@mcarvin/smart-diff 1.1.0 → 2.1.0

package/dist/index.mjs

@@ -1,3 +1,4 @@
+import { generateText } from 'ai';
 import { resolve, relative } from 'node:path';
 import { simpleGit } from 'simple-git';
 
@@ -33,9 +34,55 @@ typeof SuppressedError === "function" ? SuppressedError : function (error, suppr
     return e.name = "SuppressedError", e.error = error, e.suppressed = suppressed, e;
 };
 
+const DEFAULT_LLM_MAX_DIFF_CHARS = 120000;
+const DEFAULT_GIT_DIFF_SYSTEM_PROMPT = `You are a senior software engineer helping developers understand code and configuration changes from the git context they supplied.
+You receive: commit subject lines (when available), changed file paths, and unified git patch(es)—either one range diff or concatenated per-commit patches, depending on how the diff was produced. Patches may be truncated mid-section with an explicit marker—do not infer changes beyond visible lines.
+Explain what changed in terms of behavior, APIs, data, configuration, security, and operational risk. Tie claims to the patch when possible.
+Produce a concise, developer-focused summary in Markdown.
+Use sections that fit the change (for example: Highlights, Breaking or risky changes, API / contract changes, Data & schema, Configuration & infra, Security & auth, Tests & quality). Omit empty sections.
+Group related changes; do not list every individual file. When multiple commits appear in the context, briefly separate notable themes by commit when helpful.
+If the user message includes a Team line, use that exact team name in the summary title (for example: "## <Team> – Change summary" or similar).`;
+const LLM_GATEWAY_REQUIRED_MESSAGE = "No LLM provider configured. Set LLM_PROVIDER (openai | openai-compatible | anthropic | google | bedrock | mistral | cohere | groq | xai | deepseek), " +
+    "or a provider API key (OPENAI_API_KEY, LLM_API_KEY, ANTHROPIC_API_KEY, GOOGLE_GENERATIVE_AI_API_KEY, MISTRAL_API_KEY, COHERE_API_KEY, GROQ_API_KEY, XAI_API_KEY, DEEPSEEK_API_KEY), " +
+    "or LLM_BASE_URL / OPENAI_BASE_URL for an OpenAI-compatible gateway, " +
+    "or JSON in OPENAI_DEFAULT_HEADERS / LLM_DEFAULT_HEADERS. " +
+    "Alternatively pass llmModelProvider or openAiClientProvider to generateSummary or summarizeGitDiff.";
+
+const DEFAULT_MODEL_BY_PROVIDER = {
+    openai: "gpt-4o-mini",
+    "openai-compatible": "gpt-4o-mini",
+    anthropic: "claude-3-5-haiku-latest",
+    google: "gemini-2.0-flash",
+    bedrock: "anthropic.claude-3-5-haiku-20241022-v1:0",
+    mistral: "mistral-small-latest",
+    cohere: "command-r-08-2024",
+    groq: "llama-3.1-8b-instant",
+    xai: "grok-2-latest",
+    deepseek: "deepseek-chat",
+};
+const VALID_PROVIDERS = new Set([
+    "openai",
+    "openai-compatible",
+    "anthropic",
+    "google",
+    "bedrock",
+    "mistral",
+    "cohere",
+    "groq",
+    "xai",
+    "deepseek",
+]);
+function readEnv(name) {
+    var _a;
+    const value = (_a = process.env[name]) === null || _a === void 0 ? void 0 : _a.trim();
+    return value && value.length > 0 ? value : undefined;
+}
+function isValidProviderId(value) {
+    return VALID_PROVIDERS.has(value);
+}
 function resolveLlmBaseUrl() {
-    var _a, _b, _c;
-    return ((_b = (_a = process.env.LLM_BASE_URL) === null || _a === void 0 ? void 0 : _a.trim()) !== null && _b !== void 0 ? _b : (_c = process.env.OPENAI_BASE_URL) === null || _c === void 0 ? void 0 : _c.trim());
+    var _a;
+    return (_a = readEnv("LLM_BASE_URL")) !== null && _a !== void 0 ? _a : readEnv("OPENAI_BASE_URL");
 }
 function parseHeaderJsonObject(raw) {
     const trimmed = raw === null || raw === void 0 ? void 0 : raw.trim();
@@ -66,87 +113,187 @@ function parseLlmDefaultHeadersFromEnv() {
     const merged = Object.assign(Object.assign({}, base), override);
     return Object.keys(merged).length > 0 ? merged : undefined;
 }
-function findAuthorizationHeaderName(headers) {
-    return Object.keys(headers).find((k) => k.toLowerCase() === "authorization");
-}
-function stripBearerPrefix(value) {
+function resolveOpenAiApiKey() {
     var _a;
-    const trimmed = value.trim();
-    const match = /^Bearer\s+(\S+)/i.exec(trimmed);
-    return (_a = match === null || match === void 0 ? void 0 : match[1]) !== null && _a !== void 0 ? _a : trimmed;
-}
-function splitPromotableAuthorizationFromHeaders(headers) {
-    const authName = findAuthorizationHeaderName(headers);
