@f5xc-salesdemos/xcsh 2.2.0 → 14.0.2

package/src/commit/pipeline.ts

@@ -0,0 +1,242 @@
+import * as path from "node:path";
+import type { ThinkingLevel } from "@f5xc-salesdemos/pi-agent-core";
+import type { Api, Model } from "@f5xc-salesdemos/pi-ai";
+import { getProjectDir, logger, prompt } from "@f5xc-salesdemos/pi-utils";
+import { ModelRegistry } from "../config/model-registry";
+import { Settings } from "../config/settings";
+import { discoverAuthStorage } from "../sdk";
+import { loadProjectContextFiles } from "../system-prompt";
+import * as git from "../utils/git";
+import { runAgenticCommit } from "./agentic";
+import {
+	extractScopeCandidates,
+	generateConventionalAnalysis,
+	generateSummary,
+	validateAnalysis,
+	validateSummary,
+} from "./analysis";
+import { runChangelogFlow } from "./changelog";
+import { runMapReduceAnalysis, shouldUseMapReduce } from "./map-reduce";
+import { formatCommitMessage } from "./message";
+import { resolvePrimaryModel, resolveSmolModel } from "./model-selection";
+import summaryRetryPrompt from "./prompts/summary-retry.md" with { type: "text" };
+import typesDescriptionPrompt from "./prompts/types-description.md" with { type: "text" };
+import type { CommitCommandArgs, ConventionalAnalysis } from "./types";
+
+const SUMMARY_MAX_CHARS = 72;
+const RECENT_COMMITS_COUNT = 8;
+const TYPES_DESCRIPTION = prompt.render(typesDescriptionPrompt);
+
+/**
+ * Execute the xcsh commit pipeline for staged changes.
+ */
+export async function runCommitCommand(args: CommitCommandArgs): Promise<void> {
+	if (args.legacy) {
+		return runLegacyCommitCommand(args);
+	}
+	return runAgenticCommit(args);
+}
+
+async function runLegacyCommitCommand(args: CommitCommandArgs): Promise<void> {
+	const cwd = getProjectDir();
+	const settings = await Settings.init();
+	const commitSettings = settings.getGroup("commit");
+	const authStorage = await discoverAuthStorage();
+	const modelRegistry = new ModelRegistry(authStorage);
+	await modelRegistry.refresh();
+
+	const {
+		model: primaryModel,
+		apiKey: primaryApiKey,
+		thinkingLevel: primaryThinkingLevel,
+	} = await resolvePrimaryModel(args.model, settings, modelRegistry);
+	const {
+		model: smolModel,
+		apiKey: smolApiKey,
+		thinkingLevel: smolThinkingLevel,
+	} = await resolveSmolModel(settings, modelRegistry, primaryModel, primaryApiKey);
+
+	let stagedFiles = await git.diff.changedFiles(cwd, { cached: true });
+	if (stagedFiles.length === 0) {
+		process.stdout.write("No staged changes detected, staging all changes...\n");
+		await git.stage.files(cwd);
+		stagedFiles = await git.diff.changedFiles(cwd, { cached: true });
