karajan-code 1.35.0 → 1.36.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +3 -2
- package/docs/README.es.md +3 -2
- package/package.json +1 -1
- package/src/agents/aider-agent.js +16 -9
- package/src/agents/base-agent.js +15 -0
- package/src/agents/claude-agent.js +51 -6
- package/src/agents/codex-agent.js +35 -13
- package/src/agents/gemini-agent.js +17 -9
- package/src/agents/model-registry.js +8 -7
- package/src/agents/opencode-agent.js +17 -10
- package/src/commands/doctor.js +98 -0
- package/src/orchestrator/solomon-escalation.js +11 -2
- package/src/roles/solomon-role.js +17 -1
- package/src/utils/budget.js +12 -8
- package/src/utils/model-selector.js +3 -3
- package/src/utils/stall-detector.js +5 -5
- package/templates/kj.config.yml +3 -0
package/README.md
CHANGED
|
@@ -152,6 +152,7 @@ Use `kj roles show <role>` to inspect any template.
|
|
|
152
152
|
Karajan auto-detects and auto-configures everything it can:
|
|
153
153
|
|
|
154
154
|
- **TDD**: Detects test framework (vitest, jest, mocha) → auto-enables TDD
|
|
155
|
+
- **Bootstrap gate**: Validates all prerequisites (git repo, remote, config, agents, SonarQube) before any tool runs. Fails hard with actionable fix instructions — never silently degrades
|
|
155
156
|
- **SonarQube**: Auto-starts Docker container, generates config if missing
|
|
156
157
|
- **Pipeline complexity**: Triage classifies task → trivial tasks skip reviewer loop
|
|
157
158
|
- **Provider outages**: Retries on 500/502/503/504 with backoff (same as rate limits)
|
|
@@ -163,9 +164,9 @@ No per-project configuration required. If you want to customize, config is layer
|
|
|
163
164
|
|
|
164
165
|
Because it should be.
|
|
165
166
|
|
|
166
|
-
Karajan has **
|
|
167
|
+
Karajan has **1966 tests** across 157 files. It runs on Node.js without a build step. You can read the source, understand it, fork it, and modify it without a TypeScript compiler between you and the code.
|
|
167
168
|
|
|
168
|
-
This is a deliberate choice, not a limitation. The tests are the type safety. The legibility is a feature. **
|
|
169
|
+
This is a deliberate choice, not a limitation. The tests are the type safety. The legibility is a feature. **55 releases in 26 days** — that velocity is possible precisely because vanilla JS with good tests lets you move fast without fear.
|
|
169
170
|
|
|
170
171
|
## Recommended companions
|
|
171
172
|
|
package/docs/README.es.md
CHANGED
|
@@ -29,8 +29,9 @@ En lugar de ejecutar un agente de IA y revisar manualmente su output, `kj` encad
|
|
|
29
29
|
|
|
30
30
|
**Caracteristicas principales:**
|
|
31
31
|
- **Pipeline multi-agente** con 11 roles configurables
|
|
32
|
-
- **
|
|
33
|
-
- **Servidor MCP** con
|
|
32
|
+
- **5 agentes de IA soportados**: Claude, Codex, Gemini, Aider, OpenCode
|
|
33
|
+
- **Servidor MCP** con 20 herramientas — usa `kj` desde Claude, Codex o cualquier host compatible con MCP sin salir de tu agente. [Ver configuracion MCP](#servidor-mcp)
|
|
34
|
+
- **Bootstrap obligatorio** — valida prerequisitos del entorno (git, remote, config, agentes, SonarQube) antes de cada ejecucion. Si algo falta, para con instrucciones claras
|
|
34
35
|
- **TDD obligatorio** — se exigen cambios en tests cuando se modifican ficheros fuente
|
|
35
36
|
- **Integracion con SonarQube** — analisis estatico con quality gates (requiere [Docker](#requisitos))
|
|
36
37
|
- **Perfiles de revision** — standard, strict, relaxed, paranoid
|
package/package.json
CHANGED
|
@@ -5,21 +5,28 @@ import { resolveBin } from "./resolve-bin.js";
|
|
|
5
5
|
export class AiderAgent extends BaseAgent {
|
|
6
6
|
async runTask(task) {
|
|
7
7
|
const role = task.role || "coder";
