indifferentketchup/boocode
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge v1.12 track B: codecontext sidecar

Browse Source 
# Conflicts:
#	apps/web/src/components/ToolCallLine.tsx
#	docker-compose.yml
This commit is contained in:
indifferentketchup
2026-05-21 15:12:30 +00:00
parent be3c38ff2f 78914466d1
commit 16c69a38a1
23 changed files with 1627 additions and 204 deletions
Download Patch File Download Diff File Expand all files Collapse all files

191
AGENTS.md
View File

@@ -1,191 +0,0 @@
# Agents
## Code Reviewer
---
temperature: 0.3
description: Reviews code for bugs, security issues, and maintainability. Read-only.
---
You review code. Find real problems, not style nits.
Process:
1. Read the file(s) in question with view_file. If a diff is provided, read surrounding context too.
2. Use grep/find_files to check how changed symbols are used elsewhere.
3. Cite every finding as file:line.
Prioritize in order:
1. Bugs and logic errors
2. Security issues (injection, auth bypass, secret leakage, unsafe deserialization, SSRF, path traversal)
3. Race conditions, error handling, resource leaks
4. Performance issues with measurable impact
5. Maintainability (only if it blocks future work)
Skip: formatting, naming preferences, "consider extracting", "add a comment here". The user has a linter.
Output format:
- Critical: <file:line> — <issue> — <fix>
- Major: <file:line> — <issue> — <fix>
- Minor: <file:line> — <issue> — <fix>
If nothing critical or major, say so in one line. Do not pad.
## Debugger
---
temperature: 0.2
description: Diagnoses bugs from error messages, logs, or described symptoms.
---
You diagnose bugs. Form a hypothesis, prove it with evidence from the code.
Process:
1. Restate the symptom in one line. Confirm you understand it.
2. Read the error/stacktrace. Identify the exact frame where things go wrong.
3. view_file on that frame. Read 50 lines around it.
4. grep for callers, related state, recent changes that could explain it.
5. State the root cause with file:line evidence.
6. Propose the minimal fix. Note any side effects.
Rules:
- Never guess. If evidence is missing, say what you need (specific log line, specific file, specific repro step).
- Distinguish symptom from cause. A null check fixes the symptom; missing init causes it.
- Off-by-one, race conditions, and silent except blocks are common — check for them.
- If two plausible causes exist, name both and say what would discriminate.
Output:
- Symptom: <one line>
- Root cause: <file:line> — <explanation>
- Fix: <minimal diff or description>
- Risk: <what could break>
## Refactorer
---
temperature: 0.3
description: Proposes refactors for clarity, deduplication, or decoupling. Read-only — outputs plans, not edits.
---
You propose refactors. You do not apply them. The user applies via OpenCode or Claude Code.
Process:
1. Read the target file(s).
2. grep for callers, duplicates, and similar patterns elsewhere in the repo.
3. Identify the smallest refactor that delivers the goal.
Prioritize:
1. Deduplication where 3+ sites have near-identical logic
2. Extracting a function/module when one is doing two unrelated jobs
3. Decoupling when a change in A forces a change in B unnecessarily
4. Renaming when a name actively misleads
Reject:
- Refactors that touch 10+ files for marginal gain
- "Modernization" with no concrete benefit
- Abstraction for future flexibility that may never come
- Style-only changes
Output:
- Goal: <one line>
- Scope: <files affected, count of lines roughly>
- Plan: numbered steps, each one self-contained
- Risk: <what tests must pass, what could regress>
- Skip if: <conditions under which this refactor is not worth doing>
## Architect
---
temperature: 0.5
description: Designs new features, modules, or architectural changes. Outputs a build plan.
---
You design. You produce build plans, not code.
Process:
1. Restate the goal in your own words. Confirm constraints (perf, deploy, deps).
2. list_dir the relevant areas. Read existing patterns — match them unless there's a reason not to.
3. Decide: extend existing code or add new module. Justify.
4. Sketch the data flow: inputs → transforms → outputs → side effects.
5. Identify integration points: DB schema, API surface, env vars, container boundaries.
6. List failure modes and how the design handles them.
Rules:
- Reuse before inventing. If a service/lib in the repo already does this, say so.
- Prefer boring tech. New deps require justification.
- Tailscale IPs for internal routing. No 0.0.0.0 binds.
- Least privilege: separate read/write paths, explicit auth gates.
- State assumptions inline. Do not ask clarifying questions mid-design unless blocked.
Output:
- Goal
- Existing code to reuse: <file paths>
- New code: <file paths, one-line purpose each>
- Data model changes: <SQL or schema diff>
- API surface: <endpoints, request/response shapes>
- Failure modes: <list>
- Build order: numbered, each step 30-90 min
## Security Auditor
---
temperature: 0.2
description: Audits code for security vulnerabilities. Read-only.
---
You audit for security issues. Concrete findings only, no generic warnings.
Process:
1. Identify the trust boundary: where does untrusted input enter? Where does it leave?
2. Trace input flow with grep. Mark every transformation.
3. Check each finding against a real attack scenario.
Look for:
- Injection: SQL (raw queries, string concat into queries), command (subprocess with shell=True, unescaped args), XSS (unescaped output in HTML/JSX), template injection, NoSQL injection
- AuthN/AuthZ: missing checks on routes, IDOR (user-supplied IDs without ownership check), JWT misuse (alg=none, weak secret, no expiry), session fixation
- Secrets: hardcoded keys/passwords, .env in repo, secrets in logs, secrets in error messages
- Crypto: weak hashes (MD5, SHA1 for passwords), missing salt, predictable randomness (Math.random for tokens), ECB mode, custom crypto
- Network: SSRF (user URL → server fetch), open CORS, missing CSRF on state-changing requests, plaintext over public network
- File: path traversal, unrestricted upload type/size, zip slip
- Deserialization: pickle, yaml.load, eval, exec on user input
- Resource: missing rate limits on auth/expensive endpoints, unbounded query results
For each finding:
- Severity: Critical / High / Medium / Low
- Location: file:line
- Attack scenario: one sentence describing how an attacker exploits this
- Fix: minimal change
Skip:
- Generic "use HTTPS" advice
- "Consider adding rate limiting" without a specific endpoint
- CVE-of-the-week scares without proof the code is affected
If the code is clean, say so. Do not invent findings.
## Prompt Builder
---
temperature: 0.4
description: Builds prompts for OpenCode, Claude Code, or BooCode dispatch.
---
You write prompts that another coding agent will execute. Your output is the prompt, not the work.
Process:
1. Ask the user (or read context) for: goal, target repo, target files if known, constraints.
2. list_dir and view_file the target area. Confirm files exist and are roughly the shape you think.
3. Identify imports, exports, and conventions in the repo (component layout, error handling style, test framework).
4. Write the prompt.
Prompt structure:
- One-line goal at the top
- Constraints block: don't commit, don't push, don't pull. Use `#careful` and `#nofluff` style hashtags if the target agent honors them
- Pre-flight: list_dir or grep commands the agent must run before writing (e.g. "run: ls frontend/src/components/ui/ and only import primitives that exist")
- Files to modify: explicit paths
- Files to create: explicit paths with one-line purpose
- Behavior spec: numbered, testable
- Backup rule: `cp file file.bak-$(date +%Y%m%d)` before any destructive edit
- Verification: `py_compile`, `tsc --noEmit`, `docker compose up --build -d` — whichever applies
- Stop conditions: when to halt and report instead of pressing on
Rules:
- Tailored to the target agent: OpenCode honors hashtag snippets and skills; Claude Code honors CLAUDE.md and slash commands; BooCode batches are written as user-facing markdown
- Never include credentials or secrets
- Never instruct the agent to commit or push
- Include the exact model the user wants if dispatch is via Paseo or BooCode batch
- For BooLab frontend prompts, always include the "verify shadcn primitives exist" preflight
Output: the prompt, ready to paste. Nothing else.

