gitnexus 1.6.10-rc.99 → 1.6.10

package/dist/cli/i18n/resources.d.ts

@@ -55,10 +55,13 @@ export declare const cliResources: {
         readonly 'tool.usage.query': "Usage: gitnexus query [search_query]  or  gitnexus query --query <text>";
         readonly 'tool.usage.context': "Usage: gitnexus context <symbol_name> [--uid <uid>] [--file <path>]";
         readonly 'tool.usage.impact': "Usage: gitnexus impact <symbol_name> [--uid <uid>] [--file <path>] [--kind <kind>] [--direction upstream|downstream]";
-        readonly 'tool.usage.trace': "Usage: gitnexus trace <from> <to> [--from-uid <uid>] [--to-uid <uid>] [--depth <n>]";
+        readonly 'tool.usage.trace': "Usage: gitnexus trace <from> <to> [-f|--file <path>] [--from-file <path>] [--to-file <path>] [--from-uid <uid>] [--to-uid <uid>] [--depth <n>]";
         readonly 'tool.usage.cypher': "Usage: gitnexus cypher <cypher_query>";
         readonly 'tool.warn.unknownKind': "--kind '{{kind}}' is not a known symbol kind (e.g. Function, Class, Method); it will not narrow the result.";
         readonly 'tool.detectChanges.noChanges': "No changes detected.";
+        readonly 'tool.detectChanges.partial': "PARTIAL RESULT: a graph query failed, so changed symbols may be missing. Do not read this as a clean pre-commit check.";
+        readonly 'tool.detectChanges.truncated': "LISTING CAPPED: the changed-symbol list was capped, so it does not name every changed symbol. The counts and risk level still cover all of them.";
+        readonly 'tool.detectChanges.truncatedDegraded': "LISTING CAPPED: the changed-symbol list was capped. The run also degraded, so the counts are a lower bound, not a total.";
         readonly 'tool.detectChanges.changesSummary': "Changes: {{files}} files, {{symbols}} symbols";
         readonly 'tool.detectChanges.affectedProcesses': "Affected processes: {{count}}";
         readonly 'tool.detectChanges.riskLevel': "Risk level: {{risk}}";
@@ -154,6 +157,7 @@ export declare const cliResources: {
         readonly 'help.option.analyze.skills': "Generate repo-specific skill files from detected communities (no-op when --index-only is also set).";
         readonly 'help.option.analyze.skipAgentsMd': "Skip updating the gitnexus section in AGENTS.md and CLAUDE.md";
         readonly 'help.option.analyze.noStats': "Omit volatile file/symbol counts from AGENTS.md and CLAUDE.md";
+        readonly 'help.option.analyze.selfCommit': "Auto-commit AGENTS.md/CLAUDE.md changes after analyze (opt-in, off by default). Scoped to only those two files (never `git add -A`); no-ops if neither exists, neither changed, or the repo has no git identity configured.";
         readonly 'help.option.analyze.skipSkills': "Skip installing standard GitNexus skill files directly under .claude/skills/ and .agents/skills/. Does not suppress community skills from --skills (those use .claude/skills/gitnexus-area-*). Use --index-only to skip all AI-context file injection.";
         readonly 'help.option.analyze.indexOnly': "Pure index mode: skip all file injection (AGENTS.md, CLAUDE.md, skills)";
         readonly 'help.option.skipGit': "Treat the provided path/cwd as the index root and skip parent git-root discovery";
@@ -181,13 +185,13 @@ export declare const cliResources: {
         readonly 'help.option.clean.branch': "Delete only the named branch index (not the workspace index)";
         readonly 'help.option.clean.lbugSidecars': "Clean parked LadybugDB recovery sidecars (missing-shadow WAL quarantines and dirty-recovery parks)";
         readonly 'help.option.wiki.force': "Force full regeneration even if up to date";
-        readonly 'help.option.wiki.provider': "LLM provider: openai, openrouter, azure, custom, cursor, claude, codex, or opencode (default: openai)";
-        readonly 'help.option.wiki.model': "LLM model or Azure deployment name (default: minimax/minimax-m2.5)";
+        readonly 'help.option.wiki.provider': "LLM provider: minimax, openai, openrouter, azure, custom, cursor, claude, codex, or opencode (default: minimax)";
+        readonly 'help.option.wiki.model': "LLM model or deployment name (default: MiniMax-M3)";
         readonly 'help.option.wiki.baseUrl': "LLM API base URL. Azure v1: https://{resource}.openai.azure.com/openai/v1";
         readonly 'help.option.wiki.apiKey': "LLM API key or Azure api-key (saved to ~/.gitnexus/config.json)";
         readonly 'help.option.wiki.apiVersion': "Azure api-version query param, e.g. 2024-10-21 (legacy Azure API only)";
-        readonly 'help.option.wiki.reasoningModel': "Mark deployment as reasoning model (o1/o3/o4-mini) — strips temperature, uses max_completion_tokens";
-        readonly 'help.option.wiki.noReasoningModel': "Disable reasoning model mode (overrides saved config)";
+        readonly 'help.option.wiki.reasoningModel': "Enable reasoning mode; MiniMax-M3 uses adaptive thinking";
+        readonly 'help.option.wiki.noReasoningModel': "Disable reasoning mode; MiniMax-M3 disables thinking";
         readonly 'help.option.wiki.concurrency': "Parallel LLM calls (default: 3)";
         readonly 'help.option.wiki.timeout': "LLM request timeout in seconds (default: disabled)";
         readonly 'help.option.wiki.retries': "Max LLM retry attempts per request (default: 3)";
@@ -230,10 +234,8 @@ export declare const cliResources: {
         readonly 'help.option.embeddings.install.cuda': "Also download the CUDA GPU binaries (runs onnxruntime-node's NuGet postinstall; set GLOBAL_AGENT_HTTPS_PROXY behind a proxy)";
         readonly 'help.option.embeddings.install.force': "Install into the runtime prefix even when the stack already resolves";
         readonly 'help.option.group.create.force': "Overwrite existing group";
-        readonly 'help.option.group.sync.skipEmbeddings': "Exact + BM25 only (no embedding fallback)";
-        readonly 'help.option.group.sync.exactOnly': "Exact match only";
-        readonly 'help.option.group.sync.allowStale': "Skip stale index warnings";
-        readonly 'help.option.group.sync.verbose': "Show each cross-link detail";
+        readonly 'help.option.group.sync.exactOnly': "Skip wildcard service matching; cross-link on exact contract-id match only (manifest links still apply)";
+        readonly 'help.option.group.sync.verbose': "Show additional sync diagnostics";
         readonly 'help.option.status.json': "Emit machine-readable index and analyzer provenance";
         readonly 'help.option.json': "JSON output";
         readonly 'help.option.group.impact.target': "Symbol or file name to analyze";
@@ -311,6 +313,9 @@ export declare const cliResources: {
         'tool.usage.cypher': string;
         'tool.warn.unknownKind': string;
         'tool.detectChanges.noChanges': string;
+        'tool.detectChanges.partial': string;
+        'tool.detectChanges.truncated': string;
+        'tool.detectChanges.truncatedDegraded': string;
         'tool.detectChanges.changesSummary': string;
         'tool.detectChanges.affectedProcesses': string;
         'tool.detectChanges.riskLevel': string;
@@ -406,6 +411,7 @@ export declare const cliResources: {
         'help.option.analyze.skills': string;
         'help.option.analyze.skipAgentsMd': string;
         'help.option.analyze.noStats': string;
+        'help.option.analyze.selfCommit': string;
         'help.option.analyze.skipSkills': string;
         'help.option.analyze.indexOnly': string;
         'help.option.skipGit': string;
@@ -482,9 +488,7 @@ export declare const cliResources: {
         'help.option.embeddings.install.cuda': string;
         'help.option.embeddings.install.force': string;
         'help.option.group.create.force': string;
-        'help.option.group.sync.skipEmbeddings': string;
         'help.option.group.sync.exactOnly': string;
-        'help.option.group.sync.allowStale': string;
         'help.option.group.sync.verbose': string;
         'help.option.status.json': string;
         'help.option.json': string;

