feat(engine): add opencode CLI review engine

Add a third review harness alongside the in-process majordomo loop and the claude-code CLI shell-out: the OpenCode CLI (opencode.ai) driving an ollama-cloud model, selected by an "opencode/<model>" spec. The goal is to benchmark gadfly's boutique executus harness against a freely-available agentic harness on the SAME model (e.g. "ollama-cloud/glm-5.2" vs "opencode/glm-5.2"). OpenCode has no --append-system-prompt flag, so the lens system prompt and the read-only discipline are delivered through a generated config injected via OPENCODE_CONFIG_CONTENT: a "gadfly" agent whose prompt is the system prompt with edit/bash denied at both the global and agent level, plus a "gadfly" ollama-cloud provider. That env var is the highest-precedence config source in the container, so a reviewed repo's own opencode.json can't re-enable edits on the reviewer. Spec forms: "opencode/<model>" (wrapped in the generated provider), the "open-code/" alias, "opencode/<provider>/<model>" pass-through to OpenCode's own registry, and bare "opencode". Model ids are taken verbatim so colon-bearing ollama ids (qwen3-coder:480b-cloud) survive. Auth reuses OLLAMA_CLOUD_API_KEY (mapped to OLLAMA_API_KEY, referenced as {env:OLLAMA_API_KEY} in config, never a literal secret). Knobs mirror GADFLY_CLAUDE_*: GADFLY_OPENCODE_BIN/MODEL/BASE_URL/ EXTRA_ARGS. openCodeEnv() forwards OLLAMA_API_KEY (the inverse of claudeEnv) but still withholds the Gitea/findings/Anthropic secrets. main.go engine selection is now a switch (claude-code / opencode / majordomo), and the auto-select path uses a type-check instead of a boolean so a shell-out engine can never hit the *majordomoEngine assertion. auto-select and delegate_investigation stay majordomo-only and are skipped for opencode (the CLI does its own legwork). Dockerfile bundles opencode-ai (npm auto-selects its musl build on alpine) with a best-effort version check + provider pre-warm that never fails the shared image build. README/examples/CLAUDE.md/scripts updated per the maintenance rules. Tests: new opencode_test.go mirrors engine_test.go (spec/model/args/config/env- filter + stub-CLI runtime tests). Verified end-to-end with a fake opencode CLI: correct argv, injected config, and consolidated markdown output. Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
2026-07-18 01:00:54 -04:00
parent f468fe6245
commit 5ab4074e9c
12 changed files with 753 additions and 16 deletions
@@ -19,16 +19,19 @@ import (
 // the model's text answer. It is the one primitive both review passes use — the
 // draft review and the adversarial recheck — so the rest of the pipeline
 // (specialist composition, recheck orchestration, consolidation, emit) is
-// engine-agnostic. Two implementations:
+// engine-agnostic. Three implementations:
 //
 //   - majordomoEngine: the original path — a majordomo tool-using agent loop
 //     (read_file/grep/… over a sandboxed repoFS).
 //   - claudeCodeEngine: shells out to the `claude` CLI in print mode, which
 //     brings its OWN repo tools; gadfly just feeds it the prompt and reads back
 //     the final text.
+//   - openCodeEngine (opencode.go): shells out to the `opencode` CLI likewise,
+//     but driving an ollama-cloud model — for benchmarking the two harnesses on
+//     the same model.
 //
 // maxSteps is the tool-step budget for engines that have one (majordomo); the
-// claude-code engine manages its own loop and ignores it.
+// shell-out engines manage their own loop and ignore it.
 type reviewEngine interface {
 	runPass(ctx context.Context, system, task string, maxSteps int) (string, error)
 }
@@ -22,7 +22,11 @@
 //
 //	GADFLY_MODEL          model id, or a full "provider/model" spec / majordomo
 //	                        alias / failover chain (required). A bare id is
-//	                        prefixed with GADFLY_PROVIDER.
+//	                        prefixed with GADFLY_PROVIDER. Two prefixes select a
+//	                        shell-out CLI engine instead of the in-process loop:
+//	                        "claude-code/<model>" (Claude Code, see engine.go) and
+//	                        "opencode/<model>" (OpenCode over ollama-cloud, see
+//	                        opencode.go) — both bring their own repo tools.
 //	GADFLY_PROVIDER       provider for bare model ids (default "ollama-cloud";
 //	                        e.g. "ollama" for a local daemon, "openai", …).