2
CLAUDE.md
View File

@@ -114,6 +114,8 @@ Required: `DATABASE_URL`, `LLAMA_SWAP_URL`. Optional: `PORT` (3000), `HOST` (0.0
- A local PreToolUse hook (`security_reminder_hook.py`) regex-flags Node's older `child_process` spawn helpers as unsafe (false positive even on the File-suffixed variant). Use `spawn` — it's accepted. - A local PreToolUse hook (`security_reminder_hook.py`) regex-flags Node's older `child_process` spawn helpers as unsafe (false positive even on the File-suffixed variant). Use `spawn` — it's accepted.
- `/opt/boolab` hosts a working sibling BooCode terminal at `boocode.indifferentketchup.com`. Useful for visual side-by-side comparison on the same iPhone when debugging booterm rendering. Boolab uses Tailwind v3 (`@tailwind base`); boocode uses v4 — many subtle build differences. Don't assume parity. - `/opt/boolab` hosts a working sibling BooCode terminal at `boocode.indifferentketchup.com`. Useful for visual side-by-side comparison on the same iPhone when debugging booterm rendering. Boolab uses Tailwind v3 (`@tailwind base`); boocode uses v4 — many subtle build differences. Don't assume parity.
- booterm SSHs to the host as `samkintop@100.114.205.53` (the Tailscale IP). The hostname `ubuntu-homelab` (shown in the bash prompt after login) does NOT resolve from inside the container — only the host's `/etc/hosts` knows it. Override via `BOOTERM_SSH_HOST` / `BOOTERM_SSH_USER` env vars in docker-compose if you ever move the shell to a different machine. - booterm SSHs to the host as `samkintop@100.114.205.53` (the Tailscale IP). The hostname `ubuntu-homelab` (shown in the bash prompt after login) does NOT resolve from inside the container — only the host's `/etc/hosts` knows it. Override via `BOOTERM_SSH_HOST` / `BOOTERM_SSH_USER` env vars in docker-compose if you ever move the shell to a different machine.
- codecontext sidecar lives at `/opt/boocode/codecontext/`. Sidecar HTTP API at `http://codecontext:8080/v1/<tool_name>` over the `boocode_net` bridge (no host port). BooCode wrappers in `apps/server/src/services/tools/codecontext/`. The `.codecontextignore.template` documents recommended ignore patterns; users copy and adapt to project root manually.
- `os/exec` child supervisors must explicitly call `child.Wait()` in a goroutine and `os.Exit` on child death. `Signal(0)` returns nil on zombies and is NOT a liveness check. Without `Wait()`, docker's `restart: unless-stopped` policy never fires because the parent stays alive. The `codecontext/shim.go` implementation is the reference pattern.
## Conventions ## Conventions

205
apps/server/src/services/__tests__/codecontext_client.test.ts Normal file
View File

@@ -0,0 +1,205 @@
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
import { mkdir, mkdtemp, rm } from 'node:fs/promises';
import { join } from 'node:path';
import { tmpdir } from 'node:os';
import { callCodecontext } from '../codecontext_client.js';
// ---- fixtures ---------------------------------------------------------------
let workDir: string;
let projectDir: string;
let outsideDir: string;
beforeEach(async () => {
// Shared workspace so projectDir and outsideDir are siblings but the
// realpath escape check still treats outsideDir as outside the project.
workDir = await mkdtemp(join(tmpdir(), 'codecontext-test-'));
projectDir = join(workDir, 'project');
outsideDir = join(workDir, 'outside');
await mkdir(projectDir);
await mkdir(outsideDir);
});
afterEach(async () => {
await rm(workDir, { recursive: true, force: true });
vi.restoreAllMocks();
});
function mockJSONResponse(body: unknown, status = 200): Response {
return new Response(JSON.stringify(body), {
status,
headers: { 'content-type': 'application/json' },
});
}
// ---- tests ------------------------------------------------------------------
describe('callCodecontext — target_dir validation', () => {
it('rejects when target_dir does not exist', async () => {
const fetcher = vi.fn();
await expect(
callCodecontext(
{
toolName: 'get_codebase_overview',
args: { target_dir: '/nonexistent/path/deliberately/missing' },
projectPath: projectDir,
},
fetcher as unknown as typeof fetch,
),
).rejects.toThrow(/target_dir does not exist/);
expect(fetcher).not.toHaveBeenCalled();
});
it('rejects when target_dir is outside the project root', async () => {
const fetcher = vi.fn();
await expect(
callCodecontext(
{
toolName: 'get_codebase_overview',
args: { target_dir: outsideDir },
projectPath: projectDir,
},
fetcher as unknown as typeof fetch,
),
).rejects.toThrow(/escapes project root/);
expect(fetcher).not.toHaveBeenCalled();
});
it('injects projectPath as target_dir when args.target_dir is undefined', async () => {
const fetcher = vi.fn().mockResolvedValue(
mockJSONResponse({ result: 'overview text', error: null }),
);
await callCodecontext(
{
toolName: 'get_codebase_overview',
args: { include_stats: true },
projectPath: projectDir,
},
fetcher as unknown as typeof fetch,
);
expect(fetcher).toHaveBeenCalledTimes(1);
const body = JSON.parse(fetcher.mock.calls[0]![1]!.body as string);
expect(body.target_dir).toBe(projectDir);
expect(body.include_stats).toBe(true);
});
});
describe('callCodecontext — HTTP request shape', () => {
it('POSTs to /v1/<toolName> with JSON content-type', async () => {
const fetcher = vi.fn().mockResolvedValue(
mockJSONResponse({ result: 'ok', error: null }),
);
await callCodecontext(
{
toolName: 'search_symbols',
args: { query: 'User', limit: 5 },
projectPath: projectDir,
},
fetcher as unknown as typeof fetch,
);
expect(fetcher).toHaveBeenCalledTimes(1);
const [url, init] = fetcher.mock.calls[0]!;
expect(url).toMatch(/\/v1\/search_symbols$/);
expect(init.method).toBe('POST');
expect(init.headers['Content-Type']).toBe('application/json');
const body = JSON.parse(init.body);
expect(body).toMatchObject({ query: 'User', limit: 5, target_dir: projectDir });
});
});
describe('callCodecontext — result handling', () => {
it('returns { result, truncated: false } when codecontext result is under the 32 kB limit', async () => {
const fetcher = vi.fn().mockResolvedValue(
mockJSONResponse({ result: 'a short markdown report', error: null }),
);
const out = await callCodecontext(
{
toolName: 'get_codebase_overview',
args: {},
projectPath: projectDir,
},
fetcher as unknown as typeof fetch,
);
expect(out.truncated).toBe(false);
expect(out.result).toBe('a short markdown report');
});
it('truncates and marks truncated: true when result exceeds 32 kB', async () => {
const bigResult = 'x'.repeat(40_000);
const fetcher = vi.fn().mockResolvedValue(
mockJSONResponse({ result: bigResult, error: null }),
);
const out = await callCodecontext(
{
toolName: 'get_codebase_overview',
args: {},
projectPath: projectDir,
},
fetcher as unknown as typeof fetch,
);
expect(out.truncated).toBe(true);
expect(out.result).toMatch(/\[truncated, 8000 chars omitted; narrow with file_path/);
expect(out.result.length).toBeLessThan(bigResult.length);
});
});
describe('callCodecontext — error paths', () => {
it('throws an actionable error when codecontext reports an empty-file parser failure', async () => {
const fetcher = vi.fn().mockResolvedValue(
mockJSONResponse({
result: null,
error:
'failed to refresh analysis: failed to analyze directory: ' +
'failed to parse file /opt/boolab/.opencode/node_modules/foo/index.js: content is empty',
}),
);
await expect(
callCodecontext(
{ toolName: 'get_codebase_overview', args: {}, projectPath: projectDir },
fetcher as unknown as typeof fetch,
),
).rejects.toThrow(/codecontext parse failure.*\.codecontextignore/);
});
it('throws a generic error when codecontext reports other errors', async () => {
const fetcher = vi.fn().mockResolvedValue(
mockJSONResponse({ result: null, error: 'symbol_name is required' }),
);
await expect(
callCodecontext(
{ toolName: 'get_symbol_info', args: {}, projectPath: projectDir },
fetcher as unknown as typeof fetch,
),
).rejects.toThrow(/codecontext error: symbol_name is required/);
});
it('throws on HTTP non-2xx response', async () => {
const fetcher = vi.fn().mockResolvedValue(
new Response('upstream gateway boom', { status: 502 }),
);
await expect(
callCodecontext(
{ toolName: 'get_codebase_overview', args: {}, projectPath: projectDir },
fetcher as unknown as typeof fetch,
),
).rejects.toThrow(/codecontext HTTP 502/);
});
it('translates a fetcher AbortError to a "timed out" error', async () => {
// The catch branch in callCodecontext maps any AbortError (whether it
// came from our internal 30s setTimeout or from the fetcher itself) to a
// "timed out" message. Exercising the catch directly is cleaner than
// wrangling vi.useFakeTimers with realpath's microtask scheduling.
const abortingFetcher = vi.fn().mockImplementation(() => {
const err = new Error('The user aborted a request.');
err.name = 'AbortError';
return Promise.reject(err);
});
await expect(
callCodecontext(
{ toolName: 'get_codebase_overview', args: {}, projectPath: projectDir },
abortingFetcher as unknown as typeof fetch,
),
).rejects.toThrow(/timed out after 30000ms/);
});
});

155
apps/server/src/services/__tests__/codecontext_tools.test.ts Normal file
View File

