Commit Graph

529 Commits

Author SHA1 Message Date
0xbyt4
dfd50ceccd fix: preserve Gemini thought_signature in tool call messages
Gemini 3 thinking models attach extra_content with thought_signature
to function call responses. This must be echoed back on subsequent
API calls or the server rejects with a 400 error. The assistant
message builder was dropping this field, causing all Gemini 3 Flash/Pro
tool-calling flows to fail after the first function call.
2026-02-28 18:10:05 +03:00
0xbyt4
2390728cc3 fix: resolve 4 bugs found in HA integration code review
- Auto-authorize HA events in gateway (system-generated, not user messages)
- Guard _read_events against None/closed WebSocket after failed reconnect
- Use UUID for send() message_id instead of polluting WS sequence counter
- entity_id parameter now takes precedence over data["entity_id"]
2026-02-28 15:12:18 +03:00
0xbyt4
b32c642af3 test: add HA integration tests with fake in-process server
Fake HA server (aiohttp.web) simulates full API surface over real TCP:
- WebSocket auth handshake + event push
- REST endpoints (states, services, notifications)

14 integration tests verify end-to-end flows without mocks:
- WS connect/auth/subscribe/event-forwarding/disconnect
- REST list/get/call-service against fake server
- send() notification delivery and auth failure
- 401/500 error handling
2026-02-28 14:28:04 +03:00
0xbyt4
c36b256de5 feat: add Home Assistant integration (REST tools + WebSocket gateway)
- Add ha_list_entities, ha_get_state, ha_call_service tools via REST API
- Add WebSocket gateway adapter for real-time state_changed event monitoring
- Support domain/entity filtering, cooldown, and auto-reconnect with backoff
- Use REST API for outbound notifications to avoid WS race condition
- Gate tool availability on HASS_TOKEN env var
- Add 82 unit tests covering real logic (filtering, payload building, event pipeline)
2026-02-28 13:32:48 +03:00
teknium1
de5a88bd97 refactor: migrate tool progress configuration from environment variables to config.yaml 2026-02-28 00:05:58 -08:00
teknium1
0862fa96fd refactor(domain-intel): streamline documentation and add CLI tool for domain intelligence operations 2026-02-27 23:53:24 -08:00
Teknium
924570c5be Merge pull request #136 from FurkanL0/feat/domain-intel-skill
feat(skills): add passive domain intelligence skill — subdomains, SSL, WHOIS, DNS, availability
2026-02-27 23:47:50 -08:00
teknium1
4d8689c10c feat: add honcho-ai package to dependencies and update extras in uv.lock 2026-02-27 23:45:52 -08:00
teknium1
1d7ce5e063 feat: integrate honcho-ai package and enhance tool progress callback in delegate_tool 2026-02-27 23:45:52 -08:00
Teknium
72d3425eef Merge pull request #94 from cesareth/feat/verbose-slash-command
feat(cli): add /verbose slash command to toggle debug output at runtime
2026-02-27 23:41:25 -08:00
teknium1
b7f099beed feat: add Honcho integration for cross-session user modeling 2026-02-27 23:41:08 -08:00
Teknium
912ef50165 Merge pull request #38 from plastic-labs/feat/honcho-integration
feat: Honcho memory integration (opt-in)
2026-02-27 23:35:29 -08:00
Teknium
4a9086b848 Merge branch 'main' into feat/honcho-integration 2026-02-27 23:32:49 -08:00
teknium1
50cb4d5fc7 fix(agent): update error message for unsupported Anthropic API endpoints to clarify usage of OpenRouter 2026-02-27 23:23:31 -08:00
Teknium
2bc9508b7c Merge pull request #173 from adavyas/fix/anthropic-base-url-guard
fix(agent): fail fast on Anthropic native base URLs
2026-02-27 23:22:01 -08:00
Teknium
337cd574c8 Merge pull request #167 from Jr-kenny/pr/docs-codefences
fix(docs): add missing code block language specifiers
2026-02-27 23:16:27 -08:00
Teknium
9fb027915e Merge pull request #166 from Jr-kenny/pr/docs-config
fix(docs): correct CLI config precedence and paths
2026-02-27 23:15:36 -08:00
Teknium
2b821c3a14 Merge pull request #162 from aydnOktay/fix/memory-tool-entry-delimiter-parsing
Fix memory tool entry parsing when content contains section sign
2026-02-27 23:13:15 -08:00
Teknium
0d113fab1a Merge pull request #158 from Indelwin/feature/docker-volumes
feat: add docker_volumes config for custom volume mounts
2026-02-27 23:06:06 -08:00
teknium1
19f28a633a fix(agent): enhance 413 error handling and improve conversation history management in tests 2026-02-27 23:04:32 -08:00
Teknium
2c817ce4a5 Merge pull request #153 from tekelala/main
fix(agent): handle 413 payload-too-large via compression instead of aborting
2026-02-27 22:57:55 -08:00
teknium1
66a5bc64db fix(process): use shlex to safely quote commands in bg_command for improved security 2026-02-27 22:50:26 -08:00
Teknium
7f423508e4 Merge pull request #151 from johnh4098/fix/shell-injection-spawn-via-env-v2
fix(process): escape single quotes in spawn_via_env bg_command
2026-02-27 22:49:04 -08:00
Teknium
306c6706a6 Merge pull request #150 from VencentSoliman/fix/gateway-model-personality-commands
fix(gateway): sync /model and /personality with CLI pattern
2026-02-27 22:48:03 -08:00
Teknium
64be67e062 Merge pull request #146 from alireza78a/fix/atomic-cron-job-save
fix(cron): use atomic write in save_jobs to prevent data loss
2026-02-27 22:16:43 -08:00
adavyas
0c0a2eb0a2 fix(agent): fail fast on Anthropic native base URLs 2026-02-27 21:19:29 -08:00
teknium1
de0829cec3 fix(cli): increase max iterations for child agents and extend API call timeout for improved reliability 2026-02-27 17:35:29 -08:00
Teknium
20177660bb Merge pull request #142 from Bartok9/docs/add-slash-commands-reference
docs: add slash commands reference
2026-02-27 17:33:19 -08:00
Jr-kenny
609fc6d080 fix(docs): add missing code block language specifiers 2026-02-28 02:04:38 +01:00
Jr-kenny
518826e70c fix(docs): standardize terminology and CLI formatting 2026-02-28 02:03:39 +01:00
Jr-kenny
13992a58da fix(docs): correct CLI config precedence and paths 2026-02-28 02:00:32 +01:00
Teknium
0d2ac1c07f Merge pull request #121 from Bartok9/test-clarify-tool
test(tools): add unit tests for clarify_tool.py
2026-02-27 16:27:37 -08:00
teknium1
fb7df099e0 feat(cli): add shell noise filtering and improve command execution with interactive login shell 2026-02-27 16:26:47 -08:00
teknium1
f14ff3e041 feat(cli): use user's login shell for command execution to ensure environment consistency 2026-02-27 15:10:27 -08:00
VencentSoliman
07fcb94bc0 fix(gateway): sync /model and /personality with CLI config.yaml pattern 2026-02-27 17:39:25 -05:00
aydnOktay
66d9983d46 Fix memory tool entry parsing when content contains section sign
- Use ENTRY_DELIMITER (\\n§\\n) instead of '§' when splitting entries in _read_file
- Prevents incorrect parsing when memory entries contain '§' character
- Aligns read logic with write logic for consistency
2026-02-28 01:33:41 +03:00
teknium1
4f3cb98e5e feat(cli): implement platform-specific toolset selection with improved user interface 2026-02-27 14:26:23 -08:00
teknium1
8c1f5efcab feat(cli): add toolset API key validation and improve checklist display 2026-02-27 13:56:43 -08:00
teknium1
c92bdd8785 fix(cli): improve spinner line clearing to prevent garbled output with prompt_toolkit 2026-02-27 13:49:06 -08:00
teknium1
e09ef6b8bc feat(gateway): improve model command handling by resolving current model from environment and config file 2026-02-27 13:42:07 -08:00
Gesina Sands
f7677ed275 feat: add docker_volumes config for custom volume mounts 2026-02-28 07:12:48 +10:00
johnh4098
e5f719a33b fix(process): escape single quotes in spawn_via_env bg_command 2026-02-27 21:03:17 +03:30
tekelala
79bd65034c fix(agent): handle 413 payload-too-large via compression instead of aborting
The 413 "Request Entity Too Large" error from the LLM API was caught by the
generic 4xx handler which aborts immediately. This is wrong for 413 — it's a
payload-size issue that can be resolved by compressing conversation history.