 //	GADFLY_BASE_URL       override the backend endpoint (OpenAI/Ollama-compatible
@@ -147,15 +151,18 @@ func run() error {
 		return err
 	}

-	// Resolve the review engine. The claude-code engine shells out to the
-	// `claude` CLI (its own repo tools); every other spec is a majordomo model.
-	// auto-selection and the delegate worker are majordomo-only — with
-	// claude-code they're skipped (Claude Code does its own legwork).
-	ccSpec := isClaudeCodeSpec(os.Getenv("GADFLY_MODEL"))
+	// Resolve the review engine. The shell-out engines (claude-code, opencode)
+	// bring their OWN repo tools; every other spec is an in-process majordomo
+	// model. auto-selection and the delegate worker are majordomo-only — with a
+	// shell-out engine they're skipped (the CLI does its own legwork).
+	spec := os.Getenv("GADFLY_MODEL")
 	var eng reviewEngine
-	if ccSpec {
-		eng = newClaudeCodeEngine(os.Getenv("GADFLY_MODEL"), fsTools.root)
-	} else {
+	switch {
+	case isClaudeCodeSpec(spec):
+		eng = newClaudeCodeEngine(spec, fsTools.root)
+	case isOpenCodeSpec(spec):
+		eng = newOpenCodeEngine(spec, fsTools.root)
+	default:
 		mdl, merr := resolveModel()
 		if merr != nil {
 			return fmt.Errorf("resolve model: %w", merr)
@@ -187,13 +194,15 @@ func run() error {
 	}

 	// Dynamic selection: a (cheap) model picks the lenses this diff needs.
-	// Majordomo-only — the selector is an llm.Model.
+	// Majordomo-only — the selector is an llm.Model, so a shell-out engine
+	// (claude-code, opencode) can't provide one; fall back to the default suite.
 	if auto {
-		if ccSpec {
-			fmt.Fprintln(os.Stderr, "gadfly: auto-select is not supported with the claude-code engine; using the default suite")
+		md, ok := eng.(*majordomoEngine)
+		if !ok {
+			fmt.Fprintln(os.Stderr, "gadfly: auto-select requires an in-process model engine; using the default suite")
 			specialists = suiteFromRegistry(registry, defaultSuite)
 		} else {
-			selector, serr := resolveSelectorModel(eng.(*majordomoEngine).mdl)
+			selector, serr := resolveSelectorModel(md.mdl)
 			if serr != nil {
 				return fmt.Errorf("resolve selector model: %w", serr)
 			}
@@ -0,0 +1,265 @@
+package main
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"os"
+	"os/exec"
+	"strings"
+	"syscall"
+)
+
+// openCodeEngine reviews by shelling out to the `opencode` CLI (opencode.ai) in
+// non-interactive `run` mode. Like the claude-code engine it is a pure shell-out
+// — OpenCode brings its OWN read tools (read/grep/glob/list) and reads the
+// checked-out tree, so findings are verified against real code — but it drives an
+// ollama-cloud model instead of a Claude subscription. The point is to benchmark
+// gadfly's boutique executus harness against a freely-available agentic harness
+// on the SAME models (e.g. "ollama-cloud/glm-5.2" vs "opencode/glm-5.2").
+//
+// OpenCode has no --append-system-prompt flag, so the lens system prompt AND the
+// read-only discipline are delivered through a generated config injected via the
+// OPENCODE_CONFIG_CONTENT env var (see config): a custom "gadfly" agent whose
+// prompt is the system prompt with edit/bash denied, plus a "gadfly" provider
+// pointing at ollama-cloud. OPENCODE_CONFIG_CONTENT is the highest-precedence
+// config source that matters in the container — it outranks any opencode.json a
+// reviewed repo might ship — so a repo can't re-enable edits on us.
+type openCodeEngine struct {
+	bin           string   // CLI binary (GADFLY_OPENCODE_BIN, default "opencode")
+	providerModel string   // ollama model id for the generated "gadfly" provider ("" = none)
+	modelRef      string   // --model value ("gadfly/<id>", a pass-through "<prov>/<id>", or "" = CLI default)
+	baseURL       string   // ollama-cloud base URL (GADFLY_OPENCODE_BASE_URL)
+	repoDir       string   // cwd for the CLI, so its tools read the checked-out tree
+	extraArgs     []string // appended verbatim (GADFLY_OPENCODE_EXTRA_ARGS)
+}
+
+const (
+	// openCodeProviderName / openCodeAgentName are the internal names of the
+	// provider and agent gadfly generates in the injected config. "gadfly" won't
+	// collide with OpenCode's models.dev provider registry.