@@ -0,0 +1,155 @@
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
import { mkdtemp, rm } from 'node:fs/promises';
import { join } from 'node:path';
import { tmpdir } from 'node:os';
import { executeGetCodebaseOverview } from '../tools/codecontext/get_codebase_overview.js';
import { executeGetFileAnalysis } from '../tools/codecontext/get_file_analysis.js';
import { executeGetSymbolInfo } from '../tools/codecontext/get_symbol_info.js';
import { executeSearchSymbols } from '../tools/codecontext/search_symbols.js';
import { executeGetDependencies } from '../tools/codecontext/get_dependencies.js';
import { executeWatchChanges } from '../tools/codecontext/watch_changes.js';
import { executeGetSemanticNeighborhoods } from '../tools/codecontext/get_semantic_neighborhoods.js';
import { executeGetFrameworkAnalysis } from '../tools/codecontext/get_framework_analysis.js';
// ---- fixtures ---------------------------------------------------------------
let projectDir: string;
beforeEach(async () => {
projectDir = await mkdtemp(join(tmpdir(), 'codecontext-tools-test-'));
});
afterEach(async () => {
await rm(projectDir, { recursive: true, force: true });
vi.restoreAllMocks();
});
function mockJSONResponse(body: unknown, status = 200): Response {
return new Response(JSON.stringify(body), {
status,
headers: { 'content-type': 'application/json' },
});
}
// Stub fetcher that records every call and returns a canned successful body.
// Each test inspects fetcher.mock.calls[0] to assert URL + body shape.
function makeStub() {
return vi.fn().mockResolvedValue(
mockJSONResponse({ result: 'wrapped ok', error: null }),
);
}
function parsePOST(fetcher: ReturnType<typeof makeStub>): {
url: string;
body: Record<string, unknown>;
} {
expect(fetcher).toHaveBeenCalledTimes(1);
const [url, init] = fetcher.mock.calls[0]! as [string, { body: string }];
return { url, body: JSON.parse(init.body) };
}
// ---- per-wrapper smoke tests -----------------------------------------------
describe('codecontext wrappers — toolName + args forwarding', () => {
it('get_codebase_overview posts to /v1/get_codebase_overview with include_stats default true', async () => {
const fetcher = makeStub();
await executeGetCodebaseOverview({}, projectDir, fetcher as unknown as typeof fetch);
const { url, body } = parsePOST(fetcher);
expect(url).toMatch(/\/v1\/get_codebase_overview$/);
expect(body).toMatchObject({ include_stats: true, target_dir: projectDir });
});
it('get_file_analysis forwards file_path', async () => {
const fetcher = makeStub();
await executeGetFileAnalysis(
{ file_path: 'apps/server/src/index.ts' },
projectDir,
fetcher as unknown as typeof fetch,
);
const { url, body } = parsePOST(fetcher);
expect(url).toMatch(/\/v1\/get_file_analysis$/);
expect(body).toMatchObject({
file_path: 'apps/server/src/index.ts',
target_dir: projectDir,
});
});
it('get_symbol_info forwards symbol_name and omits optional fields when unset', async () => {
const fetcher = makeStub();
await executeGetSymbolInfo(
{ symbol_name: 'buildSystemPrompt' },
projectDir,
fetcher as unknown as typeof fetch,
);
const { url, body } = parsePOST(fetcher);
expect(url).toMatch(/\/v1\/get_symbol_info$/);
expect(body).toMatchObject({ symbol_name: 'buildSystemPrompt', target_dir: projectDir });
expect(body).not.toHaveProperty('file_path');
expect(body).not.toHaveProperty('framework_type');
});
it('search_symbols defaults limit to 20 and forwards filters when set', async () => {
const fetcher = makeStub();
await executeSearchSymbols(
{ query: 'User', symbol_type: 'class' },
projectDir,
fetcher as unknown as typeof fetch,
);
const { url, body } = parsePOST(fetcher);
expect(url).toMatch(/\/v1\/search_symbols$/);
expect(body).toMatchObject({
query: 'User',
symbol_type: 'class',
limit: 20,
target_dir: projectDir,
});
});
it('get_dependencies defaults direction to "both"', async () => {
const fetcher = makeStub();
await executeGetDependencies({}, projectDir, fetcher as unknown as typeof fetch);
const { url, body } = parsePOST(fetcher);
expect(url).toMatch(/\/v1\/get_dependencies$/);
expect(body).toMatchObject({ direction: 'both', target_dir: projectDir });
expect(body).not.toHaveProperty('file_path');
});
it('watch_changes forwards enable=false', async () => {
const fetcher = makeStub();
await executeWatchChanges(
{ enable: false },
projectDir,
fetcher as unknown as typeof fetch,
);
const { url, body } = parsePOST(fetcher);
expect(url).toMatch(/\/v1\/watch_changes$/);
expect(body).toMatchObject({ enable: false, target_dir: projectDir });
});
it('get_semantic_neighborhoods defaults max_results to 10', async () => {
const fetcher = makeStub();
await executeGetSemanticNeighborhoods(
{},
projectDir,
fetcher as unknown as typeof fetch,
);
const { url, body } = parsePOST(fetcher);
expect(url).toMatch(/\/v1\/get_semantic_neighborhoods$/);
expect(body).toMatchObject({ max_results: 10, target_dir: projectDir });
});
it('get_framework_analysis sends only target_dir when no args are provided', async () => {
const fetcher = makeStub();
await executeGetFrameworkAnalysis(
{},
projectDir,
fetcher as unknown as typeof fetch,
);
const { url, body } = parsePOST(fetcher);
expect(url).toMatch(/\/v1\/get_framework_analysis$/);
expect(body).toMatchObject({ target_dir: projectDir });
expect(body).not.toHaveProperty('framework');
expect(body).not.toHaveProperty('include_stats');
});
});

19
apps/server/src/services/agents.ts
View File

@@ -1,6 +1,7 @@
import { promises as fs } from 'node:fs'; import { promises as fs } from 'node:fs';
import { join } from 'node:path'; import { join } from 'node:path';
import type { Agent, AgentsResponse, AgentParseError } from '../types/api.js'; import type { Agent, AgentsResponse, AgentParseError } from '../types/api.js';
import { ALL_TOOLS } from './tools.js';
// v1.8.1: global agents live at /data/AGENTS.md inside the container // v1.8.1: global agents live at /data/AGENTS.md inside the container
// (./data:/data:ro mount on the host). Per-project AGENTS.md at the project // (./data:/data:ro mount on the host). Per-project AGENTS.md at the project
@@ -10,18 +11,12 @@ import type { Agent, AgentsResponse, AgentParseError } from '../types/api.js';
const GLOBAL_AGENTS_PATH = '/data/AGENTS.md'; const GLOBAL_AGENTS_PATH = '/data/AGENTS.md';
const CACHE_TTL_MS = 60_000; const CACHE_TTL_MS = 60_000;
// Tools whitelist universe matches services/tools.ts ALL_TOOLS. Keep in sync. // v1.12 Track B.3: derive from services/tools.ts ALL_TOOLS so new tools are
// Batch 9.6: skill_find / skill_use / skill_resource added. Agents without an // auto-recognized in agent frontmatter `tools:` arrays. The previous
// explicit `tools:` field inherit the full default set (which now includes // hand-maintained list drifted (web_search/web_fetch from v1.11.8 + the 8
// the skill tools); agents with an explicit `tools:` array must list any // codecontext tools were missing), silently filtering valid tool names out
// skill tool they want to use — strict opt-in. // of agents that opted in. Single source of truth is tools.ts now.
// Batch 9.7: ask_user_input added — same opt-in semantics. Agents with an const ALL_TOOL_NAMES: readonly string[] = ALL_TOOLS.map((t) => t.name);
// explicit tools list that omits it cannot trigger the interactive picker.
const ALL_TOOL_NAMES = [
'view_file', 'list_dir', 'grep', 'find_files', 'git_status',
'skill_find', 'skill_use', 'skill_resource',
'ask_user_input',
] as const;
const DEFAULT_TOOLS: string[] = [...ALL_TOOL_NAMES]; const DEFAULT_TOOLS: string[] = [...ALL_TOOL_NAMES];
const DEFAULT_TEMPERATURE = 0.7; const DEFAULT_TEMPERATURE = 0.7;

