boocode/apps/server/src/services/tools.ts

import { readFile, readdir, stat } from 'node:fs/promises';
import { resolve, basename, relative } from 'node:path';
import { z } from 'zod';
import { pathGuard, PathScopeError } from './path_guard.js';
import { isSecretPath, SecretBlockedError, filterSecretEntries } from './secret_guard.js';
import { grep as fileOpsGrep, findFiles as fileOpsFindFiles } from './file_ops.js';
import { getGitMeta } from './git_meta.js';
import { findSkills, getSkillBody, getSkillResource } from './skills.js';
import { webSearch } from './web_search.js';
import { webFetch } from './web_fetch.js';
// v1.12 Track B.2: codecontext tools. 8 wrappers re-exported from
// tools/codecontext/index.ts. Each calls into services/codecontext_client.ts
// which talks to the codecontext sidecar at http://codecontext:8080.
import {
  getCodebaseOverview,
  getFileAnalysis,
  getSymbolInfo,
  searchSymbols,
  getDependencies,
  watchChanges,
  getSemanticNeighborhoods,
  getFrameworkAnalysis,
} from './tools/codecontext/index.js';

const MAX_FILE_BYTES = 5 * 1024 * 1024;
const DEFAULT_VIEW_LINES = 200;
const MAX_GREP_RESULTS = 200;
const DEFAULT_GREP_RESULTS = 100;
const MAX_FIND_RESULTS = 200;
const DEFAULT_FIND_RESULTS = 100;
const MAX_DIR_ENTRIES = 500;

export interface ToolJsonSchema {
  type: 'function';
  function: {
    name: string;
    description: string;
    parameters: Record<string, unknown>;
  };
}

export interface ToolDef<TInput> {
  name: string;
  description: string;
  inputSchema: z.ZodType<TInput>;
  jsonSchema: ToolJsonSchema;
  execute(input: TInput, projectRoot: string): Promise<unknown>;
}

const ViewFileInput = z.object({
  path: z.string().min(1),
  start_line: z.number().int().positive().optional(),
  end_line: z.number().int().positive().optional(),
});
type ViewFileInputT = z.infer<typeof ViewFileInput>;

export const viewFile: ToolDef<ViewFileInputT> = {
  name: 'view_file',
  description:
    "Read a file under the project. Returns first 200 lines by default, or a slice via start_line/end_line (1-indexed, inclusive). Files larger than 5MB are refused. Output is truncated if longer than the slice; the response indicates truncation.",
  inputSchema: ViewFileInput,
  jsonSchema: {
    type: 'function',
    function: {
      name: 'view_file',
      description:
        "Read a file under the project. Returns first 200 lines by default, or a slice via start_line/end_line (1-indexed, inclusive). Files larger than 5MB are refused.",
      parameters: {
        type: 'object',
        properties: {
          path: { type: 'string', description: 'absolute or project-relative path' },
          start_line: { type: 'integer', description: 'first line (1-indexed)' },
          end_line: { type: 'integer', description: 'last line (1-indexed, inclusive)' },
        },
        required: ['path'],
        additionalProperties: false,
      },
    },
  },
  async execute(input, projectRoot) {
    const real = await pathGuard(projectRoot, input.path);
    // v1.11.7: secret-file deny check. Test the project-relative path
    // (matches the form continue.dev's patterns expect: basenames + dir
    // segments). Throw a typed error so executeToolCall in inference.ts
    // surfaces a clear "blocked" message to the LLM instead of silently
    // returning content the user wanted hidden.
    const relPath = relative(projectRoot, real) || basename(real);
    if (isSecretPath(relPath)) {
      throw new SecretBlockedError(relPath);
    }
    const s = await stat(real);
    if (!s.isFile()) {
      throw new PathScopeError(`not a file: ${input.path}`);
    }
    if (s.size > MAX_FILE_BYTES) {
      throw new Error(`file too large (${s.size} bytes, max ${MAX_FILE_BYTES})`);
    }
    const raw = await readFile(real, 'utf8');
    const lines = raw.split('\n');
    const total = lines.length;
    let start = input.start_line ?? 1;
    let end = input.end_line ?? Math.min(total, start + DEFAULT_VIEW_LINES - 1);
    if (input.start_line == null && input.end_line == null) {
      end = Math.min(total, DEFAULT_VIEW_LINES);
    }
    if (start < 1) start = 1;
    if (end > total) end = total;
    if (end < start) end = start;
    const slice = lines.slice(start - 1, end);
    const content = slice.join('\n');
    const truncated = total > end || start > 1;
    return {
      path: relative(projectRoot, real) || basename(real),
      content,
      total_lines: total,
      returned_lines: [start, end],
      truncated,
    };
  },
};