+	}
+	if (stagedFiles.length === 0) {
+		process.stderr.write("No changes to commit.\n");
+		return;
+	}
+
+	if (!args.noChangelog) {
+		await runChangelogFlow({
+			cwd,
+			model: primaryModel,
+			apiKey: primaryApiKey,
+			thinkingLevel: primaryThinkingLevel,
+			stagedFiles,
+			dryRun: args.dryRun,
+			maxDiffChars: commitSettings.changelogMaxDiffChars,
+		});
+	}
+
+	const diff = await git.diff(cwd, { cached: true });
+	const stat = await git.diff(cwd, { stat: true, cached: true });
+	const numstat = await git.diff.numstat(cwd, { cached: true });
+	const scopeCandidates = extractScopeCandidates(numstat).scopeCandidates;
+	const recentCommits = await git.log.subjects(cwd, RECENT_COMMITS_COUNT);
+	const contextFiles = await loadProjectContextFiles({ cwd });
+	const formattedContextFiles = contextFiles.map(file => ({
+		path: path.relative(cwd, file.path),
+		content: file.content,
+	}));
+
+	const analysis = await generateAnalysis({
+		diff,
+		stat,
+		scopeCandidates,
+		recentCommits,
+		contextFiles: formattedContextFiles,
+		userContext: args.context,
+		primaryModel,
+		primaryApiKey,
+		primaryThinkingLevel,
+		smolModel,
+		smolApiKey,
+		smolThinkingLevel,
+		commitSettings,
+	});
+
+	const analysisValidation = validateAnalysis(analysis);
+	if (!analysisValidation.valid) {
+		logger.warn("commit analysis validation failed", { errors: analysisValidation.errors });
+	}
+
+	const summary = await generateSummaryWithRetry({
+		analysis,
+		stat,
+		model: primaryModel,
+		apiKey: primaryApiKey,
+		thinkingLevel: primaryThinkingLevel,
+		userContext: args.context,
+	});
+
+	const commitMessage = formatCommitMessage(analysis, summary.summary);
+
+	if (args.dryRun) {
+		process.stdout.write("\nGenerated commit message:\n");
+		process.stdout.write(`${commitMessage}\n`);
+		return;
+	}
+
+	await git.commit(cwd, commitMessage);
+	process.stdout.write("Commit created.\n");
+	if (args.push) {
+		await git.push(cwd);
+		process.stdout.write("Pushed to remote.\n");
+	}
+}
+
+async function generateAnalysis(input: {
+	diff: string;
+	stat: string;
+	scopeCandidates: string;
+	recentCommits: string[];
+	contextFiles: Array<{ path: string; content: string }>;
+	userContext?: string;
+	primaryModel: Model<Api>;
+	primaryApiKey: string;
+	primaryThinkingLevel?: ThinkingLevel;
+	smolModel: Model<Api>;
+	smolApiKey: string;
+	smolThinkingLevel?: ThinkingLevel;
+	commitSettings: {
+		mapReduceEnabled: boolean;
+		mapReduceMinFiles: number;
+		mapReduceMaxFileTokens: number;
+		mapReduceTimeoutMs: number;
+		mapReduceMaxConcurrency: number;
+		changelogMaxDiffChars: number;