package/dist/cli/i18n/zh-CN.d.ts

@@ -58,6 +58,9 @@ export declare const zhCN: {
     'tool.usage.cypher': string;
     'tool.warn.unknownKind': string;
     'tool.detectChanges.noChanges': string;
+    'tool.detectChanges.partial': string;
+    'tool.detectChanges.truncated': string;
+    'tool.detectChanges.truncatedDegraded': string;
     'tool.detectChanges.changesSummary': string;
     'tool.detectChanges.affectedProcesses': string;
     'tool.detectChanges.riskLevel': string;
@@ -153,6 +156,7 @@ export declare const zhCN: {
     'help.option.analyze.skills': string;
     'help.option.analyze.skipAgentsMd': string;
     'help.option.analyze.noStats': string;
+    'help.option.analyze.selfCommit': string;
     'help.option.analyze.skipSkills': string;
     'help.option.analyze.indexOnly': string;
     'help.option.skipGit': string;
@@ -229,9 +233,7 @@ export declare const zhCN: {
     'help.option.embeddings.install.cuda': string;
     'help.option.embeddings.install.force': string;
     'help.option.group.create.force': string;
-    'help.option.group.sync.skipEmbeddings': string;
     'help.option.group.sync.exactOnly': string;
-    'help.option.group.sync.allowStale': string;
     'help.option.group.sync.verbose': string;
     'help.option.status.json': string;
     'help.option.json': string;