|
|
8
|
-
const args = ["--yes", "--message", task.prompt];
|
|
9
8
|
const model = this.getRoleModel(role);
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
|
|
13
|
-
|
|
14
|
-
|
|
15
|
-
|
|
16
|
-
return { ok: res.exitCode === 0, output: res.stdout, error: res.stderr, exitCode: res.exitCode };
|
|
9
|
+
const result = await this._exec(task, model);
|
|
10
|
+
if (!result.ok && model && this.isModelNotSupportedError(result)) {
|
|
11
|
+
this.logger?.warn(`Aider model "${model}" not supported — retrying with agent default`);
|
|
12
|
+
return this._exec(task, null);
|
|
13
|
+
}
|
|
14
|
+
return result;
|
|
17
15
|
}
|
|
18
16
|
|
|
19
17
|
async reviewTask(task) {
|
|
20
18
|
const role = task.role || "reviewer";
|
|
21
|
-
const args = ["--yes", "--message", task.prompt];
|
|
22
19
|
const model = this.getRoleModel(role);
|
|
20
|
+
const result = await this._exec(task, model);
|
|
21
|
+
if (!result.ok && model && this.isModelNotSupportedError(result)) {
|
|
22
|
+
this.logger?.warn(`Aider model "${model}" not supported — retrying with agent default`);
|
|
23
|
+
return this._exec(task, null);
|
|
24
|
+
}
|
|
25
|
+
return result;
|
|
26
|
+
}
|
|
27
|
+
|
|
28
|
+
async _exec(task, model) {
|
|
29
|
+
const args = ["--yes", "--message", task.prompt];
|
|
23
30
|
if (model) args.push("--model", model);
|
|
24
31
|
const res = await runCommand(resolveBin("aider"), args, {
|
|
25
32
|
onOutput: task.onOutput,
|
package/src/agents/base-agent.js
CHANGED
|
@@ -1,3 +1,12 @@
|
|
|
1
|
+
const MODEL_NOT_SUPPORTED_PATTERNS = [
|
|
2
|
+
/model.{0,30}is not supported/i,
|
|
3
|
+
/model.{0,30}not available/i,
|
|
4
|
+
/model.{0,30}does not exist/i,
|
|
5
|
+
/unsupported model/i,
|
|
6
|
+
/invalid model/i,
|
|
7
|
+
/model_not_found/i
|
|
8
|
+
];
|
|
9
|
+
|
|
1
10
|
export class BaseAgent {
|
|
2
11
|
constructor(name, config, logger) {
|
|
3
12
|
this.name = name;
|
|
@@ -24,4 +33,10 @@ export class BaseAgent {
|
|
|
24
33
|
if (role === "reviewer") return false;
|
|
25
34
|
return Boolean(this.config?.coder_options?.auto_approve);
|
|
26
35
|
}
|
|
36
|
+
|
|
37
|
+
isModelNotSupportedError(result) {
|
|
38
|
+
const text = [result?.error, result?.output, result?.stderr, result?.stdout]
|
|
39
|
+
.filter(Boolean).join("\n");
|
|
40
|
+
return MODEL_NOT_SUPPORTED_PATTERNS.some(re => re.test(text));
|
|
41
|
+
}
|
|
27
42
|
}
|
|
@@ -35,6 +35,29 @@ function collectAssistantText(obj) {
|
|
|
35
35
|
.map(block => block.text);
|
|
36
36
|
}
|
|
37
37
|
|
|
38
|
+
/**
|
|
39
|
+
* Extract usage metrics from stream-json/json NDJSON output.
|
|
40
|
+
* Looks for the "result" line which contains total_cost_usd,
|
|
41
|
+
* usage.input_tokens/output_tokens, and modelUsage.
|
|
42
|
+
* Returns an object with tokens_in, tokens_out, cost_usd, model or null if not found.
|
|
43
|
+
*/
|
|
44
|
+
export function extractUsageFromStreamJson(raw) {
|
|
45
|
+
const lines = (raw || "").split("\n").filter(Boolean);
|
|
46
|
+
for (let i = lines.length - 1; i >= 0; i--) {
|
|
47
|
+
const obj = tryParseJson(lines[i]);
|
|
48
|
+
if (!obj || obj.type !== "result") continue;
|
|
49
|
+
|
|
50
|
+
const tokens_in = obj.usage?.input_tokens ?? 0;
|
|
51
|
+
const tokens_out = obj.usage?.output_tokens ?? 0;
|
|
52
|
+
const cost_usd = obj.total_cost_usd ?? undefined;
|
|
53
|
+
const modelUsage = obj.modelUsage;
|
|
54
|
+
const model = modelUsage ? Object.keys(modelUsage)[0] || null : null;
|
|
55
|
+
|
|
56
|
+
return { tokens_in, tokens_out, cost_usd, model };
|
|
57
|
+
}
|
|
58
|
+
return null;
|
|
59
|
+
}
|
|
60
|
+
|
|
38
61
|
/**
|
|
39
62
|
* Extract the final text result from stream-json NDJSON output.