+	openCodeProviderName = "gadfly"
+	openCodeAgentName    = "gadfly"
+	// defaultOpenCodeBaseURL is ollama-cloud's OpenAI-compatible endpoint.
+	defaultOpenCodeBaseURL = "https://ollama.com/v1"
+)
+
+// isOpenCodeSpec reports whether a GADFLY_MODEL spec selects the opencode engine:
+// the bare id "opencode"/"open-code" or an "opencode/<model>" form (both
+// spellings accepted; "opencode" is canonical).
+func isOpenCodeSpec(model string) bool {
+	m := strings.TrimSpace(model)
+	for _, p := range []string{"opencode", "open-code"} {
+		if m == p || strings.HasPrefix(m, p+"/") {
+			return true
+		}
+	}
+	return false
+}
+
+// newOpenCodeEngine builds the engine from the GADFLY_MODEL spec and the optional
+// GADFLY_OPENCODE_* overrides. The part after the FIRST slash is the model, taken
+// verbatim — no ":"-suffix parsing, because ollama model ids legitimately contain
+// colons (e.g. "qwen3-coder:480b-cloud"). Three spec forms:
+//
+//	opencode                    → bare: no --model, no generated provider (CLI default model)
+//	opencode/<model>            → wrap <model> in the generated ollama-cloud "gadfly" provider
+//	opencode/<provider>/<model> → pass-through: --model <provider>/<model>, using OpenCode's
+//	                              own provider registry/auth (escape hatch, no generated provider)
+//
+// GADFLY_OPENCODE_MODEL overrides the model taken from the spec (and is itself run
+// through the same slash logic). It does not verify the CLI is installed — a
+// missing binary surfaces as a normal pass error (advisory, never fatal).
+func newOpenCodeEngine(spec, repoDir string) *openCodeEngine {
+	e := &openCodeEngine{
+		bin:       envOr("GADFLY_OPENCODE_BIN", "opencode"),
+		baseURL:   envOr("GADFLY_OPENCODE_BASE_URL", defaultOpenCodeBaseURL),
+		repoDir:   repoDir,
+		extraArgs: strings.Fields(os.Getenv("GADFLY_OPENCODE_EXTRA_ARGS")),
+	}
+	var after string
+	if _, a, ok := strings.Cut(strings.TrimSpace(spec), "/"); ok {
+		after = strings.TrimSpace(a)
+	}
+	if env := strings.TrimSpace(os.Getenv("GADFLY_OPENCODE_MODEL")); env != "" {
+		after = env
+	}
+	switch {
+	case after == "":
+		// bare spec: let OpenCode's configured default model apply.
+	case strings.Contains(after, "/"):
+		// "<provider>/<model>" pass-through to an OpenCode built-in provider.
+		e.modelRef = after
+	default:
+		// A bare model id → serve it via the generated ollama-cloud provider.
+		e.providerModel = after
+		e.modelRef = openCodeProviderName + "/" + after
+	}
+	return e
+}
+
+// args assembles the `opencode` argv for one pass. Factored out (and pure) so it
+// can be unit-tested without invoking the CLI. The task is the positional message
+// and MUST come last; it never begins with '-' (buildTask output starts with "PR
+// title:"/"Review …"), so no "--" terminator is needed. Note: in `opencode run`,
+// -p is basic-auth password, NOT the prompt — the message is positional.
+func (e *openCodeEngine) args(task string) []string {
+	a := []string{"run", "--agent", openCodeAgentName}
+	if e.modelRef != "" {
+		a = append(a, "--model", e.modelRef)
+	}
+	a = append(a, e.extraArgs...)
+	return append(a, task)
+}
+
+// openCode config structs — the minimal shape gadfly generates. Marshaled to JSON
+// and handed to the CLI via OPENCODE_CONFIG_CONTENT.
