When input is a prefix of a candidate (e.g., mcp → mcpServers), return
the prefix match directly instead of relying on edit-distance which
would incorrectly suggest env (distance 3) over mcpServers (distance 7).
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
Changed rest.len() != 1 guard to rest.is_empty() so claw cost list,
claw model list, claw permissions show, etc. now reach the
bare_slash_command_guidance guard and emit typed slash-command
guidance instead of falling through to CliAction::Prompt.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
claw models is already wired as CliAction::Models with full
print_models implementation. Both models list and models help
return bounded JSON without touching provider runtime.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
Added specific handler for --help when rest contains --resume, so
claw --resume --help shows resume help instead of consuming --help
as a session-id literal.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
The status_context function now filters loader.discover() to only count
paths that exist on disk, matching the check_config_health behavior.
Both config.discovered_files_count and workspace.discovered_config_files
now report the same number.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
Added list to KNOWN_SUBCOMMANDS so claw list is caught by typo
suggestion instead of falling through to CliAction::Prompt. Also
verified #455 (missing_credentials hint already newline-delimited).
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
Added prompt_ready:bool and prompt_blocked_reason:string|null to the
auth check in doctor --output-format json. prompt_ready is true when
any auth credential is present, false otherwise. prompt_blocked_reason
is auth_missing when prompt_ready is false.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
Added dedicated CliAction::SessionList variant for claw session list so
it no longer requires API credentials. run_session_list() calls
list_managed_sessions() directly without instantiating an API client.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
Added requested field (alias for enabled) and active_components object
with namespace/network/filesystem booleans for precise subsystem visibility.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
The enforce_broad_cwd_policy function was sending JSON error envelopes
to stderr instead of stdout. Fixed to use println! for JSON mode,
matching the main error handler and all resume error paths.
Also closed ROADMAP #446 (config warning deduplication already handled
by emit_config_warning_once) and #447 (JSON errors already routed to
stdout in main handler).
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
Skill discovery now tracks dir_name alongside frontmatter name and detects
when they differ. skills list --output-format json includes metadata_drift
array and reports degraded status when drift entries exist.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
claw --resume now enforces the same broad-cwd safety policy as claw prompt
and the interactive REPL. Running from /, $HOME, or other broad directories
blocks execution unless --allow-broad-cwd is passed.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
Agent discovery now loads .md files with YAML frontmatter alongside .toml
files, matching the Claude Code agent definition convention. Markdown
agent files must have ----delimited YAML frontmatter with at least name
or description fields.
Key changes:
- parse_agent_frontmatter extracts name, description, model, model_reasoning_effort
- load_agents_from_roots_with_invalids collects both valid and invalid agents
- InvalidAgentConfig tracks rejected .md files with reason
- AgentCollection groups valid agents with invalid entries
- agents JSON output includes valid_count, invalid_count, invalid_agents
- Status is degraded when invalid agents exist
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
Hook config now supports the Claude Code structured hook format with
partial validation. Invalid hook entries are recorded in invalid_hooks
while valid siblings are retained, following the same pattern as MCP
partial validation (#440).
Key changes:
- RuntimeInvalidHookConfig now includes typed kind field (invalid_hooks_config
or unknown_hook_event) for machine-readable error classification
- Hook parsing collects all invalid entries instead of halting at first error
- Unknown hook event names recorded as invalid without rejecting valid hooks
- Legacy bare-string hooks still load with deprecation warnings
- Claude Code documented format loads without error (matcher + nested hooks)
- config/status/doctor JSON surfaces hook_validation metadata
- classify_error_kind maps hook errors to invalid_hooks_config
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
/approve, /yes, /deny, /no (and /y, /n) are valid REPL-only slash
commands. Outside the REPL they were falling through to
format_unknown_direct_slash_command -> error_kind:unknown_slash_command.
Fix: intercept them in the SlashCommand::Unknown arm and emit
interactive_only: prefix so classify_error_kind returns the correct kind.
One new test: approve_deny_outside_repl_emits_interactive_only (covers
/approve, /yes, /deny, /no)
572 tests pass, 1 pre-existing worker_boot failure unrelated.