-    if (!authName) {
-        return { defaultHeaders: headers };
-    }
-    const raw = headers[authName];
-    if (!raw) {
-        return { defaultHeaders: headers };
-    }
-    const token = stripBearerPrefix(raw);
-    const looksBearer = /^Bearer\s+\S+/i.test(raw.trim());
-    const looksOpenAiKey = /^sk-/i.test(token);
-    if (!looksBearer && !looksOpenAiKey) {
-        return { defaultHeaders: headers };
-    }
-    const next = Object.assign({}, headers);
-    delete next[authName];
-    return { defaultHeaders: next, apiKeyFromAuthHeader: token };
-}
-function shouldUseLlmGateway() {
-    var _a, _b, _c;
-    const apiKey = (_b = (_a = process.env.LLM_API_KEY) === null || _a === void 0 ? void 0 : _a.trim()) !== null && _b !== void 0 ? _b : (_c = process.env.OPENAI_API_KEY) === null || _c === void 0 ? void 0 : _c.trim();
-    if (apiKey)
-        return true;
-    if (resolveLlmBaseUrl())
-        return true;
-    const jsonHeaders = parseLlmDefaultHeadersFromEnv();
-    if (jsonHeaders && Object.keys(jsonHeaders).length > 0)
-        return true;
-    return false;
+    return (_a = readEnv("LLM_API_KEY")) !== null && _a !== void 0 ? _a : readEnv("OPENAI_API_KEY");
 }
-function resolveOpenAiLikeClientInit() {
-    var _a, _b, _c, _d, _e;
-    const baseURL = resolveLlmBaseUrl();
-    const mergedHeaders = (_a = parseLlmDefaultHeadersFromEnv()) !== null && _a !== void 0 ? _a : {};
-    const envApiKey = (_e = (_c = (_b = process.env.LLM_API_KEY) === null || _b === void 0 ? void 0 : _b.trim()) !== null && _c !== void 0 ? _c : (_d = process.env.OPENAI_API_KEY) === null || _d === void 0 ? void 0 : _d.trim()) !== null && _e !== void 0 ? _e : "";
-    let defaultHeaders;
-    let apiKey = envApiKey;
-    if (apiKey.length === 0) {
-        const split = splitPromotableAuthorizationFromHeaders(mergedHeaders);
-        if (split.apiKeyFromAuthHeader) {
-            apiKey = split.apiKeyFromAuthHeader;
-        }
-        defaultHeaders =
-            Object.keys(split.defaultHeaders).length > 0
-                ? split.defaultHeaders
-                : undefined;
+function detectLlmProvider() {
+    var _a, _b;
+    const explicit = (_a = readEnv("LLM_PROVIDER")) === null || _a === void 0 ? void 0 : _a.toLowerCase();
+    if (explicit && isValidProviderId(explicit)) {
+        return explicit;
     }
-    else {
-        defaultHeaders =
-            Object.keys(mergedHeaders).length > 0 ? mergedHeaders : undefined;
+    if (resolveLlmBaseUrl()) {
+        return "openai-compatible";
     }
-    return Object.assign(Object.assign({ apiKey: apiKey.length > 0 ? apiKey : "unused" }, (baseURL ? { baseURL } : {})), (defaultHeaders ? { defaultHeaders } : {}));
+    if (resolveOpenAiApiKey()) {
+        return "openai";
+    }
+    if (readEnv("ANTHROPIC_API_KEY"))
+        return "anthropic";
+    if ((_b = readEnv("GOOGLE_GENERATIVE_AI_API_KEY")) !== null && _b !== void 0 ? _b : readEnv("GOOGLE_API_KEY"))
+        return "google";
+    if (readEnv("MISTRAL_API_KEY"))
+        return "mistral";
+    if (readEnv("COHERE_API_KEY"))
+        return "cohere";
+    if (readEnv("GROQ_API_KEY"))
+        return "groq";
+    if (readEnv("XAI_API_KEY"))
+        return "xai";
+    if (readEnv("DEEPSEEK_API_KEY"))
+        return "deepseek";
+    if (parseLlmDefaultHeadersFromEnv())
+        return "openai";
+    return undefined;
+}
+function isLlmProviderConfigured() {
+    return detectLlmProvider() !== undefined;
 }
-function createOpenAiLikeClient() {
+function defaultModelForProvider(provider) {
+    return DEFAULT_MODEL_BY_PROVIDER[provider];
+}
+function createOpenAiModel(modelId) {
     return __awaiter(this, void 0, void 0, function* () {
-        const { default: OpenAI } = yield import('openai');
-        return new OpenAI(resolveOpenAiLikeClientInit());
+        const { createOpenAI } = yield import('@ai-sdk/openai');
+        const apiKey = resolveOpenAiApiKey();
+        const headers = parseLlmDefaultHeadersFromEnv();
+        const provider = createOpenAI(Object.assign(Object.assign({}, (apiKey ? { apiKey } : {})), (headers ? { headers } : {})));
+        return provider(modelId);
+    });
+}
+function createOpenAiCompatibleModel(modelId) {
+    return __awaiter(this, void 0, void 0, function* () {
+        var _a;
+        const { createOpenAICompatible } = yield import('@ai-sdk/openai-compatible');