|
|
40
63
|
* Each line is a JSON object. We collect assistant text content from
|
|
@@ -135,8 +158,28 @@ const ALLOWED_TOOLS = [
|
|
|
135
158
|
export class ClaudeAgent extends BaseAgent {
|
|
136
159
|
async runTask(task) {
|
|
137
160
|
const role = task.role || "coder";
|
|
138
|
-
const args = ["-p", task.prompt, "--allowedTools", ...ALLOWED_TOOLS];
|
|
139
161
|
const model = this.getRoleModel(role);
|
|
162
|
+
const result = await this._runTaskExec(task, model, role);
|
|
163
|
+
if (!result.ok && model && this.isModelNotSupportedError(result)) {
|
|
164
|
+
this.logger?.warn(`Claude model "${model}" not supported — retrying with agent default`);
|
|
165
|
+
return this._runTaskExec(task, null, role);
|
|
166
|
+
}
|
|
167
|
+
return result;
|
|
168
|
+
}
|
|
169
|
+
|
|
170
|
+
async reviewTask(task) {
|
|
171
|
+
const role = task.role || "reviewer";
|
|
172
|
+
const model = this.getRoleModel(role);
|
|
173
|
+
const result = await this._reviewTaskExec(task, model);
|
|
174
|
+
if (!result.ok && model && this.isModelNotSupportedError(result)) {
|
|
175
|
+
this.logger?.warn(`Claude model "${model}" not supported — retrying with agent default`);
|
|
176
|
+
return this._reviewTaskExec(task, null);
|
|
177
|
+
}
|
|
178
|
+
return result;
|
|
179
|
+
}
|
|
180
|
+
|
|
181
|
+
async _runTaskExec(task, model, role) {
|
|
182
|
+
const args = ["-p", task.prompt, "--allowedTools", ...ALLOWED_TOOLS];
|
|
140
183
|
if (model) args.push("--model", model);
|
|
141
184
|
|
|
142
185
|
// Use stream-json when onOutput is provided to get real-time feedback
|
|
@@ -150,7 +193,8 @@ export class ClaudeAgent extends BaseAgent {
|
|
|
150
193
|
}));
|
|
151
194
|
const raw = pickOutput(res);
|
|
152
195
|
const output = extractTextFromStreamJson(raw);
|
|
153
|
-
|
|
196
|
+
const usage = extractUsageFromStreamJson(raw);
|
|
197
|
+
return { ok: res.exitCode === 0, output, error: res.exitCode === 0 ? "" : raw, exitCode: res.exitCode, ...usage };
|
|
154
198
|
}
|
|
155
199
|
|
|
156
200
|
// Without streaming, use json output to get structured response via stderr
|
|
@@ -158,12 +202,12 @@ export class ClaudeAgent extends BaseAgent {
|
|
|
158
202
|
const res = await runCommand(resolveBin("claude"), args, cleanExecaOpts());
|
|
159
203
|
const raw = pickOutput(res);
|
|
160
204
|
const output = extractTextFromStreamJson(raw);
|
|
161
|
-
|
|
205
|
+
const usage = extractUsageFromStreamJson(raw);
|
|
206
|
+
return { ok: res.exitCode === 0, output, error: res.exitCode === 0 ? "" : raw, exitCode: res.exitCode, ...usage };
|
|
162
207
|
}
|
|
163
208
|
|
|
164
|
-
async
|
|
209
|
+
async _reviewTaskExec(task, model) {
|
|
165
210
|
const args = ["-p", task.prompt, "--allowedTools", ...ALLOWED_TOOLS, "--output-format", "stream-json", "--verbose"];
|
|
166
|
-
const model = this.getRoleModel(task.role || "reviewer");
|
|
167
211
|
if (model) args.push("--model", model);
|
|
168
212
|
const res = await runCommand(resolveBin("claude"), args, cleanExecaOpts({
|
|
169
213
|
onOutput: task.onOutput,
|
|
@@ -171,6 +215,7 @@ export class ClaudeAgent extends BaseAgent {
|
|
|
171
215
|
timeout: task.timeoutMs
|
|
172
216
|
}));
|
|
173
217
|
const raw = pickOutput(res);
|
|
174
|
-
|
|
218
|
+
const usage = extractUsageFromStreamJson(raw);
|
|
219
|
+
return { ok: res.exitCode === 0, output: raw, error: res.exitCode === 0 ? "" : raw, exitCode: res.exitCode, ...usage };
|
|
175
220
|
}
|
|
176
221
|
}
|
|
@@ -2,27 +2,48 @@ import { BaseAgent } from "./base-agent.js";
|
|
|
2
2
|
import { runCommand } from "../utils/process.js";
|
|
3
3
|
import { resolveBin } from "./resolve-bin.js";
|
|
4
4
|
|
|
5
|
+
/**
|
|
6
|
+
* Extract token usage from Codex CLI stdout.
|
|
7
|
+
* Codex prints "tokens used\n<number>" at the end, where number may have comma separators.
|
|
8
|
+
* Returns { tokens_out } with the total token count, or null if not found.
|
|
9
|
+
* Since Codex doesn't split input/output, we assign the total to tokens_out
|
|
10
|
+
* as a conservative estimate for cost calculation.
|
|
11
|
+
*/
|
|
12
|
+
export function extractCodexTokens(stdout) {
|
|
13
|
+
const match = (stdout || "").match(/tokens?\s+used\s*\n\s*([\d,]+)/i);
|
|
14
|
+
if (!match) return null;
|
|
15
|
+
const total = Number(match[1].replace(/,/g, ""));
|
|
16
|
+
if (!Number.isFinite(total) || total <= 0) return null;
|
|
17
|
+
return { tokens_in: 0, tokens_out: total };
|
|
18
|
+
}
|
|
19
|
+
|
|
5
20
|
export class CodexAgent extends BaseAgent {
|
|
6
21
|
async runTask(task) {
|
|
7
22
|
const role = task.role || "coder";
|
|
8
|
-
const args = ["exec"];
|
|
9
23
|
const model = this.getRoleModel(role);
|
|
10
|
-
|
|
11
|
-
if (this.