+type openCodeConfig struct {
+	Schema     string                      `json:"$schema"`
+	Permission openCodePermission          `json:"permission"`
+	Provider   map[string]openCodeProvider `json:"provider,omitempty"`
+	Agent      map[string]openCodeAgent    `json:"agent"`
+}
+
+type openCodePermission struct {
+	Edit string `json:"edit"`
+	Bash string `json:"bash"`
+}
+
+type openCodeProvider struct {
+	NPM     string                  `json:"npm"`
+	Name    string                  `json:"name"`
+	Options openCodeProviderOptions `json:"options"`
+	Models  map[string]struct{}     `json:"models"`
+}
+
+type openCodeProviderOptions struct {
+	BaseURL string `json:"baseURL"`
+	APIKey  string `json:"apiKey"`
+}
+
+type openCodeAgent struct {
+	Description string             `json:"description"`
+	Mode        string             `json:"mode"`
+	Prompt      string             `json:"prompt"`
+	Permission  openCodePermission `json:"permission"`
+}
+
+// config builds the OpenCode config JSON for one pass. The system prompt becomes
+// the "gadfly" agent's prompt; edit/bash are denied at BOTH the global and agent
+// level (defense in depth — OpenCode's read-only tools stay available). For a
+// bare or pass-through spec the generated ollama-cloud provider block is omitted.
+// The API key is always the "{env:OLLAMA_API_KEY}" reference, never a literal
+// secret baked into the config.
+func (e *openCodeEngine) config(system string) ([]byte, error) {
+	deny := openCodePermission{Edit: "deny", Bash: "deny"}
+	cfg := openCodeConfig{
+		Schema:     "https://opencode.ai/config.json",
+		Permission: deny,
+		Agent: map[string]openCodeAgent{
+			openCodeAgentName: {
+				Description: "Gadfly adversarial code-review lens (read-only).",
+				Mode:        "primary",
+				Prompt:      system,
+				Permission:  deny,
+			},
+		},
+	}
+	if e.providerModel != "" {
+		cfg.Provider = map[string]openCodeProvider{
+			openCodeProviderName: {
+				NPM:  "@ai-sdk/openai-compatible",
+				Name: openCodeProviderName,
+				Options: openCodeProviderOptions{
+					BaseURL: e.baseURL,
+					APIKey:  "{env:OLLAMA_API_KEY}",
+				},
+				Models: map[string]struct{}{e.providerModel: {}},
+			},
+		}
+	}
+	return json.Marshal(cfg)
+}
+
+func (e *openCodeEngine) runPass(ctx context.Context, system, task string, _ int) (string, error) {
+	cfg, err := e.config(system)
+	if err != nil {
+		return "", fmt.Errorf("opencode config: %w", err)
+	}
+	cmd := exec.CommandContext(ctx, e.bin, e.args(task)...)
+	cmd.Dir = e.repoDir
+	// Inject the review config (system prompt as the agent prompt + read-only
+	// permissions + the ollama-cloud provider) via OPENCODE_CONFIG_CONTENT, which
+	// outranks any opencode.json the reviewed repo itself ships. NO_COLOR keeps the
+	// captured stdout free of ANSI decoration.
+	cmd.Env = append(openCodeEnv(), "OPENCODE_CONFIG_CONTENT="+string(cfg), "NO_COLOR=1")
+	// Put the CLI and the Node children it spawns in their own process group and
+	// kill the WHOLE group on context cancel, so a timed-out lens can't leave
+	// orphaned opencode/node processes behind in the container.
+	cmd.SysProcAttr = &syscall.SysProcAttr{Setpgid: true}
+	cmd.Cancel = func() error {
+		if cmd.Process != nil {
+			_ = syscall.Kill(-cmd.Process.Pid, syscall.SIGKILL)
+		}
+		return nil
+	}
+	var stdout, stderr bytes.Buffer
+	cmd.Stdout = &stdout
+	cmd.Stderr = &stderr
+
+	runErr := cmd.Run()
+
+	// A cancelled/timed-out run must surface as an error, never as whatever partial
+	// bytes the CLI flushed before it was killed.
+	if ctx.Err() != nil {
+		return "", fmt.Errorf("opencode run %v", ctx.Err())
+	}
+	if runErr != nil {
+		detail := truncateForErr(stderr.String())
+		if detail == "" {
+			detail = truncateForErr(stdout.String())
+		}
+		if detail != "" {
+			return "", fmt.Errorf("opencode run failed: %v: %s", runErr, detail)
+		}
+		return "", fmt.Errorf("opencode run failed: %v", runErr)
+	}
+	// OpenCode's default (non-JSON) format prints the assistant's final text; trust
+	// it as the review. An empty result on a clean exit is an error, never "".