+        const baseURL = resolveLlmBaseUrl();
+        if (!baseURL) {
+            throw new Error("openai-compatible provider requires LLM_BASE_URL or OPENAI_BASE_URL to be set.");
+        }
+        const apiKey = resolveOpenAiApiKey();
+        const headers = parseLlmDefaultHeadersFromEnv();
+        const provider = createOpenAICompatible(Object.assign(Object.assign({ name: (_a = readEnv("LLM_PROVIDER_NAME")) !== null && _a !== void 0 ? _a : "openai-compatible", baseURL }, (apiKey ? { apiKey } : {})), (headers ? { headers } : {})));
+        return provider(modelId);
+    });
+}
+function wrapMissingPeer(failure) {
+    const err = new Error(`Failed to load optional provider package "${failure.pkg}" for LLM_PROVIDER="${failure.provider}". ` +
+        `Install it with \`npm install ${failure.pkg}\`.`);
+    err.cause = failure.cause;
+    return err;
+}
+function importOptional(provider, pkg, loader) {
+    return __awaiter(this, void 0, void 0, function* () {
+        try {
+            return yield loader();
+        }
+        catch (cause) {
+            throw wrapMissingPeer({ provider, pkg, cause });
+        }
+    });
+}
+function createAnthropicModel(modelId) {
+    return __awaiter(this, void 0, void 0, function* () {
+        const mod = yield importOptional("anthropic", "@ai-sdk/anthropic", () => import('@ai-sdk/anthropic'));
+        const apiKey = readEnv("ANTHROPIC_API_KEY");
+        const provider = mod.createAnthropic(apiKey ? { apiKey } : undefined);
+        return provider(modelId);
+    });
+}
+function createGoogleModel(modelId) {
+    return __awaiter(this, void 0, void 0, function* () {
+        var _a;
+        const mod = yield importOptional("google", "@ai-sdk/google", () => import('@ai-sdk/google'));
+        const apiKey = (_a = readEnv("GOOGLE_GENERATIVE_AI_API_KEY")) !== null && _a !== void 0 ? _a : readEnv("GOOGLE_API_KEY");
+        const provider = mod.createGoogleGenerativeAI(apiKey ? { apiKey } : undefined);
+        return provider(modelId);
+    });
+}
+function createBedrockModel(modelId) {
+    return __awaiter(this, void 0, void 0, function* () {
+        const mod = yield importOptional("bedrock", "@ai-sdk/amazon-bedrock", () => import('@ai-sdk/amazon-bedrock'));
+        const provider = mod.createAmazonBedrock();
+        return provider(modelId);
+    });
+}
+function createMistralModel(modelId) {
+    return __awaiter(this, void 0, void 0, function* () {
+        const mod = yield importOptional("mistral", "@ai-sdk/mistral", () => import('@ai-sdk/mistral'));
+        const apiKey = readEnv("MISTRAL_API_KEY");
+        const provider = mod.createMistral(apiKey ? { apiKey } : undefined);
+        return provider(modelId);
+    });
+}
+function createCohereModel(modelId) {
+    return __awaiter(this, void 0, void 0, function* () {
+        const mod = yield importOptional("cohere", "@ai-sdk/cohere", () => import('@ai-sdk/cohere'));
+        const apiKey = readEnv("COHERE_API_KEY");
+        const provider = mod.createCohere(apiKey ? { apiKey } : undefined);
+        return provider(modelId);
+    });
+}
+function createGroqModel(modelId) {
+    return __awaiter(this, void 0, void 0, function* () {
+        const mod = yield importOptional("groq", "@ai-sdk/groq", () => import('@ai-sdk/groq'));
+        const apiKey = readEnv("GROQ_API_KEY");
+        const provider = mod.createGroq(apiKey ? { apiKey } : undefined);
+        return provider(modelId);
+    });
+}
+function createXaiModel(modelId) {
+    return __awaiter(this, void 0, void 0, function* () {
+        const mod = yield importOptional("xai", "@ai-sdk/xai", () => import('@ai-sdk/xai'));
+        const apiKey = readEnv("XAI_API_KEY");
+        const provider = mod.createXai(apiKey ? { apiKey } : undefined);
+        return provider(modelId);
+    });
+}
+function createDeepseekModel(modelId) {
+    return __awaiter(this, void 0, void 0, function* () {
+        const mod = yield importOptional("deepseek", "@ai-sdk/deepseek", () => import('@ai-sdk/deepseek'));
+        const apiKey = readEnv("DEEPSEEK_API_KEY");
+        const provider = mod.createDeepSeek(apiKey ? { apiKey } : undefined);
+        return provider(modelId);
+    });
+}
+function resolveLanguageModel() {
+    return __awaiter(this, arguments, void 0, function* (options = {}) {
+        var _a, _b, _c;