118
apps/server/src/services/codecontext_client.ts Normal file
View File

@@ -0,0 +1,118 @@
// v1.12 Track B.2: shared HTTP client for the codecontext sidecar. The 8
// per-tool wrappers under tools/codecontext/ all funnel through callCodecontext
// — they're thin adapters that supply toolName + args + projectPath. The
// client owns:
//
// 1. target_dir validation. Codecontext's HTTP shim is naive and forwards
// any target_dir to codecontext, so without this layer a model that
// hallucinated a target_dir could read /opt/anything-on-disk. The
// project root is realpath'd and the requested target_dir is constrained
// to it (same invariant as path_guard.ts but for the codecontext path).
// 2. Inline truncation at 32 kB. Codecontext outputs are markdown reports
// that can balloon on large projects; the model can re-narrow via
// file_path / file_type / limit. Matches the "inline truncation, no
// opaque-id retrieval" decision locked in the 2026-05-21 recon.
// 3. Friendly mapping of codecontext's known failure modes — the empty-
// file parser bug (upstream issue #37) returns a generic error string,
// which we re-surface with a hint to add the file to .codecontextignore.
import { realpath } from 'node:fs/promises';
export interface CodecontextRequest {
toolName: string;
args: Record<string, unknown>;
projectPath: string;
}
export interface CodecontextResponse {
result: string;
truncated: boolean;
}
const CODECONTEXT_BASE_URL = process.env['CODECONTEXT_URL'] ?? 'http://codecontext:8080';
const TRUNCATION_LIMIT = 32_000;
const REQUEST_TIMEOUT_MS = 30_000;
export async function callCodecontext(
req: CodecontextRequest,
fetcher: typeof fetch = fetch,
): Promise<CodecontextResponse> {
// Step 1: realpath the project root, then realpath the requested target_dir
// (defaulting to projectPath when the caller didn't pass one — the 8 wrappers
// never pass target_dir; tests can override). A non-existent target_dir
// throws before we hit the network so the model gets a sharp error.
const resolvedProject = await realpath(req.projectPath);
const requestedTarget = req.args['target_dir'];
const targetDir = typeof requestedTarget === 'string' && requestedTarget.length > 0
? requestedTarget
: req.projectPath;
const resolvedTarget = await realpath(targetDir).catch(() => null);
if (resolvedTarget === null) {
throw new Error(`target_dir does not exist: ${targetDir}`);
}
if (resolvedTarget !== resolvedProject && !resolvedTarget.startsWith(resolvedProject + '/')) {
throw new Error(`target_dir ${targetDir} escapes project root ${resolvedProject}`);
}
// Step 2: re-build args with the resolved target_dir so codecontext sees
// the real absolute path, not a symlink or relative form.
const argsToSend = { ...req.args, target_dir: resolvedTarget };
// Step 3: POST with a hard timeout. AbortController + setTimeout pattern
// matches web_fetch.ts; nothing fancier needed.
const controller = new AbortController();
const timer = setTimeout(() => controller.abort(), REQUEST_TIMEOUT_MS);
let response: Response;
try {
response = await fetcher(`${CODECONTEXT_BASE_URL}/v1/${req.toolName}`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify(argsToSend),
signal: controller.signal,
});
} catch (err) {
clearTimeout(timer);
if (err instanceof Error && (err.name === 'AbortError' || err.name === 'TimeoutError')) {
throw new Error(`codecontext request timed out after ${REQUEST_TIMEOUT_MS}ms`);
}
throw new Error(
`codecontext network error: ${err instanceof Error ? err.message : String(err)}`,
);
}
clearTimeout(timer);
if (!response.ok) {
const text = await response.text().catch(() => '');
throw new Error(`codecontext HTTP ${response.status}: ${text.slice(0, 200)}`);
}
const body = (await response.json()) as { result: string | null; error: string | null };
if (body.error) {
// Upstream issue #37: empty source files crash codecontext's parser. The
// error message reliably contains "content is empty"; surface an
// actionable hint instead of the bare codecontext message.
if (body.error.includes('content is empty')) {
throw new Error(
`codecontext parse failure: ${body.error}. ` +
`Add the offending path to .codecontextignore in the project root and retry.`,
);
}
throw new Error(`codecontext error: ${body.error}`);
}
if (body.result === null) {
return { result: '', truncated: false };
}
// Step 4: inline truncation. The model gets a clear hint about how to
// narrow the next call rather than a silent cut. Mirrors web_fetch.ts.
if (body.result.length > TRUNCATION_LIMIT) {
const truncated = body.result.slice(0, TRUNCATION_LIMIT);
const omitted = body.result.length - TRUNCATION_LIMIT;
return {
result:
`${truncated}\n\n[truncated, ${omitted} chars omitted; narrow with file_path, file_type, or limit]`,
truncated: true,
};
}
return { result: body.result, truncated: false };
}

18
apps/server/src/services/inference.ts
View File

@@ -603,10 +603,26 @@ async function executeToolCall(
} }
const parsed = tool.inputSchema.safeParse(toolCall.args); const parsed = tool.inputSchema.safeParse(toolCall.args);
if (!parsed.success) { if (!parsed.success) {
// v1.12 Track B.2: enrich the zod-reject path so the model sees a
// one-line, tool-named hint ("tool 'search_symbols' rejected — query:
// Required") instead of a JSON blob of flatten output. Higher recovery
// rate on the next turn; doom-loop guard still bounds infinite retries.
// The cast is because tool.inputSchema is ZodType<unknown>, so zod can't
// statically narrow flatten()'s fieldErrors key set — but the runtime
// shape is the standard { formErrors: string[]; fieldErrors: Record<...> }.
const flatten = parsed.error.flatten() as {
formErrors: string[];
fieldErrors: Record<string, string[] | undefined>;
};
const fieldErrors = Object.entries(flatten.fieldErrors)
.map(([field, errs]) => `${field}: ${errs?.[0] ?? 'invalid'}`)
.join('; ');
const formError = flatten.formErrors[0];
const hint = fieldErrors || formError || 'unknown validation error';
return { return {
output: null, output: null,
truncated: false, truncated: false,
error: `invalid input: ${JSON.stringify(parsed.error.flatten())}`, error: `tool '${toolCall.name}' rejected — ${hint}`,
}; };
} }
try { try {

34
apps/server/src/services/tools.ts
View File

@@ -8,6 +8,19 @@ import { getGitMeta } from './git_meta.js';
import { findSkills, getSkillBody, getSkillResource } from './skills.js'; import { findSkills, getSkillBody, getSkillResource } from './skills.js';
import { webSearch } from './web_search.js'; import { webSearch } from './web_search.js';
import { webFetch } from './web_fetch.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 MAX_FILE_BYTES = 5 * 1024 * 1024;
const DEFAULT_VIEW_LINES = 200; const DEFAULT_VIEW_LINES = 200;
@@ -529,6 +542,17 @@ export const ALL_TOOLS: ReadonlyArray<ToolDef<unknown>> = [
// services/inference.ts. // services/inference.ts.
webSearch as ToolDef<unknown>, webSearch as ToolDef<unknown>,
webFetch 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>,
]; ];
// v1.8.2: forward-compatible read-only whitelist. An agent whose `tools` is // v1.8.2: forward-compatible read-only whitelist. An agent whose `tools` is
@@ -554,6 +578,16 @@ export const READ_ONLY_TOOL_NAMES = [
// toolset is fully contained in this list. // toolset is fully contained in this list.
'web_search', 'web_search',
'web_fetch', '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; ] as const;
export const TOOLS_BY_NAME: Record<string, ToolDef<unknown>> = Object.fromEntries( export const TOOLS_BY_NAME: Record<string, ToolDef<unknown>> = Object.fromEntries(

59
apps/server/src/services/tools/codecontext/get_codebase_overview.ts Normal file
View File

@@ -0,0 +1,59 @@
// v1.12 Track B.2: codecontext wrapper — get_codebase_overview.
// Pattern mirrors services/web_search.ts: pure executor + ToolDef wrapper.
// target_dir is supplied by callCodecontext from the resolved project root.
import { z } from 'zod';
import type { ToolDef } from '../../tools.js';
import { callCodecontext, type CodecontextResponse } from '../../codecontext_client.js';
export const GetCodebaseOverviewInput = z.object({
include_stats: z.boolean().optional(),
});
export type GetCodebaseOverviewInputT = z.infer<typeof GetCodebaseOverviewInput>;
const DESCRIPTION =
'Returns a structured overview of the codebase: file count, symbol count, primary languages, and top-level architecture. ' +
'Use this before deeper investigation to orient yourself in an unfamiliar codebase. ' +
'Tree-sitter coverage: full for JS/Python/Java/Go/Rust/C++. TypeScript symbols are approximate (uses JS grammar). ' +
'PHP and SQL are not supported — fall back to view_file/grep for those.';
export async function executeGetCodebaseOverview(
input: GetCodebaseOverviewInputT,
projectPath: string,
fetcher: typeof fetch = fetch,
): Promise<CodecontextResponse> {
return callCodecontext(
{
toolName: 'get_codebase_overview',
args: { include_stats: input.include_stats ?? true },
projectPath,
},
fetcher,
);
}
export const getCodebaseOverview: ToolDef<GetCodebaseOverviewInputT> = {
name: 'get_codebase_overview',
description: DESCRIPTION,
inputSchema: GetCodebaseOverviewInput,
jsonSchema: {
type: 'function',
function: {
name: 'get_codebase_overview',
description: DESCRIPTION,
parameters: {
type: 'object',
properties: {
include_stats: {
type: 'boolean',
description: 'Include file count, symbol count, language stats. Defaults to true.',
},
},
additionalProperties: false,
},
},
},
async execute(input, projectRoot) {
return await executeGetCodebaseOverview(input, projectRoot);
},
};

60
apps/server/src/services/tools/codecontext/get_dependencies.ts Normal file
View File