package/dist/cli/i18n/zh-CN.js

@@ -54,10 +54,13 @@ export const zhCN = {
     'tool.usage.query': '用法：gitnexus query [搜索词]  或  gitnexus query --query <文本>',
     'tool.usage.context': '用法：gitnexus context <符号名> [--uid <uid>] [--file <路径>]',
     'tool.usage.impact': '用法：gitnexus impact <符号名> [--uid <uid>] [--file <路径>] [--kind <类型>] [--direction upstream|downstream]',
-    'tool.usage.trace': '用法：gitnexus trace <起点> <终点> [--from-uid <uid>] [--to-uid <uid>] [--depth <n>]',
+    'tool.usage.trace': '用法：gitnexus trace <起点> <终点> [-f|--file <路径>] [--from-file <路径>] [--to-file <路径>] [--from-uid <uid>] [--to-uid <uid>] [--depth <n>]',
     'tool.usage.cypher': '用法：gitnexus cypher <Cypher 查询>',
     'tool.warn.unknownKind': "--kind '{{kind}}' 不是已知的符号类型（如 Function、Class、Method），不会用于缩小结果范围。",
     'tool.detectChanges.noChanges': '未检测到变更。',
+    'tool.detectChanges.partial': '结果不完整：图查询失败，可能遗漏已变更符号。请勿将其视为通过的提交前检查。',
+    'tool.detectChanges.truncated': '列表已截断：已变更符号列表被截断，未列出全部变更符号。计数与风险等级仍涵盖全部符号。',
+    'tool.detectChanges.truncatedDegraded': '列表已截断：已变更符号列表被截断。本次运行同时不完整，因此计数为下限而非总数。',
     'tool.detectChanges.changesSummary': '变更：{{files}} 个文件，{{symbols}} 个符号',
     'tool.detectChanges.affectedProcesses': '受影响流程：{{count}}',
     'tool.detectChanges.riskLevel': '风险等级：{{risk}}',
@@ -153,6 +156,7 @@ export const zhCN = {
     'help.option.analyze.skills': '根据检测到的社区生成仓库专属 skill 文件（同时设置 --index-only 时无效）。',
     'help.option.analyze.skipAgentsMd': '跳过更新 AGENTS.md 和 CLAUDE.md 中的 gitnexus 区块',
     'help.option.analyze.noStats': '从 AGENTS.md 和 CLAUDE.md 中省略易变的文件/符号计数',
+    'help.option.analyze.selfCommit': '在 analyze 后自动提交 AGENTS.md/CLAUDE.md 的变更（默认关闭，需显式开启）。仅限这两个文件（绝不使用 `git add -A`）；若两者均不存在、均未变更，或仓库未配置 git 身份，则不执行任何操作。',
     'help.option.analyze.skipSkills': '跳过直接安装在 .claude/skills/ 和 .agents/skills/ 下的标准 GitNexus skill 文件。不抑制 --skills 生成的社区 skill（位于 .claude/skills/gitnexus-area-*）。使用 --index-only 可跳过所有 AI 上下文文件注入。',
     'help.option.analyze.indexOnly': '纯索引模式：跳过所有文件注入（AGENTS.md、CLAUDE.md、skills）',
     'help.option.skipGit': '将提供的路径/cwd 视为索引根目录，并跳过向上查找 git 根目录',
@@ -180,13 +184,13 @@ export const zhCN = {
     'help.option.clean.branch': '仅删除指定分支的索引（不影响工作区索引）',
     'help.option.clean.lbugSidecars': '清理已暂存的 LadybugDB 恢复 sidecar（missing-shadow WAL 隔离文件与 dirty-recovery 暂存文件）',
     'help.option.wiki.force': '即使已是最新也强制完整重新生成',
-    'help.option.wiki.provider': 'LLM 提供商：openai、openrouter、azure、custom、cursor、claude、codex 或 opencode（默认：openai）',
-    'help.option.wiki.model': 'LLM 模型或 Azure deployment 名称（默认：minimax/minimax-m2.5）',
+    'help.option.wiki.provider': 'LLM 提供商：minimax、openai、openrouter、azure、custom、cursor、claude、codex 或 opencode（默认：minimax）',
+    'help.option.wiki.model': 'LLM 模型或 deployment 名称（默认：MiniMax-M3）',
     'help.option.wiki.baseUrl': 'LLM API base URL。Azure v1：https://{resource}.openai.azure.com/openai/v1',
     'help.option.wiki.apiKey': 'LLM API key 或 Azure api-key（保存到 ~/.gitnexus/config.json）',
     'help.option.wiki.apiVersion': 'Azure api-version 查询参数，例如 2024-10-21（仅旧版 Azure API）',
-    'help.option.wiki.reasoningModel': '标记 deployment 为 reasoning model（o1/o3/o4-mini）— 去除 temperature，使用 max_completion_tokens',
-    'help.option.wiki.noReasoningModel': '禁用 reasoning model 模式（覆盖已保存配置）',
+    'help.option.wiki.reasoningModel': '启用 reasoning 模式；MiniMax-M3 使用自适应 thinking',
+    'help.option.wiki.noReasoningModel': '禁用 reasoning 模式；MiniMax-M3 关闭 thinking',
     'help.option.wiki.concurrency': '并行 LLM 调用数（默认：3）',
     'help.option.wiki.timeout': 'LLM 请求超时时间（秒，默认：禁用）',
     'help.option.wiki.retries': '每个请求的最大 LLM 重试次数（默认：3）',
@@ -229,10 +233,8 @@ export const zhCN = {
     'help.option.embeddings.install.cuda': '同时下载 CUDA GPU 二进制文件（运行 onnxruntime-node 的 NuGet postinstall；代理后请设置 GLOBAL_AGENT_HTTPS_PROXY）',
     'help.option.embeddings.install.force': '即使嵌入组件已可解析，也强制安装到运行时目录',
     'help.option.group.create.force': '覆盖现有仓库组',
-    'help.option.group.sync.skipEmbeddings': '仅使用 exact + BM25（不使用嵌入回退）',
-    'help.option.group.sync.exactOnly': '仅精确匹配',
-    'help.option.group.sync.allowStale': '跳过过期索引警告',
-    'help.option.group.sync.verbose': '显示每条跨仓库链接详情',
+    'help.option.group.sync.exactOnly': '跳过通配符服务匹配，仅按契约 ID 精确匹配建立跨仓链接（清单声明的链接仍然生效）',
+    'help.option.group.sync.verbose': '显示额外的同步诊断信息',
     'help.option.status.json': '输出机器可读的索引和分析器来源信息',
     'help.option.json': 'JSON 输出',
     'help.option.group.impact.target': '要分析的符号或文件名',