+        const provider = (_a = options.provider) !== null && _a !== void 0 ? _a : detectLlmProvider();
+        if (!provider) {
+            throw new Error("No LLM provider could be resolved. Set LLM_PROVIDER or a provider API key " +
+                "(OPENAI_API_KEY, ANTHROPIC_API_KEY, GOOGLE_GENERATIVE_AI_API_KEY, MISTRAL_API_KEY, " +
+                "COHERE_API_KEY, GROQ_API_KEY, XAI_API_KEY, DEEPSEEK_API_KEY), or LLM_BASE_URL for an OpenAI-compatible gateway.");
+        }
+        const modelId = (_c = (_b = options.model) !== null && _b !== void 0 ? _b : readEnv("LLM_MODEL")) !== null && _c !== void 0 ? _c : defaultModelForProvider(provider);
+        switch (provider) {
+            case "openai":
+                return createOpenAiModel(modelId);
+            case "openai-compatible":
+                return createOpenAiCompatibleModel(modelId);
+            case "anthropic":
+                return createAnthropicModel(modelId);
+            case "google":
+                return createGoogleModel(modelId);
+            case "bedrock":
+                return createBedrockModel(modelId);
+            case "mistral":
+                return createMistralModel(modelId);
+            case "cohere":
+                return createCohereModel(modelId);
+            case "groq":
+                return createGroqModel(modelId);
+            case "xai":
+                return createXaiModel(modelId);
+            case "deepseek":
+                return createDeepseekModel(modelId);
+            default: {
+                const _exhaustive = provider;
+                throw new Error(`Unhandled LLM provider: ${String(_exhaustive)}`);
+            }
+        }
     });
 }
-
-const DEFAULT_LLM_MAX_DIFF_CHARS = 120000;
-const DEFAULT_GIT_DIFF_SYSTEM_PROMPT = `You are a senior software engineer helping developers understand code and configuration changes from the git context they supplied.
-You receive: commit subject lines (when available), changed file paths, and unified git patch(es)—either one range diff or concatenated per-commit patches, depending on how the diff was produced. Patches may be truncated mid-section with an explicit marker—do not infer changes beyond visible lines.
-Explain what changed in terms of behavior, APIs, data, configuration, security, and operational risk. Tie claims to the patch when possible.
-Produce a concise, developer-focused summary in Markdown.
-Use sections that fit the change (for example: Highlights, Breaking or risky changes, API / contract changes, Data & schema, Configuration & infra, Security & auth, Tests & quality). Omit empty sections.
-Group related changes; do not list every individual file. When multiple commits appear in the context, briefly separate notable themes by commit when helpful.
-If the user message includes a Team line, use that exact team name in the summary title (for example: "## <Team> – Change summary" or similar).`;
-const LLM_GATEWAY_REQUIRED_MESSAGE = "No LLM gateway configured. Set OPENAI_API_KEY or LLM_API_KEY, and/or LLM_BASE_URL or OPENAI_BASE_URL, " +
-    "and/or JSON in OPENAI_DEFAULT_HEADERS or LLM_DEFAULT_HEADERS. " +
-    "Alternatively pass openAiClientProvider to generateSummary or summarizeGitDiff.";
 
 function resolveLlmMaxDiffChars(cliOverride) {
     var _a;
@@ -174,18 +321,26 @@ function truncateUnifiedDiffForLlm(diffText, maxChars) {
 function markdownDiffTruncationNotice(originalChars, maxChars) {
     return `> **Truncated diff:** The unified diff was ${originalChars} characters; only the first ${maxChars} were sent to the model. The summary may not reflect the full change set. Narrow the ref range, adjust path filters, or raise \`maxDiffChars\` / \`LLM_MAX_DIFF_CHARS\`—often together with switching to a model whose context window can fit a larger prompt.\n\n`;
 }
+function resolveMaxOutputTokens() {
+    var _a;
+    const raw = (_a = process.env.LLM_MAX_TOKENS) !== null && _a !== void 0 ? _a : process.env.OPENAI_MAX_TOKENS;
+    const parsed = raw !== undefined ? Number.parseInt(raw, 10) : 4000;
+    return Number.isFinite(parsed) && parsed > 0 ? parsed : 4000;
+}
 function generateSummary(input) {
     return __awaiter(this, void 0, void 0, function* () {
-        var _a, _b;
-        const { diffText, fileNames, commits, flags, openAiClientProvider, diffSummary, } = input;
-        if (!shouldUseLlmGateway() && openAiClientProvider === undefined) {