@@ -0,0 +1,60 @@
// v1.12 Track B.2: codecontext wrapper — get_dependencies.
import { z } from 'zod';
import type { ToolDef } from '../../tools.js';
import { callCodecontext, type CodecontextResponse } from '../../codecontext_client.js';
export const GetDependenciesInput = z.object({
file_path: z.string().optional(),
direction: z.enum(['incoming', 'outgoing', 'both']).optional(),
});
export type GetDependenciesInputT = z.infer<typeof GetDependenciesInput>;
const DESCRIPTION =
'Returns the import/dependency graph either for a single file (when file_path is set) or for the whole project. ' +
'Direction "outgoing" = what this file imports; "incoming" = what imports this file; "both" = the union. ' +
'Tree-sitter coverage: full for JS/Python/Java/Go/Rust/C++. TypeScript dependencies are approximate. ' +
'PHP and SQL are not supported.';
export async function executeGetDependencies(
input: GetDependenciesInputT,
projectPath: string,
fetcher: typeof fetch = fetch,
): Promise<CodecontextResponse> {
const args: Record<string, unknown> = {
direction: input.direction ?? 'both',
};
if (input.file_path) args['file_path'] = input.file_path;
return callCodecontext({ toolName: 'get_dependencies', args, projectPath }, fetcher);
}
export const getDependencies: ToolDef<GetDependenciesInputT> = {
name: 'get_dependencies',
description: DESCRIPTION,
inputSchema: GetDependenciesInput,
jsonSchema: {
type: 'function',
function: {
name: 'get_dependencies',
description: DESCRIPTION,
parameters: {
type: 'object',
properties: {
file_path: {
type: 'string',
description: 'Narrow to a single file. Omit for a project-wide graph.',
},
direction: {
type: 'string',
enum: ['incoming', 'outgoing', 'both'],
description: 'Which edges to include. Defaults to "both".',
},
},
additionalProperties: false,
},
},
},
async execute(input, projectRoot) {
return await executeGetDependencies(input, projectRoot);
},
};

58
apps/server/src/services/tools/codecontext/get_file_analysis.ts Normal file
View File

@@ -0,0 +1,58 @@
// v1.12 Track B.2: codecontext wrapper — get_file_analysis.
import { z } from 'zod';
import type { ToolDef } from '../../tools.js';
import { callCodecontext, type CodecontextResponse } from '../../codecontext_client.js';
export const GetFileAnalysisInput = z.object({
file_path: z.string().min(1),
});
export type GetFileAnalysisInputT = z.infer<typeof GetFileAnalysisInput>;
const DESCRIPTION =
'Returns detailed analysis of a single file: symbols defined, imports, exports, and inferred role. ' +
'Use when you have a specific file in mind and need its structure without view_file-ing the whole thing. ' +
'Tree-sitter coverage: full for JS/Python/Java/Go/Rust/C++. TypeScript symbols are approximate. ' +
'PHP and SQL are not supported — fall back to view_file for those.';
export async function executeGetFileAnalysis(
input: GetFileAnalysisInputT,
projectPath: string,
fetcher: typeof fetch = fetch,
): Promise<CodecontextResponse> {
return callCodecontext(
{
toolName: 'get_file_analysis',
args: { file_path: input.file_path },
projectPath,
},
fetcher,
);
}
export const getFileAnalysis: ToolDef<GetFileAnalysisInputT> = {
name: 'get_file_analysis',
description: DESCRIPTION,
inputSchema: GetFileAnalysisInput,
jsonSchema: {
type: 'function',
function: {
name: 'get_file_analysis',
description: DESCRIPTION,
parameters: {
type: 'object',
properties: {
file_path: {
type: 'string',
description: 'Absolute or project-relative path to the file.',
},
},
required: ['file_path'],
additionalProperties: false,
},
},
},
async execute(input, projectRoot) {
return await executeGetFileAnalysis(input, projectRoot);
},
};

58
apps/server/src/services/tools/codecontext/get_framework_analysis.ts Normal file
View File

@@ -0,0 +1,58 @@
// v1.12 Track B.2: codecontext wrapper — get_framework_analysis.
import { z } from 'zod';
import type { ToolDef } from '../../tools.js';
import { callCodecontext, type CodecontextResponse } from '../../codecontext_client.js';
export const GetFrameworkAnalysisInput = z.object({
framework: z.string().optional(),
include_stats: z.boolean().optional(),
});
export type GetFrameworkAnalysisInputT = z.infer<typeof GetFrameworkAnalysisInput>;
const DESCRIPTION =
'Returns framework-specific structural analysis: component relationships (React), hook usage patterns, store wiring (Vue/Pinia), service registration (Angular/Nest), etc. ' +
'When framework is omitted, codecontext auto-detects from the project files. ' +
'Tree-sitter coverage: full for JS/Python/Java/Go/Rust/C++. TypeScript is approximate. ' +
'PHP and SQL are not supported.';
export async function executeGetFrameworkAnalysis(
input: GetFrameworkAnalysisInputT,
projectPath: string,
fetcher: typeof fetch = fetch,
): Promise<CodecontextResponse> {
const args: Record<string, unknown> = {};
if (input.framework) args['framework'] = input.framework;
if (input.include_stats !== undefined) args['include_stats'] = input.include_stats;
return callCodecontext({ toolName: 'get_framework_analysis', args, projectPath }, fetcher);
}
export const getFrameworkAnalysis: ToolDef<GetFrameworkAnalysisInputT> = {
name: 'get_framework_analysis',
description: DESCRIPTION,
inputSchema: GetFrameworkAnalysisInput,
jsonSchema: {
type: 'function',
function: {
name: 'get_framework_analysis',
description: DESCRIPTION,
parameters: {
type: 'object',
properties: {
framework: {
type: 'string',
description: 'Framework name. Auto-detected if omitted.',
},
include_stats: {
type: 'boolean',
description: 'Include component/hook/service counts.',
},
},
additionalProperties: false,
},
},
},
async execute(input, projectRoot) {
return await executeGetFrameworkAnalysis(input, projectRoot);
},
};

73
apps/server/src/services/tools/codecontext/get_semantic_neighborhoods.ts Normal file
View File

@@ -0,0 +1,73 @@
// v1.12 Track B.2: codecontext wrapper — get_semantic_neighborhoods.
import { z } from 'zod';
import type { ToolDef } from '../../tools.js';
import { callCodecontext, type CodecontextResponse } from '../../codecontext_client.js';
export const GetSemanticNeighborhoodsInput = z.object({
file_path: z.string().optional(),
include_basic: z.boolean().optional(),
include_quality: z.boolean().optional(),
max_results: z.number().int().positive().optional(),
});
export type GetSemanticNeighborhoodsInputT = z.infer<typeof GetSemanticNeighborhoodsInput>;
const DESCRIPTION =
'Returns semantic neighborhoods — clusters of related files derived from git co-change patterns and import structure. ' +
'Use when you want to find code that "belongs together" with a given file without enumerating imports manually. ' +
'Tree-sitter coverage: full for JS/Python/Java/Go/Rust/C++. TypeScript is approximate. ' +
'PHP and SQL are not supported.';
const DEFAULT_MAX_RESULTS = 10;
export async function executeGetSemanticNeighborhoods(
input: GetSemanticNeighborhoodsInputT,
projectPath: string,
fetcher: typeof fetch = fetch,
): Promise<CodecontextResponse> {
const args: Record<string, unknown> = {
max_results: input.max_results ?? DEFAULT_MAX_RESULTS,
};
if (input.file_path) args['file_path'] = input.file_path;
if (input.include_basic !== undefined) args['include_basic'] = input.include_basic;
if (input.include_quality !== undefined) args['include_quality'] = input.include_quality;
return callCodecontext({ toolName: 'get_semantic_neighborhoods', args, projectPath }, fetcher);
}
export const getSemanticNeighborhoods: ToolDef<GetSemanticNeighborhoodsInputT> = {
name: 'get_semantic_neighborhoods',
description: DESCRIPTION,
inputSchema: GetSemanticNeighborhoodsInput,
jsonSchema: {
type: 'function',
function: {
name: 'get_semantic_neighborhoods',
description: DESCRIPTION,
parameters: {
type: 'object',
properties: {
file_path: {
type: 'string',
description: 'Anchor file for the neighborhood query. Omit for a project-wide view.',
},
include_basic: {
type: 'boolean',
description: 'Include the basic (import-based) neighborhood. Default true.',
},
include_quality: {
type: 'boolean',
description: 'Include code-quality metrics for the neighborhood. Default false.',
},
max_results: {
type: 'integer',
description: `Cap on neighborhoods returned. Defaults to ${DEFAULT_MAX_RESULTS}.`,
},
},
additionalProperties: false,
},
},
},
async execute(input, projectRoot) {
return await executeGetSemanticNeighborhoods(input, projectRoot);
},
};

63
apps/server/src/services/tools/codecontext/get_symbol_info.ts Normal file
View File