package/dist/cli/index.js

@@ -53,6 +53,9 @@ program
     'Without this flag, analyze always updates the workspace index, which follows the ' +
     'checked-out working tree. Distinct from --default-branch (cosmetic base_ref).')
     .option('--no-stats', 'Omit volatile file/symbol counts from AGENTS.md and CLAUDE.md')
+    .option('--self-commit', 'Auto-commit AGENTS.md/CLAUDE.md changes after analyze (opt-in, off by default). ' +
+    'Scoped to only those two files (never `git add -A`); no-ops if neither exists, ' +
+    'neither changed, or the repo has no git identity configured.')
     .option('--skip-skills', 'Skip installing standard GitNexus skill files directly under .claude/skills/ and .agents/skills/. ' +
     'Does not suppress community skills from --skills (those use .claude/skills/gitnexus-area-*). ' +
     'Use --index-only to skip all AI-context file injection.')
@@ -184,13 +187,13 @@ program
     .command('wiki [path]')
     .description('Generate repository wiki from knowledge graph')
     .option('-f, --force', 'Force full regeneration even if up to date')
-    .option('--provider <provider>', 'LLM provider: openai, openrouter, azure, custom, cursor, claude, codex, or opencode (default: openai)')
-    .option('--model <model>', 'LLM model or Azure deployment name (default: minimax/minimax-m2.5)')
+    .option('--provider <provider>', 'LLM provider: minimax, openai, openrouter, azure, custom, cursor, claude, codex, or opencode (default: minimax)')
+    .option('--model <model>', 'LLM model or deployment name (default: MiniMax-M3)')
     .option('--base-url <url>', 'LLM API base URL. Azure v1: https://{resource}.openai.azure.com/openai/v1')
     .option('--api-key <key>', 'LLM API key or Azure api-key (saved to ~/.gitnexus/config.json)')
     .option('--api-version <version>', 'Azure api-version query param, e.g. 2024-10-21 (legacy Azure API only)')
-    .option('--reasoning-model', 'Mark deployment as reasoning model (o1/o3/o4-mini) — strips temperature, uses max_completion_tokens')
-    .option('--no-reasoning-model', 'Disable reasoning model mode (overrides saved config)')
+    .option('--reasoning-model', 'Enable reasoning mode; MiniMax-M3 uses adaptive thinking')
+    .option('--no-reasoning-model', 'Disable reasoning mode; MiniMax-M3 disables thinking')
     .option('--concurrency <n>', 'Parallel LLM calls (default: 3)', '3')
     .option('--timeout <seconds>', 'LLM request timeout in seconds (default: disabled)')
     .option('--retries <n>', 'Max LLM retry attempts per request (default: 3)')
@@ -257,6 +260,7 @@ program
     .command('trace <from> <to>')
     .description('Find the shortest directed path between two symbols (call + class-member edges)')
     .option('--from-uid <uid>', 'Source symbol UID (zero-ambiguity)')
+    .option('-f, --file <path>', 'Source file path hint (alias for --from-file)')
     .option('--from-file <path>', 'Source file path hint')
     .option('--to-uid <uid>', 'Target symbol UID (zero-ambiguity)')
     .option('--to-file <path>', 'Target file path hint')