+        var _a;
+        const { diffText, fileNames, commits, flags, llmModelProvider, diffSummary, } = input;
+        if (!llmModelProvider && !isLlmProviderConfigured()) {
             throw new Error(LLM_GATEWAY_REQUIRED_MESSAGE);
         }
         const maxDiffChars = resolveLlmMaxDiffChars(flags.maxDiffChars);
         const diffTruncated = diffText.length > maxDiffChars;
         const diffForLlm = truncateUnifiedDiffForLlm(diffText, maxDiffChars);
-        const userContent = buildOpenAiUserContent(flags, commits, fileNames, diffForLlm, diffSummary);
-        const summary = yield callOpenAi(userContent, (_a = flags.model) !== null && _a !== void 0 ? _a : "gpt-4o-mini", (_b = flags.systemPrompt) !== null && _b !== void 0 ? _b : DEFAULT_GIT_DIFF_SYSTEM_PROMPT, openAiClientProvider !== null && openAiClientProvider !== void 0 ? openAiClientProvider : (() => __awaiter(this, void 0, void 0, function* () { return createOpenAiLikeClient(); })));
+        const userContent = buildUserContent(flags, commits, fileNames, diffForLlm, diffSummary);
+        const systemPrompt = (_a = flags.systemPrompt) !== null && _a !== void 0 ? _a : DEFAULT_GIT_DIFF_SYSTEM_PROMPT;
+        const maxOutputTokens = resolveMaxOutputTokens();
+        const summary = yield callLlm(userContent, systemPrompt, maxOutputTokens, llmModelProvider, flags);
         if (!diffTruncated) {
             return summary;
         }
@@ -212,7 +367,7 @@ function formatRegexFilterLines(flags) {
     return (`${incLine}${excLine}` +
         "Git context shape: concatenated per-commit unified patches for commits that pass the message filters.\n");
 }
-function buildOpenAiUserContent(flags, commits, fileNames, diffText, diffSummary) {
+function buildUserContent(flags, commits, fileNames, diffText, diffSummary) {
     var _a, _b;
     const from = flags.from;
     const to = (_a = flags.to) !== null && _a !== void 0 ? _a : "HEAD";
@@ -242,31 +397,20 @@ function buildOpenAiUserContent(flags, commits, fileNames, diffText, diffSummary
         "=== Git context (unified diff(s); patches may be truncated with an explicit marker) ===\n" +
         diffText);
 }
-function callOpenAi(userContent, model, systemPrompt, openAiClientProvider) {
+function callLlm(userContent, systemPrompt, maxOutputTokens, llmModelProvider, flags) {
     return __awaiter(this, void 0, void 0, function* () {
-        var _a, _b, _c, _d, _e, _f;
-        const client = yield openAiClientProvider();
-        const maxTokensRaw = (_a = process.env.LLM_MAX_TOKENS) !== null && _a !== void 0 ? _a : process.env.OPENAI_MAX_TOKENS;
-        const parsed = maxTokensRaw !== undefined ? Number.parseInt(maxTokensRaw, 10) : 4000;
-        const maxTokens = Number.isFinite(parsed) && parsed > 0 ? parsed : 4000;
-        const response = yield client.chat.completions.create({
+        const model = llmModelProvider
+            ? yield llmModelProvider()
+            : yield resolveLanguageModel(Object.assign(Object.assign({}, (flags.provider ? { provider: flags.provider } : {})), (flags.model ? { model: flags.model } : {})));
+        const result = yield generateText({
             model,
-            messages: [
-                {
-                    role: "system",
-                    content: systemPrompt,
-                },
-                {
-                    role: "user",
-                    content: userContent,
-                },
-            ],
+            system: systemPrompt,
+            prompt: userContent,
             temperature: 0.2,
-            max_tokens: maxTokens,
+            maxOutputTokens,
         });
-        const typedResponse = response;
-        const text = (_f = (_e = (_d = (_c = (_b = typedResponse.choices) === null || _b === void 0 ? void 0 : _b[0]) === null || _c === void 0 ? void 0 : _c.message) === null || _d === void 0 ? void 0 : _d.content) === null || _e === void 0 ? void 0 : _e.trim()) !== null && _f !== void 0 ? _f : "";
-        return text.length > 0 ? text : "No summary generated by OpenAI.";
+        const text = result.text.trim();
+        return text.length > 0 ? text : "No summary generated by the model.";
     });
 }
 
@@ -348,6 +492,130 @@ function filterCommitsByMessageRegexes(commits, includePatterns, excludePatterns
     return commits.filter((c) => commitMessagePassesFilters(c.message, includeRes, excludeRes));
 }
 