+	};
+}): Promise<ConventionalAnalysis> {
+	if (
+		shouldUseMapReduce(input.diff, {
+			enabled: input.commitSettings.mapReduceEnabled,
+			minFiles: input.commitSettings.mapReduceMinFiles,
+			maxFileTokens: input.commitSettings.mapReduceMaxFileTokens,
+		})
+	) {
+		process.stdout.write("Large diff detected, using map-reduce analysis...\n");
+		return runMapReduceAnalysis({
+			model: input.primaryModel,
+			apiKey: input.primaryApiKey,
+			thinkingLevel: input.primaryThinkingLevel,
+			smolModel: input.smolModel,
+			smolApiKey: input.smolApiKey,
+			smolThinkingLevel: input.smolThinkingLevel,
+			diff: input.diff,
+			stat: input.stat,
+			scopeCandidates: input.scopeCandidates,
+			typesDescription: TYPES_DESCRIPTION,
+			settings: {
+				enabled: input.commitSettings.mapReduceEnabled,
+				minFiles: input.commitSettings.mapReduceMinFiles,
+				maxFileTokens: input.commitSettings.mapReduceMaxFileTokens,
+				maxConcurrency: input.commitSettings.mapReduceMaxConcurrency,
+				timeoutMs: input.commitSettings.mapReduceTimeoutMs,
+			},
+		});
+	}
+
+	return generateConventionalAnalysis({
+		model: input.primaryModel,
+		apiKey: input.primaryApiKey,
+		thinkingLevel: input.primaryThinkingLevel,
+		contextFiles: input.contextFiles,
+		userContext: input.userContext,
+		typesDescription: TYPES_DESCRIPTION,
+		recentCommits: input.recentCommits,
+		scopeCandidates: input.scopeCandidates,
+		stat: input.stat,
+		diff: input.diff,
+	});
+}
+
+async function generateSummaryWithRetry(input: {
+	analysis: ConventionalAnalysis;
+	stat: string;
+	model: Model<Api>;
+	apiKey: string;
+	thinkingLevel?: ThinkingLevel;
+	userContext?: string;
+}): Promise<{ summary: string }> {
+	let context = input.userContext;
+	for (let attempt = 0; attempt < 3; attempt += 1) {
+		const result = await generateSummary({
+			model: input.model,
+			apiKey: input.apiKey,
+			thinkingLevel: input.thinkingLevel,
+			commitType: input.analysis.type,
+			scope: input.analysis.scope,
+			details: input.analysis.details.map(detail => detail.text),
+			stat: input.stat,
+			maxChars: SUMMARY_MAX_CHARS,
+			userContext: context,
+		});
+		const validation = validateSummary(result.summary, SUMMARY_MAX_CHARS);
+		if (validation.valid) {
+			return result;
+		}
+		if (attempt === 2) {
+			return result;
+		}
+		context = buildRetryContext(input.userContext, validation.errors);
+	}
+	throw new Error("Summary generation failed");
+}
+
+function buildRetryContext(base: string | undefined, errors: string[]): string {
+	return prompt.render(summaryRetryPrompt, {
+		base_context: base,
+		errors: errors.join("; "),
+	});
+}

