Route groq-prefixed models through the OpenAI-compatible client,
apply Groq token-limit metadata, and skip local tool injection for
compound models.
Add regression coverage for routing, token limits, and compound
local-tool behavior.
Co-authored-by: Oz <oz-agent@warp.dev>
feat: add persistent auto-memory system
Implement a file-based persistent memory system that allows the AI to retain knowledge about users, feedback, projects, and references across sessions.
## Implementation Details
- MemoryStore data layer with FNV-1a workspace fingerprinting
- MemoryRead/MemoryWrite tools with security hardening (path traversal, symlink, absolute path, and size limit protections)
- System prompt injection of MEMORY.md index with prompt injection mitigation (fenced code block + trust-lowering notice)
- autoMemoryEnabled config option (defaults to true)
- Doctor health check for auto-memory state
- /memory command enhancement showing persistent memory info
## Verification
✓ 1023 lib tests pass
✓ Output format contract tests pass
✓ Release build succeeds
✓ Security hardening verified
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix(runtime): prompt permission mode never invokes the prompter
PermissionMode derives Ord from declaration order, placing Prompt (and Allow)
above the real privilege ladder (ReadOnly < WorkspaceWrite < DangerFullAccess).
In PermissionPolicy::authorize_with_context the ladder check
'current_mode >= required_mode' therefore evaluates true for every tool when the
active mode is Prompt (3 >= {0,1,2}), returning Allow and making the subsequent
'if current_mode == PermissionMode::Prompt' branch that routes to prompt_or_deny
unreachable.
Effect: a session configured with the 'prompt' permission mode silently
auto-allows every tool and never calls the prompter (reached via
ConversationRuntime::run_turn with an interactive prompter), defeating the mode's
entire purpose. The sibling PermissionEnforcer already special-cases Prompt
before its own 'active_mode >= required_mode' check, confirming Prompt is not
meant to be part of the ordered ladder.
Fix: exclude Prompt from the ordered-ladder comparison so Prompt mode falls
through to the interactive prompt path. Allow remains handled by its explicit
equality check. The same comparison appears twice in authorize_with_context —
once in the shared tail and once inside the 'Some(PermissionOverride::Allow)'
arm, which is reached when a hook emits permissionDecision "allow" — so both
copies carry the guard; guarding only the tail still left a hook able to
auto-allow every tool in Prompt mode without ever consulting the prompter.
Adds regression tests covering Prompt mode with a prompter, without a prompter,
and with a hook allow override.
* refactor(runtime): make the permission privilege ladder an explicit rank
`PermissionMode` derived `PartialOrd`/`Ord`, so the ladder deciding whether a
tool runs without asking was declaration order. A variant inserted in the middle
of the enum re-ranked it silently, and the difference between "this tool may
run" and "this tool may run after a prompt" was a property of where an `enum`
line happened to sit. That is how `Prompt` came to outrank `DangerFullAccess`,
satisfy `current_mode >= required_mode` for every tool, and skip the prompter.
Replace the derive with `privilege_rank`, an exhaustive `match` naming every
variant, so inserting one is a build failure rather than a silent re-ranking.
`Ord` is deliberately not derived, so a stray `>=` on two modes no longer
compiles; the two comparisons outside this module now say which rank they read
(`PermissionEnforcer::check_with_required_mode` and the `claw doctor` permission
check). Both keep their previous answers, since `privilege_rank` reproduces the
old declaration order exactly, including `Prompt` and `Allow` above the tiers.
`Prompt` and `Allow` are modes of operation, not privilege tiers, so they are
never ranked *against* a tool requirement. The new `covers` predicate states
that by name rather than by number: `Allow` always covers, `Prompt` never does
(it asks), and only the three tiers compare ranks.
That also collapses the duplicated ladder in `authorize_with_context`. The
`Some(PermissionOverride::Allow)` arm carried a second, identical copy of the
ask-rule check and the ladder; it now falls through to the single copy below,
so a hook `allow` is an override rather than a bypass and the two copies can no
longer drift apart.
Behaviour is unchanged for every (mode, requirement, rule, override)
combination. The tests pin the `Prompt` routes — plain and hook-`allow` — across
all three tiers, plus the rank ordering itself.
Root knowledge base plus complexity-scored subdirectory files for the
rust/ workspace, its five highest-mass crates (runtime, rusty-claude-cli,
api, tools, commands, plugins), and the src/ Python porting workspace.
Generated via init-deep: 13 parallel explore agents, LSP/ast-grep code
map, centrality-scored placement. Snapshot in .omo/init-deep.json (local).