+const DEFAULT_NOISE_EXCLUDES = [
+    "package-lock.json",
+    "yarn.lock",
+    "pnpm-lock.yaml",
+    "npm-shrinkwrap.json",
+    "bun.lockb",
+    "go.sum",
+    "Cargo.lock",
+    "Gemfile.lock",
+    "composer.lock",
+    "Pipfile.lock",
+    "poetry.lock",
+    "uv.lock",
+    "Podfile.lock",
+    "node_modules",
+    "dist",
+    "build",
+    "out",
+    "coverage",
+    "__snapshots__",
+];
+function normalizeContextLines(raw) {
+    if (!Number.isFinite(raw) || raw < 0)
+        return 0;
+    return Math.trunc(raw);
+}
+function buildDiffShapingGitArgs(shaping) {
+    const args = [];
+    if ((shaping === null || shaping === void 0 ? void 0 : shaping.contextLines) !== undefined) {
+        args.push(`-U${normalizeContextLines(shaping.contextLines)}`);
+    }
+    if (shaping === null || shaping === void 0 ? void 0 : shaping.ignoreWhitespace) {
+        args.push("-w");
+    }
+    return args;
+}
+const PREAMBLE_NOISE_PREFIXES = [
+    "diff --git ",
+    "index ",
+    "new file mode ",
+    "deleted file mode ",
+    "old mode ",
+    "new mode ",
+    "similarity index ",
+    "dissimilarity index ",
+    "rename from ",
+    "rename to ",
+    "copy from ",
+    "copy to ",
+];
+function isPreambleNoiseLine(line) {
+    for (const prefix of PREAMBLE_NOISE_PREFIXES) {
+        if (line.startsWith(prefix))
+            return true;
+    }
+    return false;
+}
+function stripPreambleLines(text) {
+    return text
+        .split(/\r?\n/)
+        .filter((line) => !isPreambleNoiseLine(line))
+        .join("\n");
+}
+function isFileHeaderLine(line) {
+    return (/^--- (a\/|b\/|"a\/|"b\/|\/dev\/null)/.test(line) ||
+        /^\+\+\+ (a\/|b\/|"a\/|"b\/|\/dev\/null)/.test(line));
+}
+function elideLargeHunks(text, maxHunkLines) {
+    const limit = normalizeContextLines(maxHunkLines);
+    const lines = text.split(/\r?\n/);
+    const out = [];
+    let inHunk = false;
+    let hunkBuf = [];
+    const flushHunk = () => {
+        if (hunkBuf.length > limit) {
+            const elided = hunkBuf.length - limit;
+            out.push(...hunkBuf.slice(0, limit));
+            out.push(`[... ${elided} diff line${elided === 1 ? "" : "s"} elided ...]`);
+        }
+        else {
+            out.push(...hunkBuf);
+        }
+        hunkBuf = [];
+        inHunk = false;
+    };
+    for (const line of lines) {
+        if (line.startsWith("@@")) {
+            if (inHunk)
+                flushHunk();
+            out.push(line);
+            inHunk = true;
+            continue;
+        }
+        if (line.startsWith("diff --git ") || isFileHeaderLine(line)) {
+            if (inHunk)
+                flushHunk();
+            out.push(line);
+            continue;
+        }
+        if (inHunk) {
+            hunkBuf.push(line);
+        }
+        else {
+            out.push(line);
+        }
+    }
+    if (inHunk)
+        flushHunk();
+    return out.join("\n");
+}
+function shapeUnifiedDiff(text, shaping) {
+    if (!(shaping === null || shaping === void 0 ? void 0 : shaping.stripDiffPreamble) && (shaping === null || shaping === void 0 ? void 0 : shaping.maxHunkLines) === undefined) {
+        return text;
+    }
+    let out = text;
+    if (shaping.stripDiffPreamble) {
+        out = stripPreambleLines(out);
+    }
+    if (shaping.maxHunkLines !== undefined) {
+        out = elideLargeHunks(out, shaping.maxHunkLines);
+    }
+    return out;
+}
+
 const GIT_STATUS_BY_FIRST_CHAR = {
     A: "added",
     D: "deleted",
@@ -378,25 +646,17 @@ function mergeStatus(existing, next) {
 }
 
 function parseNameStatusLine(line) {
-    var _a;
     const parts = line.split("\t");
     let entry = null;
     if (parts.length >= 2) {
-        const statusToken = (_a = parts[0]) !== null && _a !== void 0 ? _a : "";
+        const statusToken = parts[0];
         const status = mapGitStatus(statusToken);
         const isRenameOrCopy = statusToken.startsWith("R") || statusToken.startsWith("C");
         if (isRenameOrCopy && parts.length >= 3) {
-            const oldPath = parts[1];
-            const newPath = parts[2];
-            if (oldPath !== undefined && newPath !== undefined) {
-                entry = { path: newPath, status, oldPath };
-            }
+            entry = { path: parts[2], status, oldPath: parts[1] };
         }
         else if (!isRenameOrCopy) {
-            const pathOnly = parts[1];