- Intercept 413 before the generic 4xx block and route to _compress_context
- Exclude 413 from generic is_client_error detection
- Add 'request entity too large' to context-length phrases as safety net
- Add tests for 413 compression behavior

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-27 12:21:27 -05:00
tekelala
fbb1923fad fix(security): patch path traversal, size bypass, and prompt injection in document processing
- Sanitize filenames in cache_document_from_bytes to prevent path traversal (strip directory components, null bytes, resolve check)
- Reject documents with None file_size instead of silently allowing download
- Cap text file injection at 100 KB to prevent oversized prompt payloads
- Sanitize display_name in run.py context notes to block prompt injection via filenames
- Add 35 unit tests covering document cache utilities and Telegram document handling

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-27 11:53:46 -05:00
alireza78a
bf75c450b7 fix(cron): use atomic write in save_jobs to prevent data loss 2026-02-27 20:16:49 +03:30
tekelala
b2172c4b2e feat(telegram): add document file processing for PDF, text, and Office files
Download, cache, and enrich document files sent via Telegram. Supports
.pdf, .md, .txt, .docx, .xlsx, .pptx with size validation, unsupported
type rejection, text content injection for .md/.txt, and hourly cache
cleanup.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-27 11:44:57 -05:00
Bartok Moltbot
69ccd76679 docs: add slash commands reference
Adds a comprehensive reference for all CLI slash commands including:
- Navigation & control commands
- Tools & configuration commands
- Conversation management
- Advanced features (cron, skills, platforms)
- Usage examples
- Tips for users

Makes it easier for new users to discover available commands.
2026-02-27 10:50:53 -05:00
teknium1
8b54bb4d89 docs: update CONTRIBUTING.md to enhance contribution guidelines and clarify priorities 2026-02-27 06:37:36 -08:00
FurkanL0
f9e05218ca Create SKILL.md 2026-02-27 17:07:13 +03:00
FurkanL0
2ddda5da89 Create DESCRIPTION.md 2026-02-27 17:06:17 +03:00