|
|
12
|
-
|
|
13
|
-
|
|
14
|
-
|
|
15
|
-
|
|
16
|
-
timeout: task.timeoutMs,
|
|
17
|
-
input: task.prompt
|
|
18
|
-
});
|
|
19
|
-
return { ok: res.exitCode === 0, output: res.stdout, error: res.stderr, exitCode: res.exitCode };
|
|
24
|
+
const result = await this._exec(task, model, role);
|
|
25
|
+
if (!result.ok && model && this.isModelNotSupportedError(result)) {
|
|
26
|
+
this.logger?.warn(`Codex model "${model}" not supported — retrying with agent default`);
|
|
27
|
+
return this._exec(task, null, role);
|
|
28
|
+
}
|
|
29
|
+
return result;
|
|
20
30
|
}
|
|
21
31
|
|
|
22
32
|
async reviewTask(task) {
|
|
33
|
+
const role = task.role || "reviewer";
|
|
34
|
+
const model = this.getRoleModel(role);
|
|
35
|
+
const result = await this._exec(task, model, role);
|
|
36
|
+
if (!result.ok && model && this.isModelNotSupportedError(result)) {
|
|
37
|
+
this.logger?.warn(`Codex model "${model}" not supported — retrying with agent default`);
|
|
38
|
+
return this._exec(task, null, role);
|
|
39
|
+
}
|
|
40
|
+
return result;
|
|
41
|
+
}
|
|
42
|
+
|
|
43
|
+
async _exec(task, model, role) {
|
|
23
44
|
const args = ["exec"];
|
|
24
|
-
const model = this.getRoleModel(task.role || "reviewer");
|
|
25
45
|
if (model) args.push("--model", model);
|
|
46
|
+
if (role !== "reviewer" && this.isAutoApproveEnabled(role)) args.push("--full-auto");
|
|
26
47
|
args.push("-");
|
|
27
48
|
const res = await runCommand(resolveBin("codex"), args, {
|
|
28
49
|
onOutput: task.onOutput,
|
|
@@ -30,6 +51,7 @@ export class CodexAgent extends BaseAgent {
|
|
|
30
51
|
timeout: task.timeoutMs,
|
|
31
52
|
input: task.prompt
|
|
32
53
|
});
|
|
33
|
-
|
|
54
|
+
const usage = extractCodexTokens(res.stdout);
|
|
55
|
+
return { ok: res.exitCode === 0, output: res.stdout, error: res.stderr, exitCode: res.exitCode, ...usage };
|
|
34
56
|
}
|
|
35
57
|
}
|
|
@@ -5,21 +5,29 @@ import { resolveBin } from "./resolve-bin.js";
|
|
|
5
5
|
export class GeminiAgent extends BaseAgent {
|
|
6
6
|
async runTask(task) {
|
|
7
7
|
const role = task.role || "coder";
|
|
8
|
-
const args = ["-p", task.prompt];
|
|
9
8
|
const model = this.getRoleModel(role);
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
|
|
13
|
-
|
|
14
|
-
|
|
15
|
-
|
|
16
|
-
return { ok: res.exitCode === 0, output: res.stdout, error: res.stderr, exitCode: res.exitCode };
|
|
9
|
+
const result = await this._exec(task, model, "run");
|
|
10
|
+
if (!result.ok && model && this.isModelNotSupportedError(result)) {
|
|
11
|
+
this.logger?.warn(`Gemini model "${model}" not supported — retrying with agent default`);
|
|
12
|
+
return this._exec(task, null, "run");
|
|
13
|
+
}
|
|
14
|
+
return result;
|
|
17
15
|
}
|
|
18
16
|
|
|
19
17
|
async reviewTask(task) {
|
|
20
18
|
const role = task.role || "reviewer";
|
|
21
|
-
const args = ["-p", task.prompt, "--output-format", "json"];
|
|
22
19
|
const model = this.getRoleModel(role);
|
|
20
|
+
const result = await this._exec(task, model, "review");
|
|
21
|
+
if (!result.ok && model && this.isModelNotSupportedError(result)) {
|
|
22
|
+
this.logger?.warn(`Gemini model "${model}" not supported — retrying with agent default`);
|
|
23
|
+
return this._exec(task, null, "review");
|
|
24
|
+
}
|
|
25
|
+
return result;
|
|
26
|
+
}
|
|
27
|
+
|
|
28
|
+
async _exec(task, model, mode) {
|
|
29
|
+
const args = ["-p", task.prompt];
|
|
30
|
+
if (mode === "review") args.push("--output-format", "json");
|
|
23
31
|
if (model) args.push("--model", model);
|
|
24
32
|
const res = await runCommand(resolveBin("gemini"), args, {
|
|
25
33
|
onOutput: task.onOutput,
|
|
@@ -49,15 +49,16 @@ export function buildDefaultPricingTable() {
|
|
|
49
49
|
}
|
|
50
50
|
|
|
51
51
|
// Auto-register built-in models
|
|
52
|
+
// Names must match what each CLI accepts as --model argument
|
|
52
53
|
registerModel("claude", { provider: "anthropic", pricing: { input_per_million: 3, output_per_million: 15 } });
|
|
53
|
-