-            if (pathOnly !== undefined) {
-                entry = { path: pathOnly, status };
-            }
+            entry = { path: parts[1], status };
         }
     }
     return entry;
@@ -441,12 +701,11 @@ function numStatPathToLookupKey(pathField) {
     return `${dirRaw}${toSeg}`;
 }
 function parseNumStatLine(line) {
-    var _a, _b;
     const parts = line.split("\t");
     if (parts.length < 3)
         return null;
-    const addStr = (_a = parts[0]) !== null && _a !== void 0 ? _a : "";
-    const delStr = (_b = parts[1]) !== null && _b !== void 0 ? _b : "";
+    const addStr = parts[0];
+    const delStr = parts[1];
     const pathField = parts.slice(2).join("\t");
     const additions = addStr !== "-" ? Number.parseInt(addStr, 10) || 0 : 0;
     const deletions = delStr !== "-" ? Number.parseInt(delStr, 10) || 0 : 0;
@@ -471,11 +730,10 @@ function accumulateNumStat(numStatOutput, into) {
 }
 
 function parseTabDiffSummaryLine(line) {
-    var _a;
     const parts = line.split("\t");
     if (parts.length < 3)
         return null;
-    const statusToken = (_a = parts.shift()) !== null && _a !== void 0 ? _a : "";
+    const statusToken = parts.shift();
     const status = mapGitStatus(statusToken);
     const add0 = parts[0];
     const del0 = parts[1];
@@ -593,31 +851,48 @@ function getDiffPathContext(git, pathFilter, repoRootOverride) {
 }
 function getDiff(git, query) {
     return __awaiter(this, void 0, void 0, function* () {
-        const { from, to, commits, filterByCommits, pathFilter, repoRootOverride } = query;
+        const { from, to, commits, filterByCommits, pathFilter, repoRootOverride, shaping, } = query;
         const { specs } = yield getDiffPathContext(git, pathFilter, repoRootOverride);
+        const shapingArgs = buildDiffShapingGitArgs(shaping);
         if (!filterByCommits) {
-            return git.diff([`${from}..${to}`, "--", ...specs]);
+            const raw = yield git.diff([
+                ...shapingArgs,
+                `${from}..${to}`,
+                "--",
+                ...specs,
+            ]);
+            return shapeUnifiedDiff(raw, shaping);
         }
-        const patches = yield Promise.all(commits.map((c) => git.diff([`${c.hash}^!`, "--", ...specs])));
-        return patches.filter(Boolean).join("\n");
+        const patches = yield Promise.all(commits.map((c) => git.diff([...shapingArgs, `${c.hash}^!`, "--", ...specs])));
+        return patches
+            .map((p) => shapeUnifiedDiff(p, shaping))
+            .filter(Boolean)
+            .join("\n");
     });
 }
 function getDiffSummary(git, query) {
     return __awaiter(this, void 0, void 0, function* () {
-        const { from, to, commits, filterByCommits, pathFilter, repoRootOverride } = query;
+        const { from, to, commits, filterByCommits, pathFilter, repoRootOverride, shaping, } = query;
         const { specs } = yield getDiffPathContext(git, pathFilter, repoRootOverride);
+        const whitespaceArgs = (shaping === null || shaping === void 0 ? void 0 : shaping.ignoreWhitespace) ? ["-w"] : [];
         if (!filterByCommits) {
             const [numOutput, nameOutput] = yield Promise.all([
-                git.diff(["--numstat", `${from}..${to}`, "--", ...specs]),
-                git.diff(["--name-status", `${from}..${to}`, "--", ...specs]),
+                git.diff([...whitespaceArgs, "--numstat", `${from}..${to}`, "--", ...specs]),
+                git.diff([
+                    ...whitespaceArgs,
+                    "--name-status",
+                    `${from}..${to}`,
+                    "--",
+                    ...specs,
+                ]),
             ]);
             return buildDiffSummaryFromGitOutputs(nameOutput, numOutput);
         }
         const pairs = yield Promise.all(commits.map((c) => __awaiter(this, void 0, void 0, function* () {
             const range = `${c.hash}^!`;
             const [numOutput, nameOutput] = yield Promise.all([
-                git.diff(["--numstat", range, "--", ...specs]),
-                git.diff(["--name-status", range, "--", ...specs]),
+                git.diff([...whitespaceArgs, "--numstat", range, "--", ...specs]),
+                git.diff([...whitespaceArgs, "--name-status", range, "--", ...specs]),
             ]);
             return { numOutput, nameOutput };
         })));