package/src/commit/prompts/analysis-system.md

@@ -0,0 +1,148 @@
+<context>
+Senior release engineer writing precise, changelog-ready commit classifications.
+</context>
+
+<instructions>
+Classify git diff into conventional commit format.
+## 1. Determine Scope
+
+Apply scope when 60%+ line changes target single component:
+- 150 lines in src/api/, 30 in src/lib.rs → "api"
+- 50 lines in src/api/, 50 in src/types/ → null (50/50 split)
+
+Use null for: cross-cutting changes, project-wide refactoring.
+
+Forbidden scopes (use null): src, lib, include, tests, benches, examples, docs, project name, app, main, entire, all, misc.
+
+Prefer scopes from <common-scopes> over inventing new.
+## 2. Generate Details (0-6 items)
+
+Each detail:
+1. Past-tense verb, ends with period
+2. Explains impact/rationale (skip trivial what-changed)
+3. Uses precise names (modules, APIs, files)
+4. Under 120 characters
+
+Abstraction preference:
+- BEST: "Replaced polling with event-driven model for 10x throughput."
+- GOOD: "Consolidated three HTTP builders into unified API."
+- SKIP: "Renamed workspacePath to locate."
+
+Group 3+ similar changes: "Updated 5 test files for new API." (not five bullets).
+
+Issue references inline: (#123), (#123, #456), (#123-#125).
+
+Priority: user-visible → perf/security → architecture → internal.
+
+Exclude: import changes, whitespace, formatting, trivial renames, debug prints, comment-only, file moves without modification.
+
+State only visible rationale. If unclear, use neutral: "Updated logic for correctness."
+## 3. Assign Changelog Metadata
+
+|Condition|changelog_category|
+|---|---|
+|New public API, feature, capability|"Added"|
+|Modified existing behavior|"Changed"|
+|Bug fix, correction|"Fixed"|
+|Feature marked for removal|"Deprecated"|
+|Feature/API removed|"Removed"|
+|Security fix or improvement|"Security"|
+
+user_visible: true for: new features, APIs, breaking changes, user-affecting bug fixes, user-facing docs, security fixes.
+
+user_visible: false for: internal refactoring, performance optimizations (unless documented), test/build/CI, code style.
+
+Omit changelog_category when user_visible false.
+</instructions>
+
+<output-format>
+Call create_conventional_analysis with:
+
+{
+"type": "feat|fix|refactor|docs|test|chore|style|perf|build|ci|revert",
+"scope": "component-name" | null,
+"details": [
+{
+"text": "Past-tense description ending with period.",
+"changelog_category": "Added|Changed|Fixed|Deprecated|Removed|Security",
+"user_visible": true
+},
+{
+"text": "Internal change description.",
+"user_visible": false
+}
+],
+"issue_refs": []
+}
+</output-format>
+
+<example name="feature-with-api">
+{
+  "type": "feat",
+  "scope": "api",
+  "details": [
+    {
+      "text": "Added TLS mutual authentication to prevent man-in-the-middle attacks (#100).",
+      "changelog_category": "Added",
+      "user_visible": true
+    },
+    {
+      "text": "Implemented builder pattern to simplify transport configuration (#101).",
+      "changelog_category": "Added",
+      "user_visible": true
+    },
+    {
+      "text": "Migrated 6 integration tests to exercise new security features.",
+      "user_visible": false
+    }
+  ],
+  "issue_refs": []
+}
+</example>
+
+<example name="internal-refactor">
+{
+  "type": "refactor",
+  "scope": "parser",
+  "details": [
+    {
+      "text": "Extracted validation logic into separate module for reusability.",
+      "user_visible": false
+    },
+    {
+      "text": "Consolidated error handling across 12 functions to reduce duplication.",
+      "user_visible": false
+    }
+  ],
+  "issue_refs": []
+}
+</example>
+
+<example name="bug-fix">
+{
+  "type": "fix",
+  "scope": "parser",
+  "details": [
+    {
+      "text": "Corrected off-by-one error causing buffer overflow on large inputs (#456).",
+      "changelog_category": "Fixed",
+      "user_visible": true
+    },
+    {
+      "text": "Added bounds checking to prevent panic on empty files (#457).",
+      "changelog_category": "Fixed",
+      "user_visible": true
+    }
+  ],
+  "issue_refs": []
+}
+</example>
+
+<example name="minimal-chore">
+{
+  "type": "chore",
+  "scope": "deps",
+  "details": [],
+  "issue_refs": []
+}
+</example>

package/src/commit/prompts/analysis-user.md

@@ -0,0 +1,38 @@
+{{#if context_files}}
+<project-context>
+{{#each context_files}}
+<file path="{{ path }}">
+{{ content }}
+</file>
+{{/each}}
+</project-context>
+{{/if}}
+{{#if user_context}}
+<user-context>
+{{ user_context }}
+</user-context>
+{{/if}}
+{{#if types_description}}
+<commit-types>
+{{ types_description }}
+</commit-types>
+{{/if}}
+<diff-statistics>
+{{ stat }}
+</diff-statistics>
+<scope-candidates>
+{{ scope_candidates }}
+</scope-candidates>
+{{#if common_scopes}}
+<common-scopes>
+{{ common_scopes }}
+</common-scopes>
+{{/if}}
+{{#if recent_commits}}
+<style-patterns>
+{{ recent_commits }}
+</style-patterns>
+{{/if}}
+<diff>
+{{ diff }}
+</diff>