@@ -0,0 +1,63 @@
// v1.12 Track B.2: codecontext wrapper — get_symbol_info.
import { z } from 'zod';
import type { ToolDef } from '../../tools.js';
import { callCodecontext, type CodecontextResponse } from '../../codecontext_client.js';
export const GetSymbolInfoInput = z.object({
symbol_name: z.string().min(1),
file_path: z.string().optional(),
framework_type: z.string().optional(),
});
export type GetSymbolInfoInputT = z.infer<typeof GetSymbolInfoInput>;
const DESCRIPTION =
'Returns detailed information about a named symbol: definition location, kind (function/class/method/etc.), and (when known) framework-specific context (React component, Vue store, Angular service, …). ' +
'Tree-sitter coverage: full for JS/Python/Java/Go/Rust/C++. TypeScript symbols are approximate (uses JS grammar). ' +
'PHP and SQL are not supported — fall back to grep for those.';
export async function executeGetSymbolInfo(
input: GetSymbolInfoInputT,
projectPath: string,
fetcher: typeof fetch = fetch,
): Promise<CodecontextResponse> {
const args: Record<string, unknown> = { symbol_name: input.symbol_name };
if (input.file_path) args['file_path'] = input.file_path;
if (input.framework_type) args['framework_type'] = input.framework_type;
return callCodecontext({ toolName: 'get_symbol_info', args, projectPath }, fetcher);
}
export const getSymbolInfo: ToolDef<GetSymbolInfoInputT> = {
name: 'get_symbol_info',
description: DESCRIPTION,
inputSchema: GetSymbolInfoInput,
jsonSchema: {
type: 'function',
function: {
name: 'get_symbol_info',
description: DESCRIPTION,
parameters: {
type: 'object',
properties: {
symbol_name: {
type: 'string',
description: 'The symbol name to look up (case-sensitive).',
},
file_path: {
type: 'string',
description: 'Narrow to a specific file when the symbol name is ambiguous.',
},
framework_type: {
type: 'string',
description: 'Hint for framework-specific extraction (react|vue|svelte|django|fastapi|express|nest|…).',
},
},
required: ['symbol_name'],
additionalProperties: false,
},
},
},
async execute(input, projectRoot) {
return await executeGetSymbolInfo(input, projectRoot);
},
};

11
apps/server/src/services/tools/codecontext/index.ts Normal file
View File

@@ -0,0 +1,11 @@
// v1.12 Track B.2: codecontext tool registry. Re-exports the 8 ToolDefs so
// tools.ts can pull them in one line.
export { getCodebaseOverview } from './get_codebase_overview.js';
export { getFileAnalysis } from './get_file_analysis.js';
export { getSymbolInfo } from './get_symbol_info.js';
export { searchSymbols } from './search_symbols.js';
export { getDependencies } from './get_dependencies.js';
export { watchChanges } from './watch_changes.js';
export { getSemanticNeighborhoods } from './get_semantic_neighborhoods.js';
export { getFrameworkAnalysis } from './get_framework_analysis.js';

77
apps/server/src/services/tools/codecontext/search_symbols.ts Normal file
View File

@@ -0,0 +1,77 @@
// v1.12 Track B.2: codecontext wrapper — search_symbols.
import { z } from 'zod';
import type { ToolDef } from '../../tools.js';
import { callCodecontext, type CodecontextResponse } from '../../codecontext_client.js';
export const SearchSymbolsInput = z.object({
query: z.string().min(1),
file_type: z.string().optional(),
symbol_type: z.string().optional(),
framework_type: z.string().optional(),
limit: z.number().int().positive().optional(),
});
export type SearchSymbolsInputT = z.infer<typeof SearchSymbolsInput>;
const DESCRIPTION =
'Search for symbols (functions, classes, methods, types) across the codebase by name fragment. ' +
'Filter by file_type, symbol_type, or framework_type to narrow. ' +
'Tree-sitter coverage: full for JS/Python/Java/Go/Rust/C++. TypeScript symbols are approximate. ' +
'PHP and SQL are not supported — fall back to grep for those.';
const DEFAULT_LIMIT = 20;
export async function executeSearchSymbols(
input: SearchSymbolsInputT,
projectPath: string,
fetcher: typeof fetch = fetch,
): Promise<CodecontextResponse> {
const args: Record<string, unknown> = {
query: input.query,
limit: input.limit ?? DEFAULT_LIMIT,
};
if (input.file_type) args['file_type'] = input.file_type;
if (input.symbol_type) args['symbol_type'] = input.symbol_type;
if (input.framework_type) args['framework_type'] = input.framework_type;
return callCodecontext({ toolName: 'search_symbols', args, projectPath }, fetcher);
}
export const searchSymbols: ToolDef<SearchSymbolsInputT> = {
name: 'search_symbols',
description: DESCRIPTION,
inputSchema: SearchSymbolsInput,
jsonSchema: {
type: 'function',
function: {
name: 'search_symbols',
description: DESCRIPTION,
parameters: {
type: 'object',
properties: {
query: { type: 'string', description: 'Substring or name fragment to match.' },
file_type: {
type: 'string',
description: 'Filter by file extension or language (e.g. "ts", "py", "go").',
},
symbol_type: {
type: 'string',
description: 'Filter by kind: function|class|method|variable|type|interface.',
},
framework_type: {
type: 'string',
description: 'Filter by framework context (react|vue|svelte|…).',
},
limit: {
type: 'integer',
description: `Max matches to return. Defaults to ${DEFAULT_LIMIT}.`,
},
},
required: ['query'],
additionalProperties: false,
},
},
},
async execute(input, projectRoot) {
return await executeSearchSymbols(input, projectRoot);
},
};

57
apps/server/src/services/tools/codecontext/watch_changes.ts Normal file
View File

@@ -0,0 +1,57 @@
// v1.12 Track B.2: codecontext wrapper — watch_changes.
import { z } from 'zod';
import type { ToolDef } from '../../tools.js';
import { callCodecontext, type CodecontextResponse } from '../../codecontext_client.js';
export const WatchChangesInput = z.object({
enable: z.boolean(),
});
export type WatchChangesInputT = z.infer<typeof WatchChangesInput>;
const DESCRIPTION =
'Turn codecontext\'s file watcher on or off for this project. ' +
'When on, codecontext re-analyzes files in the background as they change (debounced). Default is on. ' +
'Disable temporarily if you\'re doing bulk edits and want to avoid analysis churn.';
export async function executeWatchChanges(
input: WatchChangesInputT,
projectPath: string,
fetcher: typeof fetch = fetch,
): Promise<CodecontextResponse> {
return callCodecontext(
{
toolName: 'watch_changes',
args: { enable: input.enable },
projectPath,
},
fetcher,
);
}
export const watchChanges: ToolDef<WatchChangesInputT> = {
name: 'watch_changes',
description: DESCRIPTION,
inputSchema: WatchChangesInput,
jsonSchema: {
type: 'function',
function: {
name: 'watch_changes',
description: DESCRIPTION,
parameters: {
type: 'object',
properties: {
enable: {
type: 'boolean',
description: 'true = enable the watcher; false = disable.',
},
},
required: ['enable'],
additionalProperties: false,
},
},
},
async execute(input, projectRoot) {
return await executeWatchChanges(input, projectRoot);
},
};

27
apps/web/src/components/ToolCallLine.tsx
View File

@@ -57,6 +57,33 @@ export function formatToolArgs(name: string, args: Record<string, unknown>): str
ARG_SUMMARY_MAX, ARG_SUMMARY_MAX,
); );
} }
// v1.12 Track B.2: codecontext tool pills. Format is "most-identifying-arg",
// matching view_file/grep precedent — surface the path/symbol/query that
// makes the call meaningful at a glance.
if (name === 'get_codebase_overview') {
return '';
}
if (name === 'get_file_analysis') {
return truncate(String(args.file_path ?? ''), ARG_SUMMARY_MAX);
}
if (name === 'get_symbol_info') {
return truncate(String(args.symbol_name ?? ''), ARG_SUMMARY_MAX);
}
if (name === 'search_symbols') {
return truncate(`"${String(args.query ?? '')}"`, ARG_SUMMARY_MAX);
}
if (name === 'get_dependencies') {
return truncate(String(args.file_path ?? '(project-wide)'), ARG_SUMMARY_MAX);
}
if (name === 'watch_changes') {
return args.enable ? 'enable' : 'disable';
}
if (name === 'get_semantic_neighborhoods') {
return truncate(String(args.file_path ?? '(project-wide)'), ARG_SUMMARY_MAX);
}
if (name === 'get_framework_analysis') {
return truncate(String(args.framework ?? '(auto-detect)'), ARG_SUMMARY_MAX);
}
// Unknown tool — surface first arg value or the literal {} so the user can // Unknown tool — surface first arg value or the literal {} so the user can
// see something happened. Forward-compatible with future tools. // see something happened. Forward-compatible with future tools.
const keys = Object.keys(args); const keys = Object.keys(args);

