- #962: WebSocket auth now URL-decodes token before comparison. API keys with +/=/
characters (base64-derived) now work correctly for WS streaming.
- #939: Clippy bool_comparison lint fixed in web_fetch.rs test.
- #983: Dockerfile adds perl and make for openssl-sys compilation on slim-bookworm.
- #987: Nextcloud chat poll endpoint corrected from api/v4/room/{token}/chat to
api/v1/chat/{token}/ matching the send endpoint.
- #970: Moonshot Kimi K2/K2.5 models now redirect to api.moonshot.cn/v1 instead of
api.moonshot.ai/v1. The .ai domain only serves legacy moonshot-v1-* models.
- #882: Closed as resolved by v0.5.7 custom hand persistence fix (#984).
- #926: Verified already fixed (rmcp builder API from previous session).
All tests passing. 8 files changed, 75 insertions.
Bug: in activate_hand(), kill_agent() is called on the existing agent
BEFORE the new agent is spawned. kill_agent() invokes
cron_scheduler.remove_agent_jobs() which deletes all cron jobs from memory
AND persists [] to cron_jobs.json. The reassign_agent_jobs() call further
down was meant to migrate jobs from old to new (per #461), but it always
runs as a no-op because the jobs are already gone — the order of
operations defeats the fix.
Symptom: every daemon restart silently destroys cron jobs for hand-style
agents. cron_jobs.json is rewritten as []. /api/cron/jobs returns empty.
No error message.
Fix: snapshot the cron jobs into a local Vec BEFORE kill_agent (same
pattern as saved_triggers above), then re-add them under the new agent_id
AFTER spawn_agent_with_parent. Runtime state (next_run, last_run) is
reset so jobs get a fresh start. The existing reassign_agent_jobs()
block is kept as a defensive safety net but is now redundant in the
common path.
Verified with cargo check -p openfang-kernel --lib (clean compile, no
warnings).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The agent config reload logic was missing skills and mcp_servers from
the change detection, so edits to these fields in agent.toml weren't
being picked up when loading agents from SQLite.
Added both fields to the comparison to ensure proper hot-reload.
The previous commit accidentally included a complete MCP module rewrite
that removed Http transport and headers support, breaking compilation
against upstream kernel.rs tests.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
`MessageContent::text_length()` returned 0 for `ToolUse` blocks,
ignoring the tool name and JSON input arguments. This caused the
compactor's `estimate_token_count()` (which uses `text_length()`)
to massively undercount tokens when conversations contained tool
calls with large arguments (e.g. web_search results, page content).
The result: compaction never triggered despite the session exceeding
the context window, leading to "Token limit exceeded" errors.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Extract is_silent_token() helper for case-insensitive [SILENT] detection.
Revert unrelated Cargo.lock and formatting changes. Add unit tests.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- #771: Fix Qwen tool_calls orphaning after context overflow. Added safe drain boundaries
in compactor and context_overflow to avoid splitting tool pairs. Added missing
validate_and_repair call in streaming loop.
- #811: LINE webhook signature now uses raw request bytes (not re-serialized JSON) for
HMAC. Channel secret is trimmed. Debug logging added for mismatches.
- #752: Local skill install now hot-reloads kernel via POST /api/skills/reload. TUI skill
list fixed to parse wrapper object. ClawHub install also triggers reload.
- #772: exec_policy mode=full now bypasses approval gate for shell_exec tools. Non-shell
tools like file_delete still respect approval settings.
- #661: Closed as resolved by #770 splice() reactivity fix and #836 tool ID fix.
All tests passing. 10 files changed, 436 insertions.
Addresses review feedback:
- Add `openfang auth hash-password` subcommand so users can generate
Argon2id hashes after upgrading (the command referenced in docs).
- Emit a tracing::warn at daemon startup when auth is enabled but the
password_hash is not in Argon2id format, so users know why login fails.
Dashboard passwords were hashed with plain SHA256 (no salt), vulnerable
to rainbow tables and GPU brute force. Switch to Argon2id with random
per-hash salts. Breaking change: existing SHA256 hashes in config.toml
must be regenerated with `openfang auth hash-password`.
- #875: Install script uses robust sed parsing instead of fragile cut for version detection
- #872: Session endpoint returns full tool results (removed 2000-char truncation)
- #867: agent_send/agent_spawn get 600s timeout (was 120s), regular tools keep 120s
- #824: Doctor workspace skills count uses direct return value from load_workspace_skills
- #833: Model switching respects provider via new find_model_for_provider() lookup
- #766: Closed as resolved by combined heartbeat fixes (v0.5.3 + merged PRs)
All tests passing. Live tested with daemon.