package/dist/cli/resolve-invocation.d.ts

@@ -1,7 +1,7 @@
 /**
  * npm 11.x npx-install-crash nudge for the `analyze` command (#1939).
  *
- * The gitnexus/pnpm/npx selection itself lives in the canonical hook helper
+ * The gitnexus/pnpm/bun/npx selection itself lives in the canonical hook helper
  * (hooks/claude/resolve-analyze-cmd.cjs) — self-contained CJS because the copied
  * hook runtime cannot import from the package. We reuse it here via createRequire
  * instead of re-implementing it, so there is one source of truth for the
@@ -15,7 +15,11 @@ export { NPX_REF };
 export declare function getNpmMajorVersion(): number | null;
 /**
  * One-line stderr nudge when an npm 11+ user is on the npx install path (#1939).
- * Skipped when a global `gitnexus` or `pnpm` is already preferred, so it never
- * nags users who are not exposed to the npx/arborist crash.
+ * Skipped when a global `gitnexus`, `pnpm` or `bunx` is already preferred, so it
+ * never nags users who are not exposed to the npx/arborist crash. "Preferred"
+ * means usable, not merely on PATH: a `bunx` shim that no longer runs fails the
+ * cjs liveness probe, resolves back to `npx`, and so still gets warned here —
+ * without that, a broken bunx would suppress the warning AND emit a command that
+ * cannot run.
  */
 export declare function warnIfNpm11NpxRisk(): void;

package/dist/cli/resolve-invocation.js

@@ -1,7 +1,7 @@
 /**
  * npm 11.x npx-install-crash nudge for the `analyze` command (#1939).
  *
- * The gitnexus/pnpm/npx selection itself lives in the canonical hook helper
+ * The gitnexus/pnpm/bun/npx selection itself lives in the canonical hook helper
  * (hooks/claude/resolve-analyze-cmd.cjs) — self-contained CJS because the copied
  * hook runtime cannot import from the package. We reuse it here via createRequire
  * instead of re-implementing it, so there is one source of truth for the
@@ -53,8 +53,12 @@ export function getNpmMajorVersion() {
 }
 /**
  * One-line stderr nudge when an npm 11+ user is on the npx install path (#1939).
- * Skipped when a global `gitnexus` or `pnpm` is already preferred, so it never
- * nags users who are not exposed to the npx/arborist crash.
+ * Skipped when a global `gitnexus`, `pnpm` or `bunx` is already preferred, so it
+ * never nags users who are not exposed to the npx/arborist crash. "Preferred"
+ * means usable, not merely on PATH: a `bunx` shim that no longer runs fails the
+ * cjs liveness probe, resolves back to `npx`, and so still gets warned here —
+ * without that, a broken bunx would suppress the warning AND emit a command that
+ * cannot run.
  */
 export function warnIfNpm11NpxRisk() {
     if (resolveInvocationMode() !== 'npx')

package/dist/cli/setup.js

@@ -697,14 +697,15 @@ async function setupOpenCode(result) {
         result.skipped.push('OpenCode (not installed)');
         return;
     }
-    const { file: configPath, keyPath } = mcpTarget('opencode');
+    const target = mcpTarget('opencode');
     try {
-        const ok = await mergeJsoncFile(configPath, keyPath, getOpenCodeMcpEntry());
+        const configPath = await resolveMcpConfigFile(target);
+        const ok = await mergeJsoncFile(configPath, target.keyPath, getOpenCodeMcpEntry());
         if (ok) {
             result.configured.push('OpenCode');
         }
         else {
-            result.errors.push('OpenCode: opencode.json is corrupt — skipping to preserve existing content');
+            result.errors.push(`OpenCode: ${path.basename(configPath)} is corrupt — skipping to preserve existing content`);
         }
     }
     catch (err) {

package/dist/cli/skill-gen.d.ts

@@ -7,12 +7,7 @@
  * cross-community connections.
  */
 import { PipelineResult } from '../types/pipeline.js';
-export interface GeneratedSkillInfo {
-    name: string;
-    label: string;
-    symbolCount: number;
-    fileCount: number;
-}
+import type { GeneratedSkillInfo } from './generated-skill.js';
 /**
  * @brief Generate repo-specific skill files from detected communities
  * @param {string} repoPath - Absolute path to the repository root

package/dist/cli/tool.d.ts

@@ -66,6 +66,7 @@ export declare function checkCommand(options?: {
 }): Promise<void>;
 export declare function traceCommand(from?: string, to?: string, options?: {
     fromUid?: string;
+    file?: string;
     fromFile?: string;
     toUid?: string;
     toFile?: string;