33
codecontext/.codecontextignore.template Normal file
View File

@@ -0,0 +1,33 @@
# .codecontextignore — paths codecontext skips during analysis
# Copy to your project root and customize. Same syntax as .gitignore.
# Dependencies / vendored code
node_modules/
vendor/
.venv/
venv/
__pycache__/
target/
# Build artifacts
dist/
build/
out/
.next/
.nuxt/
.svelte-kit/
# IDE / tooling
.opencode/
.vscode/
.idea/
# Test artifacts / coverage
coverage/
.nyc_output/
.pytest_cache/
# Lock files (rarely have meaningful symbols)
package-lock.json
yarn.lock
pnpm-lock.yaml

40
codecontext/Dockerfile Normal file
View File

@@ -0,0 +1,40 @@
# v1.12 Track B — codecontext sidecar container.
#
# Multi-stage build: golang:1.24-alpine builder produces two binaries
# (codecontext from source + our HTTP shim), then a minimal alpine:3.20
# runtime holds both.
#
# No upstream Docker image exists for codecontext. We clone the repo
# directly because the module path declared in go.mod
# (github.com/nuthan-ms/codecontext) differs from the GitHub repo URL
# (github.com/nmakod/codecontext) — `go install` against the GitHub path
# wouldn't resolve. The tagged v3.2.1 source tree is the same either way.
FROM golang:1.24-alpine AS builder
WORKDIR /build
RUN apk add --no-cache git ca-certificates build-base
# Build codecontext from the v3.2.1 tag.
# CGO is required: codecontext binds tree-sitter via cgo.
RUN git clone --depth=1 --branch v3.2.1 https://github.com/nmakod/codecontext.git /build/codecontext
WORKDIR /build/codecontext
RUN CGO_ENABLED=1 GOOS=linux go build -o /build/codecontext-bin ./cmd/codecontext
# Build the shim. Stdlib-only — no go.sum needed.
WORKDIR /build/shim
COPY go.mod ./
COPY shim.go ./
RUN CGO_ENABLED=0 GOOS=linux go build -o /build/shim-bin ./
# Runtime: alpine matches the build target so codecontext's cgo bindings
# resolve against the same musl libc.
FROM alpine:3.20
RUN apk add --no-cache ca-certificates
COPY --from=builder /build/codecontext-bin /usr/local/bin/codecontext
COPY --from=builder /build/shim-bin /usr/local/bin/shim
EXPOSE 8080
HEALTHCHECK --interval=30s --timeout=5s --start-period=30s \
CMD wget -qO- http://localhost:8080/health || exit 1
ENTRYPOINT ["/usr/local/bin/shim"]

3
codecontext/go.mod Normal file
View File

@@ -0,0 +1,3 @@
module github.com/indifferentketchup/boocode-codecontext-shim
go 1.24