package/src/commit/prompts/changelog-system.md

@@ -0,0 +1,50 @@
+You're expert changelog writer analyzing git diffs to produce Keep a Changelog entries.
+
+<instructions>
+1. Identify only user-visible changes
+2. Categorize each change (use categories below)
+3. Omit categories with no entries
+</instructions>
+
+<categories>
+- Added: New features, public APIs, user-facing capabilities
+- Changed: Modified behavior
+- Deprecated: Features scheduled for removal
+- Removed: Deleted features or APIs
+- Fixed: Bug fixes with observable impact
+- Security: Vulnerability fixes
+- Breaking Changes: API-incompatible changes (use sparingly)
+</categories>
+
+<entry-format>
+- Start with past-tense verb (Added, Fixed, Implemented, Updated)
+- Describe user-visible impact, not implementation
+- Name specific feature, option, or behavior
+- Keep 1-2 lines, no trailing periods
+</entry-format>
+
+<examples>
+Good:
+- Added --dry-run flag to preview changes without applying them
+- Fixed memory leak when processing large files
+- Changed default timeout from 30s to 60s for slow connections
+
+Bad:
+- **cli**: Added dry-run flag → redundant scope prefix
+- Added new feature. → vague, trailing period
+- Refactored parser internals → not user-visible
+
+Breaking Changes:
+- Removed legacy auth flow; users must re-authenticate with OAuth tokens
+</examples>
+
+<exclude>
+Internal refactoring, code style changes, test-only modifications, minor doc updates.
+</exclude>
+
+<output-format>
+Return ONLY valid JSON; no markdown fences or explanation.
+
+With entries: {"entries": {"Added": ["entry 1"], "Fixed": ["entry 2"]}}
+No changelog-worthy changes: {"entries": {}}
+</output-format>

package/src/commit/prompts/changelog-user.md

@@ -0,0 +1,18 @@
+<context>
+Changelog: {{ changelog_path }}
+{{#if is_package_changelog}}Scope: Package-level changelog. Omit package name prefix from entries.{{/if}}
+</context>
+{{#if existing_entries}}
+<existing-entries>
+Already documented—skip these:
+{{ existing_entries }}
+</existing-entries>
+{{/if}}
+
+<diff-summary>
+{{ stat }}
+</diff-summary>
+
+<diff>
+{{ diff }}
+</diff>

package/src/commit/prompts/file-observer-system.md

@@ -0,0 +1,24 @@
+<role>Expert code analyst extracting structured observations from diffs.</role>
+
+<instructions>
+Extract factual observations from diff. This matters—be precise.
+1. Use past-tense verb + specific target + optional purpose
+2. Max 100 characters per observation
+3. Consolidate related changes (e.g., "renamed 5 helper functions")
+4. Return 1-5 observations only
+</instructions>
+
+<scope>
+Include: functions, methods, types, API changes, behavior/logic changes, error handling, performance, security.
+
+Exclude: import reordering, whitespace/formatting, comment-only changes, debug statements.
+</scope>
+
+<output-format>
+Plain list, no preamble, no summary, no markdown formatting.
+- added 'parse_config()' function for TOML configuration loading
+- removed deprecated 'legacy_init()' and all callers
+- changed 'Connection::new()' to accept '&Config' instead of individual params
+</output-format>
+
+Observations only. Classification in reduce phase.

package/src/commit/prompts/file-observer-user.md

@@ -0,0 +1,8 @@
+<file path="{{ filename }}">
+{{ diff }}
+</file>
+{{#if context_header}}
+<related-files>
+{{ context_header }}
+</related-files>
+{{/if}}