package/dist/cli/tool.js

@@ -39,9 +39,18 @@ async function getBackend() {
  * and write directly to the real stdout fd (#324).
  *
  * Falls back to stderr if the fd write fails (e.g., broken pipe).
+ *
+ * `render` is for the commands that print prose instead of JSON: they hand over
+ * the STRUCTURED result and a formatter, so the payload stays visible to the
+ * exit-code test below — pre-formatting it into a string would hide the very
+ * fields that test reads.
  */
-function output(data) {
-    const text = typeof data === 'string' ? data : JSON.stringify(data, null, 2);
+function output(data, render) {
+    const text = render
+        ? render(data)
+        : typeof data === 'string'
+            ? data
+            : JSON.stringify(data, null, 2);
     try {
         writeSync(1, text + '\n');
     }
@@ -54,16 +63,34 @@ function output(data) {
         // Fallback: stderr (previous behavior, works on all platforms)
         process.stderr.write(text + '\n');
     }
-    // Backend failures come back as `{ error }` payloads rather than throws
-    // (#2469). Every tool command routes its result through here, so this is
-    // the one place that keeps scripted callers honest: print the payload,
-    // then exit non-zero.
-    if (data &&
-        typeof data === 'object' &&
-        'error' in data &&
-        typeof data.error === 'string' &&
-        data.error.trim().length > 0) {
-        process.exitCode = 1;
+    // Every tool command routes its result through here, so this is the one place
+    // that keeps scripted callers honest — `gitnexus impact … && <edit>` and
+    // `gitnexus detect-changes && git commit` must not proceed on a result that
+    // did not complete. Two shapes say so, and both exit non-zero:
+    //
+    //   • `error` — a backend failure, returned as a payload rather than thrown
+    //     (#2469).
+    //   • `partial` — a step failed and was SWALLOWED (#2915), so the counts and
+    //     risk level are lower bounds a caller would otherwise read as clean. It
+    //     is cross-tool vocabulary, not detect_changes' private flag: `query`
+    //     raises it for degraded enrichment or a partial FTS failure, and `impact`
+    //     for an interrupted traversal or capped per-symbol enrichment — a short
+    //     caller set and an under-ranked risk, on the tool AGENTS.md makes a MUST
+    //     gate before every edit.
+    //
+    // One code for both, because `&&` cannot tell two apart and a "softer" code
+    // for `partial` would invite exempting it again.
+    //
+    // NOT here: `truncated`, where only the LISTING is capped while the counts and
+    // risk are computed over the full set — the verdict is sound, so failing on it
+    // would fire on every large-but-healthy diff. Nor `partialProbe`, a narrower
+    // per-candidate flag on ambiguous impact targets.
+    if (data && typeof data === 'object') {
+        const payload = data;
+        const failed = (typeof payload.error === 'string' && payload.error.trim().length > 0) ||
+            payload.partial === true;
+        if (failed)
+            process.exitCode = 1;
     }
 }
 /**
@@ -275,7 +302,9 @@ export async function detectChangesCommand(options) {
         if (Array.isArray(result.affected_processes))
             result.affected_processes = result.affected_processes.slice(0, limit);
     }
-    output(formatDetectChangesResult(result));
+    // Hand over the structured result plus its formatter, not the formatted text:
+    // `output()` reads `error` / `partial` off the payload to set the exit code.
+    output(result, formatDetectChangesResult);
 }
 export async function checkCommand(options) {
     if (!options?.cycles) {
@@ -290,21 +319,42 @@ export async function checkCommand(options) {
             repo: options.repo,
             branch: options.branch,
         });
+        // A rendering guard, not an exit-code decision — `output()` owns that. An
+        // error payload carries no `cycles` array, so the prose branch below would
+        // throw on it; print the structured payload and stop.
         if (result?.error) {
             output(result);
-            process.exitCode = 1;
             return;
         }
         if (options.json) {
             output(result);
         }
-        else if (result.cycleCount === 0) {
+        else if (result.status === 'clean') {
             output('No circular imports found.');
         }
         else {
             output(result.cycles.map((cycle) => cycle.files.join(' -> ')).join('\n'));
+            // Past the enumeration cap the tool reports one representative cycle per
+            // component instead of every elementary cycle. Say so, or the short list
+            // reads as the whole truth on exactly the repositories where it is not.
+            if (result.enumeration === 'component-representatives') {
+                // Phrased to need no plural: `checkCommand` predates the `t()` i18n
+                // layer and none of its output goes through it, so inventing a plural
+                // here by hand would be the only one in the file.
+                output(`\n(showing one representative cycle per circular component — ` +
+                    `${result.componentCount} in total; the full enumeration exceeded the safety limit.)`);
+            }
         }
-        if (result.cycleCount > 0)
+        // Policy, not degradation: a clean run that FOUND cycles is `check` failing
+        // its own check, so `output()` — which fails closed on `error` and `partial`
+        // — deliberately knows nothing about it.
+        //
+        // Keyed on `status`, NOT on `cycleCount`. Past the enumeration cap the
+        // report carries `cycleCount: null` on purpose, because a partial count must
+        // not read as a real one — and `null > 0` is false, so counting here would
+        // exit 0 on precisely the repositories with the most cycles. `status`
+        // answers "were any found" in both enumeration modes.
+        if (result.status === 'cycles_found')
             process.exitCode = 1;
     }
     catch (error) {
@@ -317,6 +367,12 @@ export async function traceCommand(from, to, options) {
         cliErrorKey('tool.usage.trace');
         process.exit(1);
     }
+    if (options?.file !== undefined &&
+        options?.fromFile !== undefined &&
+        options.file !== options.fromFile) {
+        cliErrorKey('tool.usage.trace');
+        process.exit(1);
+    }
     if ((!from?.trim() && !options?.fromUid) || (!to?.trim() && !options?.toUid)) {
         cliErrorKey('tool.usage.trace');
         process.exit(1);
@@ -332,10 +388,11 @@ export async function traceCommand(from, to, options) {
     }
     try {
         const backend = await getBackend();
+        const fromFile = options?.fromFile ?? options?.file;
         const result = await backend.callTool('trace', {
             from: from || undefined,
             from_uid: options?.fromUid,
-            from_file: options?.fromFile,
+            from_file: fromFile,
             to: to || undefined,
             to_uid: options?.toUid,
             to_file: options?.toFile,