const ListDirInput = z.object({
  path: z.string().min(1),
  show_hidden: z.boolean().optional(),
});
type ListDirInputT = z.infer<typeof ListDirInput>;

export const listDir: ToolDef<ListDirInputT> = {
  name: 'list_dir',
  description: 'List entries in a directory (up to 500). Hidden files excluded unless show_hidden=true.',
  inputSchema: ListDirInput,
  jsonSchema: {
    type: 'function',
    function: {
      name: 'list_dir',
      description:
        'List entries in a directory (up to 500). Hidden files (dot-prefixed) excluded unless show_hidden=true.',
      parameters: {
        type: 'object',
        properties: {
          path: { type: 'string' },
          show_hidden: { type: 'boolean' },
        },
        required: ['path'],
        additionalProperties: false,
      },
    },
  },
  async execute(input, projectRoot) {
    const real = await pathGuard(projectRoot, input.path);
    const s = await stat(real);
    if (!s.isDirectory()) {
      throw new PathScopeError(`not a directory: ${input.path}`);
    }
    const entries = await readdir(real, { withFileTypes: true });
    const filtered = input.show_hidden
      ? entries
      : entries.filter((e) => !e.name.startsWith('.'));
    const total = filtered.length;
    const slice = filtered.slice(0, MAX_DIR_ENTRIES);
    const out = await Promise.all(
      slice.map(async (e) => {
        const child = resolve(real, e.name);
        let size: number | undefined;
        if (e.isFile()) {
          try {
            const cs = await stat(child);
            size = cs.size;
          } catch {
            /* ignore */
          }
        }
        return {
          name: e.name,
          type: e.isDirectory() ? ('dir' as const) : ('file' as const),
          ...(size != null ? { size } : {}),
        };
      })
    );
    // v1.11.7: filter entries whose project-relative path matches a secret
    // pattern. Each entry is tested using the project-rel dir + its name
    // so the pattern's path/segment semantics work for nested dirs like
    // `.aws/`. The count is surfaced via `pathguard_note` — we never list
    // the hidden paths (defeats the purpose).
    const relDir = relative(projectRoot, real) || '.';
    const secretFilter = filterSecretEntries(out, (e) =>
      relDir === '.' ? e.name : `${relDir}/${e.name}`,
    );
    return {
      path: relDir,
      entries: secretFilter.kept,
      total: secretFilter.kept.length,
      truncated: total > MAX_DIR_ENTRIES,
      ...(secretFilter.note ? { pathguard_note: secretFilter.note } : {}),
    };
  },
};

const GrepInput = z.object({
  pattern: z.string().min(1),
  path: z.string().optional(),
  case_sensitive: z.boolean().optional(),
  max_results: z.number().int().positive().optional(),
  hidden: z.boolean().optional(),
});
type GrepInputT = z.infer<typeof GrepInput>;

export const grep: ToolDef<GrepInputT> = {
  name: 'grep',
  description:
    'Search file contents with ripgrep. Default path is project root. Max 100 results (200 cap).',
  inputSchema: GrepInput,
  jsonSchema: {
    type: 'function',
    function: {
      name: 'grep',
      description:
        'Search file contents with ripgrep. Returns up to 100 matches (cap 200). Set hidden=true to include dot-prefixed files.',
      parameters: {
        type: 'object',
        properties: {
          pattern: { type: 'string' },
          path: { type: 'string' },
          case_sensitive: { type: 'boolean' },
          max_results: { type: 'integer' },
          hidden: { type: 'boolean' },
        },
        required: ['pattern'],
        additionalProperties: false,
      },
    },
  },
  async execute(input, projectRoot) {
    const limit = Math.min(
      Math.max(input.max_results ?? DEFAULT_GREP_RESULTS, 1),
      MAX_GREP_RESULTS
    );
    // Delegate to file_ops.grep; reshape match objects to preserve LLM output format
    // (file_ops uses {path, line, text}; tool output uses {path, line, content})
    const result = await fileOpsGrep(projectRoot, input.pattern, {
      path: input.path,
      max_matches: limit,
      case_sensitive: input.case_sensitive,
      hidden: input.hidden,
    });
    const reshaped = result.matches.map((m) => ({
      path: m.path,
      line: m.line,
      content: m.text,
    }));
    // v1.11.7: drop matches whose source file is a known-secret pattern.
    // file_ops.grep returns project-relative paths, so we feed them straight
    // into isSecretPath. Multiple matches in the same secret file each get
    // dropped individually — they all count in the hidden tally.
    const secretFilter = filterSecretEntries(reshaped, (m) => m.path);
    return {
      matches: secretFilter.kept,
      total: secretFilter.kept.length,
      truncated: result.truncated,
      ...(secretFilter.note ? { pathguard_note: secretFilter.note } : {}),
    };
  },
};

