-radius, and Flux will simply recreate it if the file is bad. Manual
+review gating was friction for no compensating safety gain on experiment
+namespaces.

internal/skills/project/handlers.go

@@ -97,8 +97,7 @@ func (s *Skill) handleCreate(ctx context.Context, raw json.RawMessage) (json.Raw
 
 	// Step 3: commit staging namespace manifest to infra repo. Done before
 	// the issue so the staging env is reconciling by the time the issue lands.
-	branch := fmt.Sprintf("staging/%s", args.Name)
+	if err := s.callInfraCommit(ctx, args.Name); err != nil {
-	if err := s.callInfraCommit(ctx, args.Name, branch); err != nil {
 		if !isConflict(err) {
 			return marshalPartial(res, stepInfraCommit, err)
 		}
@@ -171,17 +170,16 @@ func (s *Skill) callMirror(ctx context.Context, name string) error {
 	}, nil)
 }
 
-// callInfraCommit writes the staging namespace manifest into the infra repo
+// callInfraCommit writes the staging namespace manifest directly to infra
-// on a dedicated branch. Flux picks it up after merge.
+// main. Flux reconciles within ~60s. See DECISIONS.md 2026-05-18.
-func (s *Skill) callInfraCommit(ctx context.Context, name, branch string) error {
+func (s *Skill) callInfraCommit(ctx context.Context, name string) error {
 	manifest := stagingNamespaceManifest(name, time.Now().UTC().Format(time.RFC3339))
 	return s.cfg.Client.CallTool(ctx, "file_write_branch", map[string]any{
 		"owner":   s.cfg.GiteaOwner,
 		"name":    s.cfg.InfraRepo,
 		"path":    fmt.Sprintf("k3s/staging/%s/namespace.yaml", name),
 		"content": manifest,
-		"branch":  branch,
+		"branch":  "main",
-		"base":    "main",
 		"message": fmt.Sprintf("feat(staging): add namespace for %s\n\nGenerated by hyperguild project_create.", name),
 	}, nil)
 }