package/src/commit/prompts/reduce-system.md

@@ -0,0 +1,50 @@
+Senior engineer synthesizing file-level observations into conventional commit analysis.
+<context>
+Given map-phase observations, produce unified commit classification with changelog metadata.
+</context>
+<instructions>
+Determine:
+1. TYPE: Single classification
+2. SCOPE: Primary component
+3. DETAILS: 3–4 summary points (max 6)
+4. CHANGELOG: Metadata for user-visible changes
+</instructions>
+<scope-rules>
+- Component name if ≥60% changes target it
+- null if spread across multiple components
+- scope_candidates as primary source
+- Valid: specific component names (api, parser, config, etc.)
+</scope-rules>
+<output-format>
+Each detail point:
+- Start with past-tense verb (added, fixed, moved, extracted)
+- Under 120 chars, ends with period
+- Group related cross-file changes
+Priority: user-visible behavior > performance/security > architecture > internal implementation
+changelog_category: Added|Changed|Fixed|Deprecated|Removed|Security
+user_visible: true for features, user-facing bugs, breaking changes, security
+</output-format>
+<example>
+Input observations:
+- api/client.ts: added token refresh guard to prevent duplicate refreshes
+- api/http.ts: introduced retry wrapper for 429 responses
+- api/index.ts: updated exports for retry helper
+Output:
+{
+"type": "fix",
+"scope": "api",
+"details": [
+{
+"text": "Added token refresh guard to prevent duplicate refreshes.",
+"changelog_category": "Fixed",
+"user_visible": true
+},
+{
+"text": "Introduced retry wrapper for 429 responses.",
+"changelog_category": "Fixed",
+"user_visible": true
+}
+],
+"issue_refs": []
+}
+</example>

package/src/commit/prompts/reduce-user.md

@@ -0,0 +1,17 @@
+{{#if types_description}}
+<type-definitions>
+{{ types_description }}
+</type-definitions>
+{{/if}}
+
+<observations>
+{{ observations }}
+</observations>
+
+<diff-statistics>
+{{ stat }}
+</diff-statistics>
+
+<scope-candidates>
+{{ scope_candidates }}
+</scope-candidates>

package/src/commit/prompts/summary-retry.md

@@ -0,0 +1,3 @@
+{{#if base_context}}
+{{ base_context }}
+{{/if}}Previous summary failed validation: {{ errors }}

package/src/commit/prompts/summary-system.md

@@ -0,0 +1,38 @@
+You are commit message specialist generating precise, informative descriptions.
+<context>
+Output: ONLY description after "{{ commit_type }}{{ scope_prefix }}:"; max {{ chars }} chars; no trailing period; no type prefix.
+</context>
+
+<instructions>
+1. Start with lowercase past-tense verb (not "{{ commit_type }}")
+2. Name specific subsystem/component affected
+3. Include WHY when clarifies intent
+4. One focused concept per message
+</instructions>
+
+<verb-reference>
+|Type|Use|
+|---|---|
+|feat|added, introduced, implemented, enabled|
+|fix|corrected, resolved, patched, addressed|
+|refactor|restructured, reorganized, migrated, simplified|
+|perf|optimized, reduced, eliminated, accelerated|
+|docs|documented, clarified, expanded|
+|build|upgraded, pinned, configured|
+|chore|cleaned, removed, renamed, organized|
+</verb-reference>
+<examples>
+feat | TLS encryption added to HTTP client for MITM prevention
+→ added TLS support to prevent man-in-the-middle attacks
+refactor | Consolidated HTTP transport into unified builder pattern
+→ migrated HTTP transport to unified builder API
+fix | Race condition in connection pool causing exhaustion under load
+→ corrected race condition causing connection pool exhaustion
+perf | Batch processing optimized to reduce memory allocations
+→ eliminated allocation overhead in batch processing
+build | Updated serde to fix CVE-2024-1234
+→ upgraded serde to 1.0.200 for CVE-2024-1234
+</examples>
+<banned-words>
+comprehensive, various, several, improved, enhanced, quickly, simply, basically, this change, this commit, now
+</banned-words>

package/src/commit/prompts/summary-user.md

@@ -0,0 +1,13 @@
+{{#if user_context}}
+<user-context>
+{{ user_context }}
+</user-context>
+{{/if}}
+
+<detail-points>
+{{ details }}
+</detail-points>
+
+<diff-stat>
+{{ stat }}
+</diff-stat>

package/src/commit/prompts/types-description.md

@@ -0,0 +1,2 @@
+Types: feat, fix, refactor, perf, docs, test, build, ci, chore, style, revert.
+Format: <type>(<scope>): <summary> with past-tense summary.