registerModel("
|
|
54
|
-
registerModel("
|
|
55
|
-
registerModel("
|
|
54
|
+
registerModel("sonnet", { provider: "anthropic", pricing: { input_per_million: 3, output_per_million: 15 } });
|
|
55
|
+
registerModel("opus", { provider: "anthropic", pricing: { input_per_million: 15, output_per_million: 75 } });
|
|
56
|
+
registerModel("haiku", { provider: "anthropic", pricing: { input_per_million: 0.25, output_per_million: 1.25 } });
|
|
56
57
|
registerModel("codex", { provider: "openai", pricing: { input_per_million: 1.5, output_per_million: 4 } });
|
|
57
|
-
registerModel("
|
|
58
|
-
registerModel("
|
|
58
|
+
registerModel("o4-mini", { provider: "openai", pricing: { input_per_million: 1.5, output_per_million: 4 } });
|
|
59
|
+
registerModel("o3", { provider: "openai", pricing: { input_per_million: 10, output_per_million: 40 } });
|
|
59
60
|
registerModel("gemini", { provider: "google", pricing: { input_per_million: 1.25, output_per_million: 5 } });
|
|
60
|
-
registerModel("gemini
|
|
61
|
-
registerModel("gemini
|
|
61
|
+
registerModel("gemini-2.5-pro", { provider: "google", pricing: { input_per_million: 1.25, output_per_million: 5 } });
|
|
62
|
+
registerModel("gemini-2.0-flash", { provider: "google", pricing: { input_per_million: 0.075, output_per_million: 0.3 } });
|
|
62
63
|
registerModel("aider", { provider: "aider", pricing: { input_per_million: 3, output_per_million: 15 } });
|
|
63
64
|
registerModel("opencode", { provider: "opencode", pricing: { input_per_million: 0, output_per_million: 0 } });
|
|
@@ -5,22 +5,29 @@ import { resolveBin } from "./resolve-bin.js";
|
|
|
5
5
|
export class OpenCodeAgent extends BaseAgent {
|
|
6
6
|
async runTask(task) {
|
|
7
7
|
const role = task.role || "coder";
|
|
8
|
-
const args = ["run"];
|
|
9
8
|
const model = this.getRoleModel(role);
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
|
|
13
|
-
|
|
14
|
-
|
|
15
|
-
|
|
16
|
-
});
|
|
17
|
-
return { ok: res.exitCode === 0, output: res.stdout, error: res.stderr, exitCode: res.exitCode };
|
|
9
|
+
const result = await this._exec(task, model, false);
|
|
10
|
+
if (!result.ok && model && this.isModelNotSupportedError(result)) {
|
|
11
|
+
this.logger?.warn(`OpenCode model "${model}" not supported — retrying with agent default`);
|
|
12
|
+
return this._exec(task, null, false);
|
|
13
|
+
}
|
|
14
|
+
return result;
|
|
18
15
|
}
|
|
19
16
|
|
|
20
17
|
async reviewTask(task) {
|
|
21
18
|
const role = task.role || "reviewer";
|
|
22
|
-
const args = ["run", "--format", "json"];
|
|
23
19
|
const model = this.getRoleModel(role);
|
|
20
|
+
const result = await this._exec(task, model, true);
|
|
21
|
+
if (!result.ok && model && this.isModelNotSupportedError(result)) {
|
|
22
|
+
this.logger?.warn(`OpenCode model "${model}" not supported — retrying with agent default`);
|
|
23
|
+
return this._exec(task, null, true);
|
|
24
|
+
}
|
|
25
|
+
return result;
|
|
26
|
+
}
|
|
27
|
+
|
|
28
|
+
async _exec(task, model, jsonFormat) {
|
|
29
|
+
const args = ["run"];
|
|
30
|
+
if (jsonFormat) args.push("--format", "json");
|
|
24
31
|
if (model) args.push("--model", model);
|
|
25
32
|
args.push(task.prompt);
|
|
26
33
|
const res = await runCommand(resolveBin("opencode"), args, {
|
package/src/commands/doctor.js
CHANGED
|
@@ -1,5 +1,7 @@
|
|
|
1
1
|
import { readFileSync } from "node:fs";
|
|
2
|
+
import fs from "node:fs/promises";
|
|
2
3
|
import { fileURLToPath } from "node:url";
|
|
4
|
+
import os from "node:os";
|
|
3
5
|
import path from "node:path";
|
|
4
6
|
import { runCommand } from "../utils/process.js";
|
|
5
7
|
import { exists } from "../utils/fs.js";
|
|
@@ -239,6 +241,101 @@ async function checkRuleFiles(config) {
|
|
|
239
241
|
];
|
|
240
242
|
}
|
|
241
243
|
|
|
244
|
+
/**
|
|
245
|
+
* Detect duplicate TOML table headers (e.g. [mcp_servers."karajan-mcp"] appearing twice).
|
|
246
|
+
* Full TOML parsing would require a dependency — this catches the most common config error.