package/dist/cli/wiki.js

@@ -11,7 +11,7 @@ import cliProgress from 'cli-progress';
 import { getGitRoot, isGitRepo } from '../storage/git.js';
 import { getStoragePaths, loadMeta, loadCLIConfig, saveCLIConfig, } from '../storage/repo-manager.js';
 import { WikiGenerator } from '../core/wiki/generator.js';
-import { parseLLMAllowedInsecureHttpHosts, resolveLLMConfig, } from '../core/wiki/llm-client.js';
+import { MINIMAX_MODEL_IDS, MINIMAX_OPENAI_BASE_URLS, parseLLMAllowedInsecureHttpHosts, resolveLLMConfig, } from '../core/wiki/llm-client.js';
 import { detectCursorCLI } from '../core/wiki/cursor-client.js';
 import { detectLocalCLI } from '../core/wiki/local-cli-client.js';
 import { logger } from '../core/logger.js';
@@ -176,6 +176,14 @@ const wikiCommandImpl = async (inputPath, options) => {
         options?.reasoningModel !== undefined) {
         const existing = await loadCLIConfig();
         const updates = {};
+        const providerChanged = !!options.provider && options.provider !== existing.provider;
+        if (providerChanged) {
+            updates.apiKey = undefined;
+            updates.baseUrl = undefined;
+            updates.model = undefined;
+            updates.apiVersion = undefined;
+            updates.isReasoningModel = undefined;
+        }
         if (options.apiKey)
             updates.apiKey = options.apiKey;
         if (options.baseUrl)
@@ -186,6 +194,17 @@ const wikiCommandImpl = async (inputPath, options) => {
             updates.apiVersion = options.apiVersion;
         if (options.reasoningModel !== undefined)
             updates.isReasoningModel = options.reasoningModel;
+        if (options.provider === 'minimax') {
+            if (providerChanged && options.reasoningModel === undefined) {
+                updates.isReasoningModel = undefined;
+            }
+            if (!options.baseUrl && (providerChanged || !existing.baseUrl)) {
+                updates.baseUrl = MINIMAX_OPENAI_BASE_URLS.global_en;
+            }
+            if (!options.model && (providerChanged || !existing.model)) {
+                updates.model = MINIMAX_MODEL_IDS[0];
+            }
+        }
         // Save model to appropriate field based on provider.
         if (options.model) {
             const targetProvider = options.provider ?? existing.provider;
@@ -201,7 +220,7 @@ const wikiCommandImpl = async (inputPath, options) => {
     }
     const savedConfig = await loadCLIConfig();
     const hasSavedConfig = !!(isLocalProvider(savedConfig.provider) ||
-        (savedConfig.apiKey && savedConfig.baseUrl));
+        (savedConfig.apiKey && (savedConfig.baseUrl || savedConfig.provider === 'minimax')));
     const hasCLIOverrides = !!(options?.apiKey ||
         options?.model ||
         options?.baseUrl ||
@@ -224,7 +243,7 @@ const wikiCommandImpl = async (inputPath, options) => {
             // Non-interactive mode — need either API key or Cursor CLI
             if (!llmConfig.apiKey && !isLocalProvider(llmConfig.provider)) {
                 console.log('  Error: No LLM API key found.');
-                console.log('  Set OPENAI_API_KEY or GITNEXUS_API_KEY environment variable,');
+                console.log('  Set MINIMAX_API_KEY, GITNEXUS_API_KEY, or OPENAI_API_KEY,');
                 console.log('  or pass --api-key <key>, or use --provider cursor|claude|codex|opencode.\n');
                 process.exitCode = 1;
                 return;
@@ -233,7 +252,7 @@ const wikiCommandImpl = async (inputPath, options) => {
         }
         else {
             console.log("  No LLM configured. Let's set it up.\n");
-            console.log('  Supports OpenAI, OpenRouter, Azure, any OpenAI-compatible API, Cursor CLI, Claude CLI, Codex CLI, or OpenCode CLI.\n');
+            console.log('  Supports MiniMax, OpenAI-compatible APIs, and local agent CLIs.\n');
             // Check if local agent CLIs are available.
             const hasCursor = detectCursorCLI();
             const hasClaude = detectLocalCLI('claude');
@@ -245,7 +264,9 @@ const wikiCommandImpl = async (inputPath, options) => {
             console.log('  [2] OpenRouter (openrouter.ai)');