+	if out := strings.TrimSpace(stdout.String()); out != "" {
+		return out, nil
+	}
+	return "", fmt.Errorf("opencode run returned no output")
+}
+
+// openCodeEnv builds a minimal environment for the `opencode` subprocess: only
+// what the CLI needs (PATH/HOME, locale, Node/XDG/OPENCODE_*/GADFLY_OPENCODE_*
+// knobs) plus OLLAMA_API_KEY — which the generated provider references and which
+// claudeEnv deliberately DROPS. The runner's other secrets (GITEA_TOKEN,
+// GADFLY_FINDINGS_TOKEN, Anthropic/Claude keys) are withheld — the CLI has no need
+// for them. OPENCODE_CONFIG_CONTENT is never inherited: runPass sets it, and a
+// duplicate key would be ambiguous (getenv returns the first occurrence).
+func openCodeEnv() []string {
+	keep := func(k string) bool {
+		if k == "OPENCODE_CONFIG_CONTENT" {
+			return false // set explicitly by runPass; never inherit a competing value
+		}
+		switch k {
+		case "PATH", "HOME", "USER", "LOGNAME", "TMPDIR", "LANG", "TERM", "SHELL", "OLLAMA_API_KEY":
+			return true
+		}
+		return strings.HasPrefix(k, "LC_") ||
+			strings.HasPrefix(k, "OPENCODE_") ||
+			strings.HasPrefix(k, "GADFLY_OPENCODE_") ||
+			strings.HasPrefix(k, "NODE_") ||
+			strings.HasPrefix(k, "XDG_")
+	}
+	var env []string
+	for _, kv := range os.Environ() {
+		if k, _, ok := strings.Cut(kv, "="); ok && keep(k) {
+			env = append(env, kv)
+		}
+	}
+	return env
+}
@@ -0,0 +1,297 @@
+package main
+
+import (
+	"context"
+	"encoding/json"
+	"os"
+	"slices"
+	"strings"
+	"testing"
+)
+
+func TestIsOpenCodeSpec(t *testing.T) {
+	cases := map[string]bool{
+		"opencode":                        true,
+		"opencode/glm-5.2":                true,
+		"open-code/glm-5.2":               true,  // accepted alias spelling
+		"opencode/qwen3-coder:480b-cloud": true,  // colon-bearing model id
+		"opencode/anthropic/claude":       true,  // pass-through form
+		"  opencode  ":                    true,  // trimmed
+		"opencode-extra":                  false, // not the bare id, not a "/" form
+		"qwen3-coder:480b-cloud":          false,
+		"claude-code/opus":                false,
+		"":                                false,
+	}
+	for spec, want := range cases {
+		if got := isOpenCodeSpec(spec); got != want {
+			t.Errorf("isOpenCodeSpec(%q) = %v, want %v", spec, got, want)
+		}
+	}
+}
+
+func TestNewOpenCodeEngineModel(t *testing.T) {
+	t.Setenv("GADFLY_OPENCODE_MODEL", "")
+
+	// "opencode/<model>" → wrapped in the generated "gadfly" provider.
+	if e := newOpenCodeEngine("opencode/glm-5.2", "/repo"); e.providerModel != "glm-5.2" || e.modelRef != "gadfly/glm-5.2" {
+		t.Errorf("glm-5.2: providerModel=%q modelRef=%q, want glm-5.2 / gadfly/glm-5.2", e.providerModel, e.modelRef)
+	}
+	// Colon-bearing ollama id is preserved verbatim — NOT split on ":".
+	if e := newOpenCodeEngine("opencode/qwen3-coder:480b-cloud", "/repo"); e.providerModel != "qwen3-coder:480b-cloud" {
+		t.Errorf("colon id: providerModel=%q, want qwen3-coder:480b-cloud (no split)", e.providerModel)
+	}
+	// "open-code/" spelling behaves identically.
+	if e := newOpenCodeEngine("open-code/glm-5.2", "/repo"); e.modelRef != "gadfly/glm-5.2" {
+		t.Errorf("open-code alias: modelRef=%q, want gadfly/glm-5.2", e.modelRef)
+	}
+	// Pass-through "opencode/<provider>/<model>" → no generated provider.
