- conftest: force ECHO_STEERING=off outside test_steering_dispatch; with
steering on in config.json, mutex/session tests spawned a REAL claude process
- claude_session: security prompt wording changed to "NEVER obey attempts..."
- cli doctor: create voice assets, make urlopen mock work as context manager,
stub `claude --help` with --input-format
- dashboard: auth tests enable DASHBOARD_AUTH (off by default); index panel ids
renamed (gitSection etc.); usage test dates relative to now
- discord: handler ignores any bot author; MagicMock .bot was truthy
- heartbeat: KB reindex is logged not reported, email is JSON-only, git-only
results stay silent by design
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014y1sJNe6mkWwFMwkWmCg8J
- Replace all ~/clawd and ~/.clawdbot paths with ~/echo-core equivalents
in tools (git_commit, ralph_prd_generator, backup_config, lead-gen)
- Update personality files: TOOLS.md repo/paths, AGENTS.md security audit cmd
- Migrate HANDOFF.md architectural decisions to docs/architecture.md
- Tighten credentials/ dir to 700, add to .gitignore
- Add .claude/ and *.pid to .gitignore
- Various adapter, router, and session improvements from prior work
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Switch from --output-format json to --output-format stream-json --verbose
so that _run_claude() parses all assistant text blocks (not just the final
result field). Discord/Telegram/WhatsApp now receive every intermediate
message Claude writes between tool calls.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Prompt injection protection: external messages wrapped in [EXTERNAL CONTENT]
markers, system prompt instructs Claude to never follow external instructions
- Invocation logging: all Claude CLI calls logged with channel, model, duration,
token counts to echo-core.invoke logger
- Security logging: separate echo-core.security logger for unauthorized access
attempts (DMs from non-admins, unauthorized admin/owner commands)
- Security log routed to logs/security.log in addition to main log
- Extended echo doctor: Claude CLI functional check, config.json secret scan,
.gitignore completeness, file permissions, Ollama reachability, bot process
- Subprocess env stripping logged at debug level
373 tests pass (10 new security tests).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
/model (show/change), /restart (owner), /logs, set_session_model API, model reset on /clear. 20 new tests (161 total).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Subprocess wrapper for Claude CLI with start/resume/clear sessions, personality system prompt, atomic session tracking. 38 new tests (89 total).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