|
|
247
|
+
*/
|
|
248
|
+
function findDuplicateTomlKeys(content) {
|
|
249
|
+
const tableHeaders = [];
|
|
250
|
+
const duplicates = [];
|
|
251
|
+
for (const line of content.split("\n")) {
|
|
252
|
+
const match = line.match(/^\s*\[([^\]]+)\]\s*$/);
|
|
253
|
+
if (match) {
|
|
254
|
+
const key = match[1].trim();
|
|
255
|
+
if (tableHeaders.includes(key)) {
|
|
256
|
+
duplicates.push(key);
|
|
257
|
+
} else {
|
|
258
|
+
tableHeaders.push(key);
|
|
259
|
+
}
|
|
260
|
+
}
|
|
261
|
+
}
|
|
262
|
+
return duplicates;
|
|
263
|
+
}
|
|
264
|
+
|
|
265
|
+
async function checkAgentConfigs() {
|
|
266
|
+
const checks = [];
|
|
267
|
+
const home = os.homedir();
|
|
268
|
+
|
|
269
|
+
// Claude: ~/.claude.json
|
|
270
|
+
const claudeJsonPath = path.join(home, ".claude.json");
|
|
271
|
+
try {
|
|
272
|
+
const raw = await fs.readFile(claudeJsonPath, "utf8");
|
|
273
|
+
JSON.parse(raw);
|
|
274
|
+
checks.push({ name: "agent-config:claude", label: "Agent config: claude (~/.claude.json)", ok: true, detail: "Valid JSON", fix: null });
|
|
275
|
+
} catch (err) {
|
|
276
|
+
if (err.code === "ENOENT") {
|
|
277
|
+
// File doesn't exist — not an error, Claude may not be configured
|
|
278
|
+
} else {
|
|
279
|
+
checks.push({
|
|
280
|
+
name: "agent-config:claude",
|
|
281
|
+
label: "Agent config: claude (~/.claude.json)",
|
|
282
|
+
ok: false,
|
|
283
|
+
detail: `Invalid JSON: ${err.message.split("\n")[0]}`,
|
|
284
|
+
fix: "Fix the JSON syntax in ~/.claude.json. Common issues: trailing commas, missing quotes."
|
|
285
|
+
});
|
|
286
|
+
}
|
|
287
|
+
}
|
|
288
|
+
|
|
289
|
+
// Codex: ~/.codex/config.toml
|
|
290
|
+
const codexTomlPath = path.join(home, ".codex", "config.toml");
|
|
291
|
+
try {
|
|
292
|
+
const raw = await fs.readFile(codexTomlPath, "utf8");
|
|
293
|
+
const duplicates = findDuplicateTomlKeys(raw);
|
|
294
|
+
if (duplicates.length > 0) {
|
|
295
|
+
checks.push({
|
|
296
|
+
name: "agent-config:codex",
|
|
297
|
+
label: "Agent config: codex (~/.codex/config.toml)",
|
|
298
|
+
ok: false,
|
|
299
|
+
detail: `Duplicate TOML keys: ${duplicates.join(", ")}`,
|
|
300
|
+
fix: `Remove duplicate entries in ~/.codex/config.toml: ${duplicates.join(", ")}`
|
|
301
|
+
});
|
|
302
|
+
} else {
|
|
303
|
+
checks.push({ name: "agent-config:codex", label: "Agent config: codex (~/.codex/config.toml)", ok: true, detail: "Valid TOML (no duplicate keys)", fix: null });
|
|
304
|
+
}
|
|
305
|
+
} catch (err) {
|
|
306
|
+
if (err.code !== "ENOENT") {
|
|
307
|
+
checks.push({
|
|
308
|
+
name: "agent-config:codex",
|
|
309
|
+
label: "Agent config: codex (~/.codex/config.toml)",
|
|
310
|
+
ok: false,
|
|
311
|
+
detail: `Cannot read: ${err.message.split("\n")[0]}`,
|
|
312
|
+
fix: "Check file permissions on ~/.codex/config.toml"
|
|
313
|
+
});
|
|
314
|
+
}
|
|
315
|
+
}
|
|
316
|
+
|
|
317
|
+
// KJ config: ~/.karajan/kj.config.yml (validate YAML)
|
|
318
|
+
const kjConfigPath = getConfigPath();
|
|
319
|
+
try {
|
|
320
|
+
const raw = await fs.readFile(kjConfigPath, "utf8");
|
|
321
|
+
const yaml = await import("js-yaml");
|
|
322
|
+
yaml.default.load(raw);
|
|
323
|
+
checks.push({ name: "agent-config:karajan", label: "Agent config: karajan (kj.config.yml)", ok: true, detail: "Valid YAML", fix: null });
|
|
324
|
+
} catch (err) {
|
|
325
|
+
if (err.code !== "ENOENT") {
|
|
326
|
+
checks.push({
|
|
327
|
+
name: "agent-config:karajan",
|
|
328
|
+
label: "Agent config: karajan (kj.config.yml)",
|
|
329
|
+
ok: false,
|
|
330
|
+
detail: `Invalid YAML: ${err.message.split("\n")[0]}`,
|
|
331
|
+
fix: `Fix YAML syntax in ${kjConfigPath}. Run 'kj init' to regenerate if needed.`
|
|
332
|
+
});
|
|
333
|
+
}
|
|
334
|
+
}
|
|
335
|