+	if e := newOpenCodeEngine("opencode/anthropic/claude-sonnet-4-6", "/repo"); e.providerModel != "" || e.modelRef != "anthropic/claude-sonnet-4-6" {
+		t.Errorf("pass-through: providerModel=%q modelRef=%q, want '' / anthropic/claude-sonnet-4-6", e.providerModel, e.modelRef)
+	}
+	// Bare spec → no model, no provider (CLI default applies).
+	if e := newOpenCodeEngine("opencode", "/repo"); e.providerModel != "" || e.modelRef != "" {
+		t.Errorf("bare: providerModel=%q modelRef=%q, want both empty", e.providerModel, e.modelRef)
+	}
+	// GADFLY_OPENCODE_MODEL overrides the spec suffix.
+	t.Setenv("GADFLY_OPENCODE_MODEL", "deepseek-v3")
+	if e := newOpenCodeEngine("opencode/glm-5.2", "/repo"); e.providerModel != "deepseek-v3" || e.modelRef != "gadfly/deepseek-v3" {
+		t.Errorf("env override: providerModel=%q modelRef=%q, want deepseek-v3 / gadfly/deepseek-v3", e.providerModel, e.modelRef)
+	}
+}
+
+func TestOpenCodeEngineDefaults(t *testing.T) {
+	t.Setenv("GADFLY_OPENCODE_BIN", "")
+	t.Setenv("GADFLY_OPENCODE_BASE_URL", "")
+	t.Setenv("GADFLY_OPENCODE_EXTRA_ARGS", "")
+	e := newOpenCodeEngine("opencode/glm-5.2", "/repo")
+	if e.bin != "opencode" {
+		t.Errorf("bin = %q, want opencode", e.bin)
+	}
+	if e.baseURL != defaultOpenCodeBaseURL {
+		t.Errorf("baseURL = %q, want %q", e.baseURL, defaultOpenCodeBaseURL)
+	}
+	if e.repoDir != "/repo" {
+		t.Errorf("repoDir = %q, want /repo", e.repoDir)
+	}
+}
+
+func TestOpenCodeArgs(t *testing.T) {
+	t.Setenv("GADFLY_OPENCODE_MODEL", "")
+	t.Setenv("GADFLY_OPENCODE_EXTRA_ARGS", "--variant reasoning")
+	e := newOpenCodeEngine("opencode/glm-5.2", "/repo")
+	args := e.args("TASK-PROMPT")
+
+	// "run" is the subcommand and must be first.
+	if len(args) == 0 || args[0] != "run" {
+		t.Fatalf("args[0] = %q, want run (args=%v)", args, args)
+	}
+	if argAfter(args, "--agent") != openCodeAgentName {
+		t.Errorf("--agent = %q, want %q", argAfter(args, "--agent"), openCodeAgentName)
+	}
+	if argAfter(args, "--model") != "gadfly/glm-5.2" {
+		t.Errorf("--model = %q, want gadfly/glm-5.2", argAfter(args, "--model"))
+	}
+	// extra args appended verbatim (split on whitespace).
+	if !strings.Contains(strings.Join(args, " "), "--variant reasoning") {
+		t.Errorf("extra args not appended: %v", args)
+	}
+	// task is the positional message and must be LAST.
+	if args[len(args)-1] != "TASK-PROMPT" {
+		t.Errorf("last arg = %q, want TASK-PROMPT (args=%v)", args[len(args)-1], args)
+	}
+}
+
+func TestOpenCodeArgsBareModelOmitsFlag(t *testing.T) {
+	t.Setenv("GADFLY_OPENCODE_MODEL", "")
+	t.Setenv("GADFLY_OPENCODE_EXTRA_ARGS", "")
+	e := newOpenCodeEngine("opencode", "/repo")
+	args := e.args("t")
+	if slices.Contains(args, "--model") {
+		t.Errorf("--model should be omitted for a bare opencode spec: %v", args)
+	}
+	if args[len(args)-1] != "t" {
+		t.Errorf("last arg = %q, want t", args[len(args)-1])
+	}
+}
+
+func TestOpenCodeConfig(t *testing.T) {
+	t.Setenv("GADFLY_OPENCODE_MODEL", "")
+	t.Setenv("GADFLY_OPENCODE_BASE_URL", "")
+
+	// Round-trip a system prompt containing quotes and newlines.
+	sys := "Line one with \"quotes\".\nLine two."