const FindFilesInput = z.object({
  pattern: z.string().min(1),
  path: z.string().optional(),
  max_results: z.number().int().positive().optional(),
});
type FindFilesInputT = z.infer<typeof FindFilesInput>;

export const findFiles: ToolDef<FindFilesInputT> = {
  name: 'find_files',
  description: 'Glob for filenames. Default path is project root. Max 100 results (200 cap).',
  inputSchema: FindFilesInput,
  jsonSchema: {
    type: 'function',
    function: {
      name: 'find_files',
      description:
        'Glob for filenames under a directory. Default path is project root. Max 100 results (cap 200). Pattern uses standard glob (e.g. "**/*.ts").',
      parameters: {
        type: 'object',
        properties: {
          pattern: { type: 'string' },
          path: { type: 'string' },
          max_results: { type: 'integer' },
        },
        required: ['pattern'],
        additionalProperties: false,
      },
    },
  },
  async execute(input, projectRoot) {
    const limit = Math.min(
      Math.max(input.max_results ?? DEFAULT_FIND_RESULTS, 1),
      MAX_FIND_RESULTS
    );
    // Delegate to file_ops.findFiles; reshape { files, total, truncated } to
    // preserve the LLM-visible output format { paths, total, truncated }
    const result = await fileOpsFindFiles(projectRoot, input.pattern, {
      path: input.path,
      max_results: limit,
    });
    // v1.11.7: drop paths matching secret patterns. The original `total`
    // from file_ops includes pre-truncation count; we report the visible
    // count post-filter so the LLM can't infer hidden-count by subtraction.
    const secretFilter = filterSecretEntries(result.files, (p) => p);
    return {
      paths: secretFilter.kept,
      total: secretFilter.kept.length,
      truncated: result.truncated,
      ...(secretFilter.note ? { pathguard_note: secretFilter.note } : {}),
    };
  },
};

// v1.8 Level 1 branch awareness: gives the model a read-only view of the
// project's git state. No path input — operates on the inference-resolved
// project root via getGitMeta. Subprocess runs with a 2s timeout (see git_meta).
const GitStatusInput = z.object({}).strict();
type GitStatusInputT = z.infer<typeof GitStatusInput>;

export const gitStatus: ToolDef<GitStatusInputT> = {
  name: 'git_status',
  description:
    "Returns the current git branch, whether the working tree is dirty, and ahead/behind counts vs upstream. Read-only. Use when you need to know which branch the user is currently working on.",
  inputSchema: GitStatusInput,
  jsonSchema: {
    type: 'function',
    function: {
      name: 'git_status',
      description:
        'Returns the current git branch, dirty flag, and ahead/behind counts vs upstream. Read-only.',
      parameters: {
        type: 'object',
        properties: {},
        additionalProperties: false,
      },
    },
  },
  async execute(_input, projectRoot) {
    const meta = await getGitMeta(projectRoot);
    if (meta === null) {
      return { repo: false, branch: null, is_dirty: false, ahead: 0, behind: 0 };
    }
    return { repo: true, ...meta };
  },
};

// Batch 9.6: skill_find, skill_use, skill_resource. Lazy-loaded markdown
// playbooks at /data/skills/. Three tools rather than one to keep each call
// cheap — the model lists, then loads, then optionally pulls support files.