@@ -667,6 +942,37 @@ function getChangedFiles(git, query) {
     });
 }
 
+function buildShapingFromOptions(options) {
+    const shaping = {};
+    if (options.contextLines !== undefined) {
+        shaping.contextLines = options.contextLines;
+    }
+    if (options.ignoreWhitespace)
+        shaping.ignoreWhitespace = true;
+    if (options.stripDiffPreamble)
+        shaping.stripDiffPreamble = true;
+    if (options.maxHunkLines !== undefined) {
+        shaping.maxHunkLines = options.maxHunkLines;
+    }
+    return Object.keys(shaping).length > 0 ? shaping : undefined;
+}
+function buildEffectiveExcludeFolders(options) {
+    var _a;
+    const userExcludes = (_a = options.excludeFolders) !== null && _a !== void 0 ? _a : [];
+    if (!options.excludeDefaultNoise) {
+        return userExcludes.length > 0 ? userExcludes : undefined;
+    }
+    const seen = new Set();
+    const merged = [];
+    for (const p of [...DEFAULT_NOISE_EXCLUDES, ...userExcludes]) {
+        const key = p.trim();
+        if (!key || seen.has(key))
+            continue;
+        seen.add(key);
+        merged.push(p);
+    }
+    return merged;
+}
 function hasNonEmptyTrimmed(arr) {
     return (arr !== null && arr !== void 0 ? arr : []).some((s) => s.trim().length > 0);
 }
@@ -683,22 +989,25 @@ function summarizeGitDiff(options) {
         const git = (_a = options.git) !== null && _a !== void 0 ? _a : createGitClient(options.cwd);
         const from = options.from;
         const to = (_b = options.to) !== null && _b !== void 0 ? _b : "HEAD";
+        const effectiveExcludeFolders = buildEffectiveExcludeFolders(options);
         const pathFilter = hasNonEmptyTrimmed(options.includeFolders) ||
-            hasNonEmptyTrimmed(options.excludeFolders)
+            hasNonEmptyTrimmed(effectiveExcludeFolders)
             ? {
                 includeFolders: options.includeFolders,
-                excludeFolders: options.excludeFolders,
+                excludeFolders: effectiveExcludeFolders,
             }
             : undefined;
         const allCommits = yield getCommits(git, from, to);
         const filteredCommits = filterCommitsByMessageRegexes(allCommits, options.commitMessageIncludeRegexes, options.commitMessageExcludeRegexes);
         const filterByCommits = shouldFilterByCommits(allCommits, filteredCommits, options);
+        const shaping = buildShapingFromOptions(options);
         const rangeQuery = {
             from,
             to,
             commits: filteredCommits,
             filterByCommits,
             pathFilter,
+            shaping,
         };
         const [diffText, fileNames, diffSummary] = yield Promise.all([
             getDiff(git, rangeQuery),
@@ -710,6 +1019,7 @@ function summarizeGitDiff(options) {
             to,
             team: options.teamName,
             model: options.model,
+            provider: options.provider,
             maxDiffChars: options.maxDiffChars,
             systemPrompt: options.systemPrompt,
             commitMessageIncludeRegexes: options.commitMessageIncludeRegexes,
@@ -720,11 +1030,11 @@ function summarizeGitDiff(options) {
             fileNames,
             commits: filteredCommits,
             flags: summarizeFlags,
-            openAiClientProvider: options.openAiClientProvider,
+            llmModelProvider: options.llmModelProvider,
             diffSummary,
         });
     });
 }
 
-export { DEFAULT_GIT_DIFF_SYSTEM_PROMPT, LLM_GATEWAY_REQUIRED_MESSAGE, buildDiffPathspecs, createGitClient, createOpenAiLikeClient, filterCommitsByMessageRegexes, generateSummary, getChangedFiles, getCommits, getDiff, getDiffSummary, getRepoRoot, parseLlmDefaultHeadersFromEnv, resolveLlmBaseUrl, resolveLlmMaxDiffChars, resolveOpenAiLikeClientInit, shouldUseLlmGateway, splitPromotableAuthorizationFromHeaders, summarizeGitDiff, truncateUnifiedDiffForLlm };
+export { DEFAULT_GIT_DIFF_SYSTEM_PROMPT, DEFAULT_NOISE_EXCLUDES, LLM_GATEWAY_REQUIRED_MESSAGE, buildDiffPathspecs, buildDiffShapingGitArgs, createGitClient, defaultModelForProvider, detectLlmProvider, filterCommitsByMessageRegexes, generateSummary, getChangedFiles, getCommits, getDiff, getDiffSummary, getRepoRoot, isLlmProviderConfigured, parseLlmDefaultHeadersFromEnv, resolveLanguageModel, resolveLlmBaseUrl, resolveLlmMaxDiffChars, shapeUnifiedDiff, summarizeGitDiff, truncateUnifiedDiffForLlm };
 //# sourceMappingURL=index.mjs.map