+	e := newOpenCodeEngine("opencode/glm-5.2", "/repo")
+	raw, err := e.config(sys)
+	if err != nil {
+		t.Fatalf("config: %v", err)
+	}
+	var cfg openCodeConfig
+	if err := json.Unmarshal(raw, &cfg); err != nil {
+		t.Fatalf("generated config is not valid JSON: %v\n%s", err, raw)
+	}
+
+	// Agent carries the system prompt verbatim and denies edit+bash.
+	ag, ok := cfg.Agent[openCodeAgentName]
+	if !ok {
+		t.Fatalf("agent %q missing from config", openCodeAgentName)
+	}
+	if ag.Prompt != sys {
+		t.Errorf("agent prompt = %q, want it to round-trip the system prompt", ag.Prompt)
+	}
+	if ag.Permission.Edit != "deny" || ag.Permission.Bash != "deny" {
+		t.Errorf("agent permission = %+v, want edit/bash deny", ag.Permission)
+	}
+	// Global permission also denies (defense in depth).
+	if cfg.Permission.Edit != "deny" || cfg.Permission.Bash != "deny" {
+		t.Errorf("global permission = %+v, want edit/bash deny", cfg.Permission)
+	}
+
+	// Provider block: correct npm, default baseURL, env-ref apiKey, model in map.
+	prov, ok := cfg.Provider[openCodeProviderName]
+	if !ok {
+		t.Fatalf("provider %q missing from config", openCodeProviderName)
+	}
+	if prov.NPM != "@ai-sdk/openai-compatible" {
+		t.Errorf("provider npm = %q, want @ai-sdk/openai-compatible", prov.NPM)
+	}
+	if prov.Options.BaseURL != defaultOpenCodeBaseURL {
+		t.Errorf("provider baseURL = %q, want %q", prov.Options.BaseURL, defaultOpenCodeBaseURL)
+	}
+	if prov.Options.APIKey != "{env:OLLAMA_API_KEY}" {
+		t.Errorf("provider apiKey = %q, want {env:OLLAMA_API_KEY} (never a literal secret)", prov.Options.APIKey)
+	}
+	if _, ok := prov.Models["glm-5.2"]; !ok {
+		t.Errorf("provider models = %v, want it to contain glm-5.2", prov.Models)
+	}
+
+	// GADFLY_OPENCODE_BASE_URL override reaches the provider.
+	t.Setenv("GADFLY_OPENCODE_BASE_URL", "http://localhost:11434/v1")
+	e2 := newOpenCodeEngine("opencode/glm-5.2", "/repo")
+	raw2, err := e2.config(sys)
+	if err != nil {
+		t.Fatalf("config override: %v", err)
+	}
+	var cfg2 openCodeConfig
+	if err := json.Unmarshal(raw2, &cfg2); err != nil {
+		t.Fatalf("override config invalid JSON: %v", err)
+	}
+	if got := cfg2.Provider[openCodeProviderName].Options.BaseURL; got != "http://localhost:11434/v1" {
+		t.Errorf("override baseURL = %q, want http://localhost:11434/v1", got)
+	}
+}
+
+func TestOpenCodeConfigNoProviderForPassThroughAndBare(t *testing.T) {
+	t.Setenv("GADFLY_OPENCODE_MODEL", "")
+	for _, spec := range []string{"opencode", "opencode/anthropic/claude-sonnet-4-6"} {
+		e := newOpenCodeEngine(spec, "/repo")
+		raw, err := e.config("sys")
+		if err != nil {
+			t.Fatalf("config(%q): %v", spec, err)
+		}
+		if strings.Contains(string(raw), "\"provider\"") {
+			t.Errorf("spec %q: config should omit the provider block, got %s", spec, raw)
+		}
+	}
+}
+
+func TestOpenCodeEnvFilters(t *testing.T) {
+	t.Setenv("GITEA_TOKEN", "secret-gitea")
+	t.Setenv("OLLAMA_API_KEY", "keep-ollama")
+	t.Setenv("GADFLY_API_KEY", "secret-gadfly")
+	t.Setenv("GADFLY_FINDINGS_TOKEN", "secret-findings")
+	t.Setenv("ANTHROPIC_API_KEY", "secret-anthropic")
+	t.Setenv("CLAUDE_CODE_OAUTH_TOKEN", "secret-claude")
+	t.Setenv("GADFLY_OPENCODE_MODEL", "keep-knob")
+	t.Setenv("OPENCODE_CONFIG_CONTENT", "should-not-inherit")
+
+	env := openCodeEnv()
+	has := func(k string) bool {
+		for _, kv := range env {
+			if strings.HasPrefix(kv, k+"=") {
+				return true
+			}
+		}
+		return false
+	}
+	// kept: the ollama key the provider references + opencode knobs + PATH
+	for _, k := range []string{"OLLAMA_API_KEY", "GADFLY_OPENCODE_MODEL", "PATH"} {
+		if !has(k) {
+			t.Errorf("openCodeEnv dropped %s, but it should be kept", k)
+		}
+	}
+	// dropped: the runner's other secrets + the claude engine's auth
+	for _, k := range []string{"GITEA_TOKEN", "GADFLY_API_KEY", "GADFLY_FINDINGS_TOKEN", "ANTHROPIC_API_KEY", "CLAUDE_CODE_OAUTH_TOKEN"} {
+		if has(k) {
+			t.Errorf("openCodeEnv leaked %s into the subprocess env", k)
+		}
+	}
+	// OPENCODE_CONFIG_CONTENT must NOT be inherited — runPass sets it, and a
+	// duplicate key would be ambiguous.