+
|
|
336
|
+
return checks;
|
|
337
|
+
}
|
|
338
|
+
|
|
242
339
|
export async function runChecks({ config }) {
|
|
243
340
|
const checks = [];
|
|
244
341
|
|
|
@@ -260,6 +357,7 @@ export async function runChecks({ config }) {
|
|
|
260
357
|
checks.push(...await checkBecariaInfra(config));
|
|
261
358
|
}
|
|
262
359
|
|
|
360
|
+
checks.push(...await checkAgentConfigs());
|
|
263
361
|
checks.push(...await checkRuleFiles(config));
|
|
264
362
|
checks.push(await checkRtk());
|
|
265
363
|
|
|
@@ -30,10 +30,17 @@ export async function invokeSolomon({ config, logger, emitter, eventBase, stage,
|
|
|
30
30
|
});
|
|
31
31
|
}
|
|
32
32
|
|
|
33
|
+
const solomonError = ruling.result?.error;
|
|
34
|
+
if (!ruling.ok && solomonError) {
|
|
35
|
+
logger.warn(`Solomon execution failed: ${solomonError}`);
|
|
36
|
+
}
|
|
37
|
+
|
|
33
38
|
emitProgress(
|
|
34
39
|
emitter,
|
|
35
40
|
makeEvent("solomon:end", { ...eventBase, stage: "solomon" }, {
|
|
36
|
-
message:
|
|
41
|
+
message: ruling.ok
|
|
42
|
+
? `Solomon ruling: ${ruling.result?.ruling || "unknown"}`
|
|
43
|
+
: `Solomon failed: ${(solomonError || ruling.summary || "unknown error").slice(0, 200)}`,
|
|
37
44
|
detail: ruling.result
|
|
38
45
|
})
|
|
39
46
|
);
|
|
@@ -43,13 +50,15 @@ export async function invokeSolomon({ config, logger, emitter, eventBase, stage,
|
|
|
43
50
|
iteration,
|
|
44
51
|
ruling: ruling.result?.ruling,
|
|
45
52
|
escalate: ruling.result?.escalate,
|
|
53
|
+
error: solomonError ? solomonError.slice(0, 500) : undefined,
|
|
46
54
|
subtask: ruling.result?.subtask?.title || null
|
|
47
55
|
});
|
|
48
56
|
|
|
49
57
|
if (!ruling.ok) {
|
|
58
|
+
const reason = ruling.result?.escalate_reason || solomonError || ruling.summary;
|
|
50
59
|
return escalateToHuman({
|
|
51
60
|
askQuestion, session, emitter, eventBase, stage, iteration,
|
|
52
|
-
conflict: { ...conflict, solomonReason:
|
|
61
|
+
conflict: { ...conflict, solomonReason: reason }
|
|
53
62
|
});
|
|
54
63
|
}
|
|
55
64
|
|
|
@@ -62,12 +62,28 @@ function buildPrompt({ conflict, task, instructions }) {
|
|
|
62
62
|
const iterationCount = conflict?.iterationCount ?? "?";
|
|
63
63
|
const maxIterations = conflict?.maxIterations ?? "?";
|
|
64
64
|
|
|
65
|
+
const isFirstRejection = conflict?.isFirstRejection ?? false;
|
|
66
|
+
const isRepeat = conflict?.isRepeat ?? false;
|
|
67
|
+
|
|
65
68
|
sections.push(
|
|
66
69
|
`## Conflict context`,
|
|
67
70
|
`Stage: ${stage}`,
|
|
68
|
-
`Iterations exhausted: ${iterationCount}/${maxIterations}
|
|
71
|
+
`Iterations exhausted: ${iterationCount}/${maxIterations}`,
|
|
72
|
+
`isFirstRejection: ${isFirstRejection}`,
|
|
73
|
+
`isRepeat: ${isRepeat}`
|
|
69
74
|
);
|
|
70
75
|
|
|
76
|
+
if (conflict?.issueCategories) {
|
|
77
|
+
sections.push(`## Issue categories\n${JSON.stringify(conflict.issueCategories, null, 2)}`);
|
|
78
|
+
}
|
|
79
|
+
|
|
80
|
+
if (conflict?.blockingIssues?.length) {
|
|
81
|
+
const issueList = conflict.blockingIssues
|
|
82
|
+
.map((issue, i) => `${i + 1}. [${issue.severity || "unknown"}] ${issue.description || issue}`)
|
|
83
|
+
.join("\n");
|
|
84
|
+
sections.push(`## Blocking issues\n${issueList}`);
|
|
85
|
+
}
|
|
86
|
+
|
|
71
87
|
if (task) {
|
|
72
88
|
sections.push(`## Original task\n${task}`);
|
|
73
89
|
}
|
package/src/utils/budget.js
CHANGED
|
@@ -40,18 +40,22 @@ export function extractUsageMetrics(result, defaultModel = null) {
|
|
|
40
40
|
null;
|
|
41
41
|
|
|
42
42
|
// If no real token data AND no explicit cost, estimate from prompt/output sizes.
|
|
43
|
-
//
|
|
43
|
+
// Primary: uses result.promptSize when explicitly provided.
|
|
44
|
+
// Fallback: estimates from result.output or result.error text length.
