Commit Graph
15 Commits
Author SHA1 Message Date
Muhammed Mukhthar CM de5b75eff6 fix(tools): resolve Read/Write/Edit paths against workspace directory
Previously, Read/Write/Edit tools used the global tool instances from
pi-coding-agent which had process.cwd() baked in at import time. Since
the gateway starts from /root/dev/ai/clawdbot, relative paths like
'SOUL.md' would incorrectly resolve there instead of the agent's
workspace (/root/clawd).

This fix:
- Adds workspaceDir option to createClawdbotCodingTools
- Creates fresh Read/Write/Edit tools bound to workspaceDir
- Adds cwd option to Bash tool defaults for consistency
- Passes effectiveWorkspace from pi-embedded-runner

Absolute paths and ~/... paths are unaffected. Sandboxed sessions
continue to use sandbox root as before.

Includes tests for Read/Write/Edit workspace path resolution.
2026-01-10 17:08:56 +01:00
Muhammed Mukhthar CM d0450bb425 fix(antigravity): add fail-fast on 429 rate limit
When Antigravity returns 429, throw immediately instead of waiting for the
server-provided retry delay (which can be 10+ minutes). This lets clawdbot
quickly rotate to another account.

This patch was previously in PR #454 but was accidentally removed in 0dbb569
when bumping to pi-ai 0.40.0. The upstream release did NOT include this fix.

Context: Antigravity rate limits cause pi-ai to sleep for the full retry
delay inside the request, blocking the thread. Clawdbot's timeout would
eventually fire, but waiting 10+ minutes is unacceptable UX.

Bundled with the empty error message filter since both handle 429 recovery.
2026-01-09 18:10:23 +01:00
Muhammed Mukhthar CM 1cfe409a09 fix: filter empty error messages to prevent session corruption
When 429/500 errors occur during tool execution, empty assistant messages
with stopReason='error' and content=[] get persisted to the session file.

These break the tool_use -> tool_result chain that Claude/Gemini require:
- Claude expects every tool_use block to have a matching tool_result
- Empty error messages inserted mid-sequence violate this invariant
- Results in: 'tool_use ids were found without tool_result blocks'

This patch filters out empty error messages when building session context,
allowing sessions to recover gracefully from transient API errors.

Evidence from production:
- 113 of 170 sessions had empty error messages
- Session 30764430 demonstrated recovery: 429 at 14:30:11 IST,
  resumed successfully at 14:30:22, completed at 14:30:34

Sorry Peter, one more patch! 🙈
2026-01-09 18:10:23 +01:00
mukhtharcm 80ca04af01 fix(antigravity): add CLIProxyAPI v6.6.89 compatibility to fix 429 errors
Port Antigravity payload enhancements from CLIProxyAPI v6.6.89:
- Add ANTIGRAVITY_SYSTEM_INSTRUCTION with agent identity/guidelines
- Inject systemInstruction with role 'user' for Antigravity requests
- Add requestType: 'agent' to wrapped request body
- Update userAgent to 'antigravity' for Antigravity requests

This fixes RESOURCE_EXHAUSTED (429) errors when using Antigravity.

Adapted from: https://github.com/NoeFabris/opencode-antigravity-auth/pull/137
Reference: https://github.com/router-for-me/CLIProxyAPI/commit/67985d8
2026-01-08 05:33:50 +00:00
Muhammed Mukhthar CM ee99311130 test(telegram): mock grammyjs/runner for fast tests 2026-01-07 22:08:20 +01:00
Muhammed Mukhthar CM 1a41fecf67 feat(telegram): use grammyjs/runner for concurrent update processing
Previously, grammY's default bot.start() processed updates sequentially,
blocking all Telegram messages while one was being handled. This made
maxConcurrent settings ineffective for Telegram.

Now uses @grammyjs/runner which processes updates concurrently, matching
the behavior of Discord (Promise.all) and WhatsApp (fire-and-forget).

Benefits:
- Ack reactions (👀) appear immediately, not after queue clears
- Multiple chats can be processed in parallel
- maxConcurrent setting now works correctly for Telegram
- Long-running tool calls no longer block other conversations
2026-01-07 22:08:20 +01:00
Muhammed Mukhthar CM eb5f758f6b fix(auth): improve multi-account round-robin rotation and 429 handling
This commit fixes several issues with multi-account OAuth rotation that
were causing slow responses and inefficient account cycling.

## Changes

### 1. Fix usageStats race condition (auth-profiles.ts)

The `markAuthProfileUsed`, `markAuthProfileCooldown`, `markAuthProfileGood`,
and `clearAuthProfileCooldown` functions were using a stale in-memory store
passed as a parameter. Long-running sessions would overwrite usageStats
updates from concurrent sessions when saving.

**Fix:** Re-read the store from disk before each update to get fresh
usageStats from other sessions, then merge the update.

### 2. Capture AbortError from waitForCompactionRetry (pi-embedded-runner.ts)

When a request timed out, `session.abort()` was called which throws an
`AbortError`. The code structure was:

```javascript
try {
  await session.prompt(params.prompt);
} catch (err) {
  promptError = err;  // Catches AbortError here
}
await waitForCompactionRetry();  // But THIS also throws AbortError!
```

The second `AbortError` from `waitForCompactionRetry()` escaped and
bypassed the rotation/fallback logic entirely.