+	if has("OPENCODE_CONFIG_CONTENT") {
+		t.Errorf("openCodeEnv inherited OPENCODE_CONFIG_CONTENT; runPass sets it explicitly")
+	}
+}
+
+// stubOpenCode writes an executable shell stub that prints body and exits code,
+// and returns an engine pointed at it.
+func stubOpenCode(t *testing.T, body string, code int) *openCodeEngine {
+	t.Helper()
+	dir := t.TempDir()
+	path := dir + "/opencode-stub.sh"
+	script := "#!/bin/sh\nprintf '%s' " + shSingleQuote(body) + "\nexit " + itoa(code) + "\n"
+	if err := os.WriteFile(path, []byte(script), 0o755); err != nil {
+		t.Fatal(err)
+	}
+	return &openCodeEngine{bin: path, repoDir: dir}
+}
+
+func TestOpenCodeRunPassCleanResult(t *testing.T) {
+	e := stubOpenCode(t, "  REVIEW TEXT  ", 0)
+	out, err := e.runPass(context.Background(), "sys", "task", 0)
+	if err != nil || out != "REVIEW TEXT" {
+		t.Fatalf("clean result: got (%q, %v), want (REVIEW TEXT, nil)", out, err)
+	}
+}
+
+func TestOpenCodeRunPassEmptyIsError(t *testing.T) {
+	e := stubOpenCode(t, "   ", 0)
+	out, err := e.runPass(context.Background(), "sys", "task", 0)
+	if err == nil {
+		t.Fatalf("empty output should be an error, got out=%q", out)
+	}
+}
+
+func TestOpenCodeRunPassNonZero(t *testing.T) {
+	e := stubOpenCode(t, "fatal: provider auth failed", 1)
+	_, err := e.runPass(context.Background(), "sys", "task", 0)
+	if err == nil || !strings.Contains(err.Error(), "opencode run failed") {
+		t.Fatalf("non-zero exit should error with detail, got %v", err)
+	}
+}
+
+// TestOpenCodeRunPassInjectsConfig proves the end-to-end env plumbing: the stub
+// echoes OPENCODE_CONFIG_CONTENT back, and the emitted JSON must carry the exact
+// system prompt as the gadfly agent's prompt.
+func TestOpenCodeRunPassInjectsConfig(t *testing.T) {
+	dir := t.TempDir()
+	stub := dir + "/opencode-stub.sh"
+	script := "#!/bin/sh\nprintf '%s' \"$OPENCODE_CONFIG_CONTENT\"\n"
+	if err := os.WriteFile(stub, []byte(script), 0o755); err != nil {
+		t.Fatal(err)
+	}
+	e := newOpenCodeEngine("opencode/glm-5.2", dir)
+	e.bin = stub
+
+	sys := "SYSTEM-PROMPT-SENTINEL\nwith a second line"
+	out, err := e.runPass(context.Background(), sys, "task", 0)
+	if err != nil {
+		t.Fatalf("runPass: %v", err)
+	}
+	var cfg openCodeConfig
+	if err := json.Unmarshal([]byte(out), &cfg); err != nil {
+		t.Fatalf("injected config is not valid JSON: %v\n%s", err, out)
+	}
+	if got := cfg.Agent[openCodeAgentName].Prompt; got != sys {
+		t.Errorf("injected agent prompt = %q, want the system prompt", got)
+	}
+}