const SkillFindInput = z.object({
  query: z.string().optional(),
});
type SkillFindInputT = z.infer<typeof SkillFindInput>;

export const skillFind: ToolDef<SkillFindInputT> = {
  name: 'skill_find',
  description:
    'Find skills (markdown playbooks under /data/skills) by name or description. Returns up to 5 matches. Empty query or "*" returns all available skills. Call this first to discover what skills are available.',
  inputSchema: SkillFindInput,
  jsonSchema: {
    type: 'function',
    function: {
      name: 'skill_find',
      description:
        'Find skills by name or description. Returns up to 5 matches. Empty or "*" returns all.',
      parameters: {
        type: 'object',
        properties: {
          query: { type: 'string', description: 'substring matched against skill name and description' },
        },
        additionalProperties: false,
      },
    },
  },
  async execute(input) {
    return await findSkills(input.query ?? '');
  },
};

const SkillUseInput = z.object({
  name: z.string().min(1),
});
type SkillUseInputT = z.infer<typeof SkillUseInput>;

export const skillUse: ToolDef<SkillUseInputT> = {
  name: 'skill_use',
  description:
    "Load the full body of a skill's SKILL.md by name. Returns the markdown playbook to follow. Discover names via skill_find. Errors: unknown_skill.",
  inputSchema: SkillUseInput,
  jsonSchema: {
    type: 'function',
    function: {
      name: 'skill_use',
      description: "Load the full body of a skill's SKILL.md by name.",
      parameters: {
        type: 'object',
        properties: {
          name: { type: 'string', description: 'skill name from skill_find' },
        },
        required: ['name'],
        additionalProperties: false,
      },
    },
  },
  async execute(input) {
    const body = await getSkillBody(input.name);
    if (body === null) {
      return { error: 'unknown_skill', message: `unknown skill: ${input.name}` };
    }
    return { body };
  },
};

const SkillResourceInput = z.object({
  name: z.string().min(1),
  path: z.string().min(1),
});
type SkillResourceInputT = z.infer<typeof SkillResourceInput>;

export const skillResource: ToolDef<SkillResourceInputT> = {
  name: 'skill_resource',
  description:
    "Read a support file inside a skill's folder (e.g. references/root-cause-tracing.md). Path is relative to the skill folder. Use skill_use to read SKILL.md itself. Errors: unknown_skill, unknown_resource, path_escape.",
  inputSchema: SkillResourceInput,
  jsonSchema: {
    type: 'function',
    function: {
      name: 'skill_resource',
      description: "Read a support file inside a skill's folder. Path is relative to the skill folder.",
      parameters: {
        type: 'object',
        properties: {
          name: { type: 'string', description: 'skill name' },
          path: { type: 'string', description: 'relative path under the skill folder' },
        },
        required: ['name', 'path'],
        additionalProperties: false,
      },
    },
  },
  async execute(input) {
    const result = await getSkillResource(input.name, input.path);
    if (!result.ok) {
      return { error: result.code, message: result.message };
    }
    return { content: result.content };
  },
};

// Batch 9.7: ask_user_input. Interactive elicitation. The model emits a tool
// call with 1-3 structured questions; the inference loop PAUSES (does not
// execute the tool server-side, does not recurse) and waits for the frontend
// to POST /api/chats/:id/answer_user_input with the user's selections. See
// routes/messages.ts for the resume path and services/inference.ts for the
// pause branch in executeToolPhase.
const AskUserInputInput = z.object({
  questions: z
    .array(
      z.object({
        question: z.string().min(1).max(200),
        type: z.enum(['single_select', 'multi_select']),
        options: z.array(z.string().min(1).max(80)).min(2).max(6),
      }),
    )
    .min(1)
    .max(3),
});
type AskUserInputInputT = z.infer<typeof AskUserInputInput>;

export const askUserInput: ToolDef<AskUserInputInputT> = {
  name: 'ask_user_input',
  description:
    "Ask the user 1-3 structured questions through an inline picker UI. Use when you genuinely need a choice the user must make (e.g. scope, options, preferences) before continuing. Each question has 2-6 options and accepts free-text answers in addition. The tool call pauses the conversation until the user submits — the next assistant turn sees their answers as the tool result. Do not use for trivial yes/no clarifications you could infer; prefer it over multi-paragraph speculation about what the user might want.",
  inputSchema: AskUserInputInput,
  jsonSchema: {
    type: 'function',
    function: {
      name: 'ask_user_input',
      description:
        'Ask the user 1-3 structured questions through an inline picker. Pauses the conversation until the user answers; the next turn sees their selections.',
      parameters: {
        type: 'object',
        properties: {
          questions: {
            type: 'array',
            minItems: 1,
            maxItems: 3,
            items: {
              type: 'object',
              properties: {
                question: { type: 'string', description: '<=200 chars, shown to the user' },
                type: {
                  type: 'string',
                  enum: ['single_select', 'multi_select'],
                  description: 'single_select = at most one option; multi_select = any subset',
                },
                options: {
                  type: 'array',
                  minItems: 2,
                  maxItems: 6,
                  items: { type: 'string' },
                  description: '2-6 strings, each <=80 chars; free-text input is always available alongside',
                },
              },
              required: ['question', 'type', 'options'],
              additionalProperties: false,
            },
          },
        },
        required: ['questions'],
        additionalProperties: false,
      },
    },
  },
  // Server-side no-op. The "execution" of ask_user_input is the user's
  // response, captured client-side and posted to /api/chats/:id/answer_user_input.
  // The inference loop detects this tool by name and pauses before reaching
  // executeToolCall — this fallback only runs if something bypasses that
  // branch, in which case the pending sentinel matches the pause-path shape.
  async execute(input) {
    return { _pending: true, questions: input.questions };
  },
};