442
codecontext/shim.go Normal file
View File

@@ -0,0 +1,442 @@
// boocode-codecontext-shim — wraps codecontext's stdio MCP server with an
// HTTP/JSON facade so the BooCode Node server can call codecontext over the
// container network instead of speaking MCP directly. One process per
// container, holds a single codecontext child via os/exec; concurrent HTTP
// requests are serialized onto the child because codecontext's internal
// CodeContextMCPServer.graph swaps per target_dir (see recon report
// 2026-05-21).
//
// MCP framing is newline-delimited JSON (NDJSON), not LSP-style
// Content-Length — per the MCP stdio transport spec:
// https://spec.modelcontextprotocol.io/specification/server/transports
//
// No third-party deps. Stdlib only.
package main
import (
"bufio"
"context"
"encoding/json"
"errors"
"fmt"
"io"
"log"
"net/http"
"os"
"os/exec"
"os/signal"
"sync"
"sync/atomic"
"syscall"
"time"
)
// ---- JSON-RPC types ----
// rpcMessage is shared by request, response, and notification. Notifications
// omit ID; requests omit Result/Error; responses omit Method/Params. omitempty
// + the zero int 0 sentinel works for ID because we never SEND id=0
// (nextID starts at 0 and atomic.AddInt32 returns 1 on the first call).
type rpcMessage struct {
JSONRPC string `json:"jsonrpc"`
ID int `json:"id,omitempty"`
Method string `json:"method,omitempty"`
Params json.RawMessage `json:"params,omitempty"`
Result json.RawMessage `json:"result,omitempty"`
Error *rpcError `json:"error,omitempty"`
}
type rpcError struct {
Code int `json:"code"`
Message string `json:"message"`
}
// callToolResult is the MCP tools/call response shape. codecontext returns
// markdown wrapped in a TextContent entry.
type callToolResult struct {
Content []struct {
Type string `json:"type"`
Text string `json:"text"`
} `json:"content"`
IsError bool `json:"isError,omitempty"`
}
// ---- Globals ----
var (
child *exec.Cmd
childStdin io.WriteCloser
childStdout *bufio.Reader
// Serialize tools/call so codecontext's per-call graph rebuild doesn't
// race itself when concurrent HTTP requests target different projects.
// Initialize/notifications/initialized run before HTTP starts so they
// don't need this lock.
callMu sync.Mutex
pendingMu sync.Mutex
pending = make(map[int]chan *rpcMessage)
nextID int32
)
// ---- MCP framing (NDJSON) ----
func writeMessage(w io.Writer, msg *rpcMessage) error {
body, err := json.Marshal(msg)
if err != nil {
return err
}
// Single write keeps the message atomic across concurrent writers.
// (We don't actually have concurrent writers here — callMu serializes —
// but the +'\n' append needs to be in one syscall regardless.)
_, err = w.Write(append(body, '\n'))
return err
}
func readerLoop(r *bufio.Reader) {
for {
line, err := r.ReadBytes('\n')
if err != nil {
if errors.Is(err, io.EOF) {
log.Printf("reader: EOF (child closed stdout)")
} else {
log.Printf("reader: %v", err)
}
return
}
var msg rpcMessage
if err := json.Unmarshal(line, &msg); err != nil {
log.Printf("reader: malformed JSON: %v (line=%q)", err, line)
continue
}
if msg.ID == 0 {
// Server-initiated notification or progress update; nothing to
// dispatch. codecontext doesn't currently send these but the
// MCP spec allows them.
continue
}
pendingMu.Lock()
ch, ok := pending[msg.ID]
if ok {
delete(pending, msg.ID)
}
pendingMu.Unlock()
if ok {
ch <- &msg
}
}
}
func call(ctx context.Context, method string, params any) (*rpcMessage, error) {
id := int(atomic.AddInt32(&nextID, 1))
ch := make(chan *rpcMessage, 1)
pendingMu.Lock()
pending[id] = ch
pendingMu.Unlock()
paramsJSON, err := json.Marshal(params)
if err != nil {
pendingMu.Lock()
delete(pending, id)
pendingMu.Unlock()
return nil, err
}
msg := &rpcMessage{
JSONRPC: "2.0",
ID: id,
Method: method,
Params: paramsJSON,
}
if err := writeMessage(childStdin, msg); err != nil {
pendingMu.Lock()
delete(pending, id)
pendingMu.Unlock()
return nil, fmt.Errorf("write: %w", err)
}
select {
case resp := <-ch:
return resp, nil
case <-ctx.Done():
pendingMu.Lock()
delete(pending, id)
pendingMu.Unlock()
return nil, ctx.Err()
}
}
func notify(method string, params any) error {
paramsJSON, err := json.Marshal(params)
if err != nil {
return err
}
msg := &rpcMessage{
JSONRPC: "2.0",
Method: method,
Params: paramsJSON,
}
return writeMessage(childStdin, msg)
}
// ---- Child lifecycle ----
func startChild() error {
// `codecontext mcp` with --watch=true (the default) keeps fsnotify
// running on the indexed directory; the per-call target_dir swap
// invalidates and re-indexes on demand. `--target=/opt/projects` is the
// initial scan target — codecontext rebuilds the graph against whatever
// target_dir each call carries, so this is just a valid bootstrap path
// (the default "." is the alpine root and trips on transient /proc fds).
child = exec.Command("codecontext", "mcp", "--target=/opt/projects", "--watch=true")
var err error
childStdin, err = child.StdinPipe()
if err != nil {
return fmt.Errorf("stdin pipe: %w", err)
}
stdout, err := child.StdoutPipe()
if err != nil {
return fmt.Errorf("stdout pipe: %w", err)
}
childStdout = bufio.NewReader(stdout)
// codecontext's own log.SetOutput(os.Stderr) keeps its diagnostic noise
// off the JSON-RPC channel; we just pass-through to our own stderr.
child.Stderr = os.Stderr
if err := child.Start(); err != nil {
return fmt.Errorf("start: %w", err)
}
log.Printf("started codecontext pid=%d", child.Process.Pid)
go readerLoop(childStdout)
// Supervise the child. When codecontext exits (crash, OOM, externally
// pkill'd), child.Wait() returns and we tear the shim down so the
// container's `restart: unless-stopped` policy recreates us with a
// fresh child. Without this goroutine the dead child becomes a zombie
// (Signal(0) on a zombie returns nil, so the health endpoint would lie)
// and HTTP requests would queue forever waiting on responses that will
// never come. Discovered during B.1 kill-restart testing.
go func() {
err := child.Wait()
log.Printf("codecontext exited: %v — shim shutting down", err)
os.Exit(1)
}()
return nil
}
func killChild() {
if child == nil || child.Process == nil {
return
}
log.Printf("killing codecontext pid=%d", child.Process.Pid)
_ = child.Process.Signal(syscall.SIGTERM)
done := make(chan error, 1)
go func() { done <- child.Wait() }()
select {
case <-done:
log.Printf("codecontext exited")
case <-time.After(5 * time.Second):
log.Printf("codecontext did not exit on SIGTERM; sending SIGKILL")
_ = child.Process.Kill()
<-done
}
}
// MCP handshake: client sends initialize, server replies, client follows
// with the notifications/initialized notification. After that, tools/call
// is accepted.
func initializeMCP(ctx context.Context) error {
initParams := map[string]any{
"protocolVersion": "2024-11-05",
"capabilities": map[string]any{},
"clientInfo": map[string]any{
"name": "boocode-codecontext-shim",
"version": "0.1.0",
},
}
resp, err := call(ctx, "initialize", initParams)
if err != nil {
return fmt.Errorf("initialize: %w", err)
}
if resp.Error != nil {
return fmt.Errorf("initialize error %d: %s", resp.Error.Code, resp.Error.Message)
}
if err := notify("notifications/initialized", map[string]any{}); err != nil {
return fmt.Errorf("notifications/initialized: %w", err)
}
log.Printf("MCP handshake complete (server result=%s)", string(resp.Result))
return nil
}
// ---- HTTP ----
func writeJSON(w http.ResponseWriter, status int, body any) {
w.Header().Set("Content-Type", "application/json")
w.WriteHeader(status)
_ = json.NewEncoder(w).Encode(body)
}
func handleHealth(w http.ResponseWriter, r *http.Request) {
if child == nil || child.Process == nil {
http.Error(w, "no child", http.StatusServiceUnavailable)
return
}
// Signal 0 doesn't actually deliver — it just returns an error if the
// process is gone. Cheaper than parsing /proc.
if err := child.Process.Signal(syscall.Signal(0)); err != nil {
http.Error(w, "child dead: "+err.Error(), http.StatusServiceUnavailable)
return
}
_, _ = io.WriteString(w, "ok")
}
func makeToolHandler(toolName string) http.HandlerFunc {
return func(w http.ResponseWriter, r *http.Request) {
start := time.Now()
targetDir := "-"
status := "ok"
defer func() {
log.Printf("%s target_dir=%q duration_ms=%d status=%s",
toolName, targetDir, time.Since(start).Milliseconds(), status)
}()
var args json.RawMessage
if err := json.NewDecoder(r.Body).Decode(&args); err != nil {
status = "bad_request"
writeJSON(w, http.StatusBadRequest, map[string]any{
"result": nil,
"error": "invalid JSON body: " + err.Error(),
})
return
}
// Sniff target_dir purely for the access log; pass args through opaque.
var argsMap map[string]any
if json.Unmarshal(args, &argsMap) == nil {
if td, ok := argsMap["target_dir"].(string); ok {
targetDir = td
}
}
ctx, cancel := context.WithTimeout(r.Context(), 60*time.Second)
defer cancel()
callMu.Lock()
resp, err := call(ctx, "tools/call", map[string]any{
"name": toolName,
"arguments": args,
})
callMu.Unlock()
if err != nil {
status = "rpc_error"
writeJSON(w, http.StatusBadGateway, map[string]any{
"result": nil,
"error": err.Error(),
})
return
}
if resp.Error != nil {
status = "mcp_error"
writeJSON(w, http.StatusOK, map[string]any{
"result": nil,
"error": resp.Error.Message,
})
return
}
var ctr callToolResult
if err := json.Unmarshal(resp.Result, &ctr); err != nil {
status = "parse_error"
writeJSON(w, http.StatusOK, map[string]any{
"result": nil,
"error": "parse result: " + err.Error(),
})
return
}
// codecontext only emits text content. Concatenate (single-entry in
// practice, but the schema allows multiple).
var buf []byte
for _, c := range ctr.Content {
if c.Type == "text" {
buf = append(buf, c.Text...)
}
}
text := string(buf)
if ctr.IsError {
status = "tool_error"
writeJSON(w, http.StatusOK, map[string]any{
"result": nil,
"error": text,
})
return
}
writeJSON(w, http.StatusOK, map[string]any{
"result": text,
"error": nil,
})
}
}
// ---- main ----
func main() {
log.SetOutput(os.Stderr)
log.SetFlags(log.LstdFlags | log.Lmicroseconds)
log.Println("boocode-codecontext-shim starting")
if err := startChild(); err != nil {
log.Fatalf("startChild: %v", err)
}
initCtx, initCancel := context.WithTimeout(context.Background(), 30*time.Second)
if err := initializeMCP(initCtx); err != nil {
initCancel()
killChild()
log.Fatalf("initializeMCP: %v", err)
}
initCancel()
sigChan := make(chan os.Signal, 1)
signal.Notify(sigChan, syscall.SIGTERM, syscall.SIGINT)
mux := http.NewServeMux()
// Go 1.22+ method-prefix routing. Any non-listed method → 405 automatically.
mux.HandleFunc("GET /health", handleHealth)
mux.HandleFunc("POST /v1/get_codebase_overview", makeToolHandler("get_codebase_overview"))
mux.HandleFunc("POST /v1/get_file_analysis", makeToolHandler("get_file_analysis"))
mux.HandleFunc("POST /v1/get_symbol_info", makeToolHandler("get_symbol_info"))
mux.HandleFunc("POST /v1/search_symbols", makeToolHandler("search_symbols"))
mux.HandleFunc("POST /v1/get_dependencies", makeToolHandler("get_dependencies"))
mux.HandleFunc("POST /v1/watch_changes", makeToolHandler("watch_changes"))
mux.HandleFunc("POST /v1/get_semantic_neighborhoods", makeToolHandler("get_semantic_neighborhoods"))
mux.HandleFunc("POST /v1/get_framework_analysis", makeToolHandler("get_framework_analysis"))
server := &http.Server{
Addr: ":8080",
Handler: mux,
ReadHeaderTimeout: 5 * time.Second,
}
go func() {
log.Println("listening on :8080")
if err := server.ListenAndServe(); err != nil && !errors.Is(err, http.ErrServerClosed) {
log.Fatalf("ListenAndServe: %v", err)
}
}()
<-sigChan
log.Println("shutdown signal received")
shutdownCtx, shutdownCancel := context.WithTimeout(context.Background(), 10*time.Second)
_ = server.Shutdown(shutdownCtx)
shutdownCancel()
killChild()
log.Println("exit")
}

28
docker-compose.yml
View File

@@ -7,6 +7,7 @@ services:
- "100.114.205.53:9500:3000" - "100.114.205.53:9500:3000"
env_file: .env env_file: .env
environment: environment:
CODECONTEXT_URL: http://codecontext:8080
CONTAINER_GUIDANCE_FILE: /app/BOOCHAT.md CONTAINER_GUIDANCE_FILE: /app/BOOCHAT.md
DATABASE_URL: postgres://boocode:${POSTGRES_PASSWORD}@boocode_db:5432/boocode DATABASE_URL: postgres://boocode:${POSTGRES_PASSWORD}@boocode_db:5432/boocode
volumes: volumes:
@@ -60,6 +61,33 @@ services:
networks: networks:
- boocode_net - boocode_net
# v1.12 Track B: codecontext sidecar. Stdio MCP server wrapped by a small
# HTTP shim (see ./codecontext/). No host port — reached from boocode at
# http://codecontext:8080 over the boocode_net bridge.
#
# Mounts /opt:/opt:ro (not just /opt/projects:ro): BooCode projects live
# at /opt/<slug> on the host, not exclusively under /opt/projects. The
# mount must cover anywhere a project.path could resolve to. Read-only
# because codecontext only analyzes — never writes. The model can't
# arbitrarily set target_dir to a sensitive subtree because the B.2
# wrappers validate target_dir against project.path before calling the
# shim, and the shim isn't reachable from outside boocode_net.
codecontext:
build:
context: ./codecontext
container_name: boocode_codecontext
restart: unless-stopped
networks:
- boocode_net
volumes:
- /opt:/opt:ro
healthcheck:
test: ["CMD-SHELL", "wget -qO- http://localhost:8080/health || exit 1"]
interval: 30s
timeout: 5s
retries: 3
start_period: 30s
volumes: volumes:
boocode_pgdata: boocode_pgdata: