feat: add retry logic for transient failures

- @with_retry decorator and retry_async() function
- Exponential backoff with jitter
- Retries on: timeout, connection errors, HTTP 429/5xx
- Web search tool now retries on network failures
- Configurable via RETRY_MAX_ATTEMPTS, RETRY_BASE_DELAY, RETRY_MAX_DELAY
- 29 new tests (205 total passing)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

webber-api/docs/COVERAGE.md

@@ -126,7 +126,7 @@ Last updated: 2026-01-11
 | **Todo tracking** | CLI | Built-in task list (`/todo`) | Medium |
 | **Git integration** | CLI | Auto-commit, branch management | Medium |
 | **Agent handoff** | Orchestration | Explore → Plan → Task workflow | High |
-| **Retry logic** | Infrastructure | Auto-retry on tool failures | Low |
+| ~~**Retry logic**~~ | Infrastructure | ✅ Auto-retry with exponential backoff | Low |
 
 ### Low Priority
 
@@ -151,11 +151,12 @@ Last updated: 2026-01-11
 | Task agent tests | 15 | 15 | ✅ |
 | Conversation tests | 19 | 19 | ✅ |
 | Token tests | 6 | 6 | ✅ |
+| Retry tests | 29 | 29 | ✅ |
 | Security tests | 14 | 14 | ✅ |
 | Integration tests | 10 | 10 | ✅ Agent + real LLM |
 | E2E tests | 12 | 12 | ✅ Full API workflow |
 
-**Total: 176 tests passing**
+**Total: 205 tests passing**
 
 **Test breakdown:**
 - Read/Glob/Grep tools: 17 tests
@@ -168,6 +169,7 @@ Last updated: 2026-01-11
 - Task agent: 15 tests
 - Conversations: 19 tests
 - Tokens: 6 tests
+- Retry: 29 tests
 - Security: 14 tests
 - Health checks: 2 tests
 - Integration (LLM): 10 tests

webber-api/docs/architecture.md

@@ -217,6 +217,9 @@ All settings via environment variables or `.env`:
 | SUMMARIZATION_THRESHOLD | 0.8 | Summarize at N% of max tokens |
 | SUMMARIZATION_TARGET_TOKENS | 500 | Target summary size |
 | KEEP_RECENT_MESSAGES | 6 | Messages to keep unsummarized |
+| RETRY_MAX_ATTEMPTS | 3 | Max retry attempts for transient failures |
+| RETRY_BASE_DELAY | 1.0 | Base delay between retries (seconds) |
+| RETRY_MAX_DELAY | 30.0 | Maximum delay between retries (seconds) |
 
 ---