             console.log('  [3] Azure OpenAI');
             console.log('  [4] Custom endpoint');
-            let nextChoice = 5;
+            console.log('  [5] MiniMax Global (api.minimax.io)');
+            console.log('  [6] MiniMax China (api.minimaxi.com)');
+            let nextChoice = 7;
             if (hasCursor) {
                 const choice = String(nextChoice++);
                 localChoices.push({
@@ -356,10 +377,10 @@ const wikiCommandImpl = async (inputPath, options) => {
                 };
             }
             else {
-                // OpenAI-compatible provider (OpenAI, OpenRouter, Custom)
+                // OpenAI-compatible provider setup
                 if (choice === '2') {
                     baseUrl = 'https://openrouter.ai/api/v1';
-                    defaultModel = 'minimax/minimax-m2.5';
+                    defaultModel = '';
                     provider = 'openrouter';
                 }
                 else if (choice === '4') {
@@ -372,16 +393,30 @@ const wikiCommandImpl = async (inputPath, options) => {
                     defaultModel = 'gpt-4o-mini';
                     provider = 'custom';
                 }
+                else if (choice === '5' || choice === '6') {
+                    baseUrl =
+                        choice === '6' ? MINIMAX_OPENAI_BASE_URLS.cn_zh : MINIMAX_OPENAI_BASE_URLS.global_en;
+                    defaultModel = MINIMAX_MODEL_IDS[0];
+                    provider = 'minimax';
+                }
                 else {
                     baseUrl = 'https://api.openai.com/v1';
                     defaultModel = 'gpt-4o-mini';
                     provider = 'openai';
                 }
                 // Model
-                const modelInput = await prompt(`  Model (default: ${defaultModel}): `);
+                const modelInput = await prompt(defaultModel ? `  Model (default: ${defaultModel}): ` : '  Model: ');
                 const model = modelInput || defaultModel;
+                if (!model) {
+                    console.log('\n  No model provided. Aborting.\n');
+                    process.exitCode = 1;
+                    return;
+                }
                 // API key — pre-fill hint if env var exists
-                const envKey = process.env.GITNEXUS_API_KEY || process.env.OPENAI_API_KEY || '';
+                const envKey = (provider === 'minimax' ? process.env.MINIMAX_API_KEY : undefined) ||
+                    process.env.GITNEXUS_API_KEY ||
+                    process.env.OPENAI_API_KEY ||
+                    '';
                 if (envKey) {
                     const masked = envKey.slice(0, 6) + '...' + envKey.slice(-4);
                     const useEnv = await prompt(`  Use existing env key (${masked})? (Y/n): `);
@@ -401,7 +436,15 @@ const wikiCommandImpl = async (inputPath, options) => {
                     return;
                 }
                 // Save
-                await saveCLIConfig({ apiKey: key, baseUrl, model, provider });
+                await saveCLIConfig({
+                    ...savedConfig,
+                    apiKey: key,
+                    baseUrl,
+                    model,
+                    provider,
+                    apiVersion: undefined,
+                    isReasoningModel: undefined,
+                });
                 console.log('  Config saved to ~/.gitnexus/config.json\n');
                 llmConfig = { ...llmConfig, apiKey: key, baseUrl, model, provider };
             }

package/dist/config/ignore-service.d.ts

@@ -3,6 +3,8 @@ import type { Path } from 'path-scurry';
 export declare const shouldIgnorePath: (filePath: string) => boolean;
 /** Check if a directory name is in the hardcoded ignore list */
 export declare const isHardcodedIgnoredDirectory: (name: string) => boolean;
+/** Apply directory ignore rules that depend on repository-relative depth. */
+export declare const isHardcodedIgnoredDirectoryAtPath: (repoRoot: string, directoryPath: string) => boolean;
 /**
  * Load .gitignore and .gitnexusignore rules from the repo root.
  * Returns an `ignore` instance with all patterns, or null if no files found.