|
|
44
45
|
let estimated = false;
|
|
45
46
|
let finalTokensIn = tokens_in;
|
|
46
47
|
let finalTokensOut = tokens_out;
|
|
47
48
|
const hasExplicitCost = cost_usd !== undefined && cost_usd !== null && cost_usd !== "";
|
|
48
|
-
if (!tokens_in && !tokens_out && !hasExplicitCost
|
|
49
|
-
const
|
|
50
|
-
const
|
|
51
|
-
const
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
49
|
+
if (!tokens_in && !tokens_out && !hasExplicitCost) {
|
|
50
|
+
const outputText = result?.output || result?.error || result?.summary || "";
|
|
51
|
+
const promptSize = result?.promptSize || 0;
|
|
52
|
+
const MIN_TEXT_FOR_ESTIMATION = 40;
|
|
53
|
+
if (promptSize > 0 || outputText.length >= MIN_TEXT_FOR_ESTIMATION) {
|
|
54
|
+
const est = estimateTokens(promptSize, outputText.length);
|
|
55
|
+
finalTokensIn = est.tokens_in;
|
|
56
|
+
finalTokensOut = est.tokens_out;
|
|
57
|
+
estimated = true;
|
|
58
|
+
}
|
|
55
59
|
}
|
|
56
60
|
|
|
57
61
|
return { tokens_in: finalTokensIn, tokens_out: finalTokensOut, cost_usd, model, estimated };
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
const DEFAULT_MODEL_TIERS = {
|
|
2
|
-
claude: { trivial: "
|
|
3
|
-
codex: { trivial: "
|
|
4
|
-
gemini: { trivial: "gemini
|
|
2
|
+
claude: { trivial: "haiku", simple: "haiku", medium: "sonnet", complex: "opus" },
|
|
3
|
+
codex: { trivial: "o4-mini", simple: "o4-mini", medium: "o4-mini", complex: "o3" },
|
|
4
|
+
gemini: { trivial: "gemini-2.0-flash", simple: "gemini-2.0-flash", medium: "gemini-2.5-pro", complex: "gemini-2.5-pro" },
|
|
5
5
|
aider: { trivial: null, simple: null, medium: null, complex: null }
|
|
6
6
|
};
|
|
7
7
|
|
|
@@ -51,7 +51,7 @@ export function createStallDetector({
|
|
|
51
51
|
lastCriticalWarnAt = now;
|
|
52
52
|
emitProgress(emitter, makeEvent("agent:stall", { ...eventBase, stage }, {
|
|
53
53
|
status: "critical",
|
|
54
|
-
message: `Agent ${provider} unresponsive for ${Math.round(silenceMs / 1000)}s — may be hung`,
|
|
54
|
+
message: `[${stage}] Agent ${provider} unresponsive for ${Math.round(silenceMs / 1000)}s — may be hung`,
|
|
55
55
|
detail: {
|
|
56
56
|
provider,
|
|
57
57
|
silenceMs,
|
|
@@ -65,7 +65,7 @@ export function createStallDetector({
|
|
|
65
65
|
lastStallWarnAt = now;
|
|
66
66
|
emitProgress(emitter, makeEvent("agent:stall", { ...eventBase, stage }, {
|
|
67
67
|
status: "warning",
|
|
68
|
-
message: `Agent ${provider} silent for ${Math.round(silenceMs / 1000)}s — still waiting`,
|
|
68
|
+
message: `[${stage}] Agent ${provider} silent for ${Math.round(silenceMs / 1000)}s — still waiting`,
|
|
69
69
|
detail: {
|
|
70
70
|
provider,
|
|
71
71
|
silenceMs,
|
|
@@ -79,8 +79,8 @@ export function createStallDetector({
|
|
|
79
79
|
|
|
80
80
|
emitProgress(emitter, makeEvent("agent:heartbeat", { ...eventBase, stage }, {
|
|
81
81
|
message: silenceMs < stallTimeoutMs
|
|
82
|
-
? `Agent ${provider} active — ${lineCount} lines, ${Math.round(elapsedMs / 1000)}s elapsed`
|
|
83
|
-
: `Agent ${provider} waiting — silent ${Math.round(silenceMs / 1000)}s, ${Math.round(elapsedMs / 1000)}s elapsed`,
|
|
82
|
+
? `[${stage}] Agent ${provider} active — ${lineCount} lines, ${Math.round(elapsedMs / 1000)}s elapsed`
|
|
83
|
+
: `[${stage}] Agent ${provider} waiting — silent ${Math.round(silenceMs / 1000)}s, ${Math.round(elapsedMs / 1000)}s elapsed`,
|
|
84
84
|
detail: {
|
|
85
85
|
provider,
|
|
86
86
|
elapsedMs,
|
|
@@ -96,7 +96,7 @@ export function createStallDetector({
|
|
|
96
96
|
maxSilenceTriggered = true;
|
|
97
97
|
emitProgress(emitter, makeEvent("agent:stall", { ...eventBase, stage }, {
|
|
98
98
|
status: "fail",
|
|
99
|
-
message: `Agent ${provider} exceeded max silence (${Math.round(hardLimit / 1000)}s)`,
|
|
99
|
+
message: `[${stage}] Agent ${provider} exceeded max silence (${Math.round(hardLimit / 1000)}s)`,
|
|
100
100
|
detail: {
|
|
101
101
|
provider,
|
|
102
102
|
silenceMs,
|
package/templates/kj.config.yml
CHANGED
|
@@ -34,6 +34,9 @@ development:
|
|
|
34
34
|
- .spec.
|
|
35
35
|
|
|
36
36
|
# SonarQube settings
|
|
37
|
+
# Authentication: set token below, or KJ_SONAR_TOKEN env var,
|
|
38
|
+
# or save admin credentials in ~/.karajan/sonar-credentials.json:
|
|
39
|
+
# {"user": "admin", "password": "your-password"}
|
|
37
40
|
sonarqube:
|
|
38
41
|
enabled: true
|
|
39
42
|
host: http://localhost:9000
|