// v1.13.3: alpha-sorted by tool.name at module load. llama.cpp's prompt
// cache hits on byte-identical prefixes; the tool list lives near the top
// of the system prompt, so any order drift would invalidate every cached
// turn. Single source of truth for ordering lives here — toolJsonSchemas()
// and TOOLS_BY_NAME inherit it.
export const ALL_TOOLS: ReadonlyArray<ToolDef<unknown>> = [
  viewFile as ToolDef<unknown>,
  listDir as ToolDef<unknown>,
  grep as ToolDef<unknown>,
  findFiles as ToolDef<unknown>,
  gitStatus as ToolDef<unknown>,
  skillFind as ToolDef<unknown>,
  skillUse as ToolDef<unknown>,
  skillResource as ToolDef<unknown>,
  askUserInput as ToolDef<unknown>,
  // v1.11.8: web tools. Gated per-chat via session.web_search_enabled
  // (with project default fallback) — see effectiveTools filter in
  // services/inference.ts.
  webSearch as ToolDef<unknown>,
  webFetch as ToolDef<unknown>,
  // v1.12 Track B.2: codecontext tools. Backed by the codecontext sidecar
  // container. All read-only. target_dir is resolved server-side from the
  // project root in codecontext_client.ts (the LLM never supplies it).
  getCodebaseOverview as ToolDef<unknown>,
  getFileAnalysis as ToolDef<unknown>,
  getSymbolInfo as ToolDef<unknown>,
  searchSymbols as ToolDef<unknown>,
  getDependencies as ToolDef<unknown>,
  watchChanges as ToolDef<unknown>,
  getSemanticNeighborhoods as ToolDef<unknown>,
  getFrameworkAnalysis as ToolDef<unknown>,
].sort((a, b) => a.name.localeCompare(b.name));

// v1.8.2: forward-compatible read-only whitelist. An agent whose `tools` is
// fully contained in this set gets a generous default tool budget (30);
// anything outside means the agent can mutate state and gets a tighter
// default (10). Every tool in v1.8.2 happens to be read-only, so the
// non-RO branch only takes effect once BooCoder lands write tools.
// Batch 9.6: skill_* added; all still read-only.
// Batch 9.7: ask_user_input added — it pauses execution but doesn't mutate
// project state, so it belongs in the read-only set for budget purposes.
export const READ_ONLY_TOOL_NAMES = [
  'view_file',
  'list_dir',
  'grep',
  'find_files',
  'git_status',
  'skill_find',
  'skill_use',
  'skill_resource',
  'ask_user_input',
  // v1.11.8: web tools don't mutate project state; counted as read-only
  // for the budget-tier calculation (BUDGET_READ_ONLY=30) when an agent's
  // toolset is fully contained in this list.
  'web_search',
  'web_fetch',
  // v1.12 Track B.2: codecontext tools. Read-only — they call the
  // codecontext sidecar which only analyzes files (never writes).
  'get_codebase_overview',
  'get_file_analysis',
  'get_symbol_info',
  'search_symbols',
  'get_dependencies',
  'watch_changes',
  'get_semantic_neighborhoods',
  'get_framework_analysis',
] as const;

export const TOOLS_BY_NAME: Record<string, ToolDef<unknown>> = Object.fromEntries(
  ALL_TOOLS.map((t) => [t.name, t])
);

export function toolJsonSchemas(): ToolJsonSchema[] {
  return ALL_TOOLS.map((t) => t.jsonSchema);
}