**Fix:** Wrap `waitForCompactionRetry()` in its own try/catch to capture
the error as `promptError`, enabling proper timeout handling.

Root cause analysis and fix proposed by @erikpr1994 in #313.

Fixes #313

### 3. Fail fast on 429 rate limits (pi-ai patch)

The pi-ai library was retrying 429 errors up to 3 times with exponential
backoff before throwing. This meant a rate-limited account would waste
30+ seconds retrying before our rotation code could try the next account.

**Fix:** Patch google-gemini-cli.js to:
- Throw immediately on first 429 (no retries)
- Not catch and retry 429 errors in the network error handler

This allows the caller to rotate to the next account instantly on rate limit.

Note: We submitted this fix upstream (https://github.com/badlogic/pi-mono/pull/504)
but it was closed without merging. Keeping as a local patch for now.

## Testing

With 6 Antigravity accounts configured:
- Accounts rotate properly based on lastUsed (round-robin)
- 429s trigger immediate rotation to next account
- usageStats persist correctly across concurrent sessions
- Cooldown tracking works as expected

## Before/After

**Before:** Multiple 429 retries on same account, 30-90s delays
**After:** Instant rotation on 429, responses in seconds
2026-01-07 00:56:32 +01:00
Muhammed Mukhthar CM 18c7795ee0 feat: treat timeout as rate limit for profile rotation
Antigravity rate limits cause requests to hang indefinitely rather than
returning 429 errors. This change detects timeouts and treats them as
potential rate limits:

- Added timedOut flag to track timeout-triggered aborts
- Timeout now triggers profile cooldown + rotation
- Logs: "Profile X timed out (possible rate limit). Trying next account..."

This ensures automatic failover when Antigravity hangs due to rate limiting.
2026-01-06 05:20:01 +00:00
Muhammed Mukhthar CM ce6c7737c1 feat: add round-robin rotation and cooldown for auth profiles
Adds usage tracking to auth profiles for automatic rotation:

- ProfileUsageStats type with lastUsed, cooldownUntil, errorCount
- markAuthProfileUsed(): tracks successful usage, resets errors
- markAuthProfileCooldown(): applies exponential backoff (1/5/25/60min)
- isProfileInCooldown(): checks if profile should be skipped
- orderProfilesByMode(): now sorts by lastUsed (oldest first)

On auth/rate-limit failures, profiles are marked for cooldown before
rotation. On success, usage is recorded for round-robin ordering.

This enables automatic load distribution across multiple accounts
(e.g., Antigravity 5-hour rate limit windows).
2026-01-06 05:17:59 +00:00
Muhammed Mukhthar CM 06df6a955a feat: use email-based profile IDs for OAuth providers
Changes writeOAuthCredentials and applyAuthProfileConfig calls to use
the email from OAuth response as part of the profile ID instead of
hardcoded ":default".

This enables multiple accounts per provider - each login creates a
separate profile (e.g., google-antigravity:user@gmail.com) instead
of overwriting the same :default profile.

Affected files:
- src/commands/onboard-auth.ts (generic writeOAuthCredentials)
- src/commands/configure.ts (Antigravity flow)
- src/wizard/onboarding.ts (Antigravity flow)
2026-01-06 05:17:59 +00:00
Muhammed Mukhthar CM 4d42811ecf fix(telegram): add textLimit to block reply chunking
Block streaming replies were missing the textLimit parameter in
deliverReplies(), causing long messages to fail with 'message is too
long' error instead of being chunked properly.

The final reply path already included textLimit, but the onBlockReply
callback path did not.
2026-01-03 11:12:15 +01:00
mukhtharcm 82ad7e29a6 fix: reject antigravity auth in non-interactive onboarding mode 2026-01-03 05:01:42 +01:00
mukhtharcm 2290a3c8af feat: add VPS-aware Antigravity OAuth with manual URL paste fallback
Detects SSH/VPS/headless environments and prompts user to paste
the OAuth callback URL instead of relying on localhost server.

- Add antigravity-oauth.ts with VPS detection and manual OAuth flow
- Update onboard-interactive.ts to use VPS-aware flow
- Update configure.ts to use VPS-aware flow
2026-01-03 05:01:42 +01:00
mukhtharcm d216cebff5 fix: use claude-opus-4-5-thinking as default antigravity model 2026-01-03 05:01:42 +01:00
mukhtharcm 05bd345828 feat: add Google Antigravity authentication support
- Add 'antigravity' as new auth choice in onboard and configure wizards
- Implement Google Antigravity OAuth flow using loginAntigravity from pi-ai
- Update writeOAuthCredentials to accept any OAuthProvider (not just 'anthropic')
- Add schema sanitization for Google Cloud Code Assist API to fix tool call errors
- Default model set to google-antigravity/claude-opus-4-5 after successful auth

The schema sanitization removes unsupported JSON Schema keywords (patternProperties,
const, anyOf, etc.) that Google's Cloud Code Assist API doesn't understand.
2026-01-03 05:01:42 +01:00