- OLLAMA_HOST takes priority over OPENAI_BASE_URL for local Ollama instances
- No API key required; placeholder token used for Authorization header
- Model names like 'qwen3:8b' bypass strict provider/model syntax validation
- detect_provider_kind() checks OLLAMA_HOST first in routing cascade
- ProviderClient dispatch uses from_ollama_env() when OLLAMA_HOST is set
- Updated USAGE.md and docs with OLLAMA_HOST as preferred env var
- Added OLLAMA_CONFIG constant and from_ollama_env() to openai_compat
- Added test_ollama_host_bypasses_model_validation unit test
- Supersedes PR #3213 (which had a duplicate if-let bug in mod.rs)
The setup wizard was merged in PR #3017 but was orphaned -- it was not
declared as a module in main.rs, making it unreachable. Additionally,
the setup_wizard.rs imports RuntimeProviderConfig which did not exist
on upstream/main. This commit makes the wizard accessible and adds the
necessary RuntimeProviderConfig type.
Changes:
- Add RuntimeProviderConfig struct to runtime/src/config.rs with
kind(), api_key(), base_url(), model() accessors.
- Add parse_optional_provider_config() to parse the provider object
from merged settings JSON.
- Add provider() method to RuntimeConfig and RuntimeFeatureConfig.
- Export RuntimeProviderConfig, save_user_provider_settings,
clear_user_provider_settings, and default_config_home from runtime
crate public API (runtime/src/lib.rs).
- Add mod setup_wizard to rusty-claude-cli/src/main.rs.
- Add claw setup CLI subcommand.
- Add /setup slash command.
- Add Setup variant to SlashCommand enum.
- Add Setup to LocalHelpTopic enum.
- Add setup to diagnostic subcommand matching.
- Add subagentModel to TOP_LEVEL_FIELDS in config_validate.rs.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
SessionLifecycleSummary now collects all matching tmux panes into an
all_panes field and includes them in the JSON output. Previously the
status command returned on the first non-idle pane, losing all other
active panes in the same workspace/session.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
/resume mode /clear now preserves the original session_id instead of
generating a new one. This prevents the filename/meta-header divergence
where /session list reported an id that --resume couldn't find.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
/session switch and /session fork now return structured JSON with
kind:error, error_kind:unsupported_resumed_command, and actionable
hint instead of a raw error string that resume callers couldn't parse.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
Add friendly_cwd() helper that strips /private prefix on macOS so
status, doctor, and diff JSON output matches user-visible invocation
cwd instead of the canonicalized /private/tmp path.
Applied to status_context() and render_doctor_report().
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
/model was in the unsupported resume group but is a read-only command
that can safely return model configuration. Now returns default_model,
configured_model, resolved_model, and requested_model in JSON mode.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
--compact was silently ignored when used with non-prompt commands like
claw --compact status or claw --compact config. Now returns a typed
error with guidance on proper usage.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
/tasks was marked resume_supported but rejected in resume mode.
Now returns a structured JSON response with kind:'tasks' and note
that background tasks are only available in the interactive REPL.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
- /config help now returns available_sections array and loaded_keys
count instead of treating 'help' as an unsupported section
- Updated test to exclude 'help' from unsupported sections test
- Added new test config_help_returns_structured_section_list_344
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
/config help now returns a list of available config sections in both
text and JSON mode instead of treating 'help' as an unsupported section.
Text mode shows available sections with descriptions.
JSON mode returns available_sections array with loaded_keys count.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
Top-level 'claw --output-format json help' now includes a 'commands'
array with name, summary, and resume_supported for each registered
slash command, plus 'total_commands' count.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
Add GitOperation enum to detect mid-operation git states from the
branch header in git status --short --branch output.
- Rebase: 'rebasing ...' in branch header
- Merge: '[merge-in-progress]' tag
- Cherry-pick: 'cherry-pick-in-progress' tag
- Bisect: 'bisect-in-progress' tag
Operation state appears in:
- status text: 'rebase-in-progress, dirty · 3 files · ...'
- status JSON: 'git_operation' field (null when no operation)
- git_state headline includes operation prefix
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
--base-commit now rejects non-hex strings and strings outside 7-64
character range. Matches the pattern used by --reasoning-effort.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
The --cwd validation added in #99 rejects non-existent paths, but the
test used /tmp/project which doesn't exist on CI Linux runners. Changed
to /tmp which exists everywhere.
Also marks ROADMAP #123 DONE (--allowedTools normalization verified).
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
status/doctor JSON now reports git_state:'no_git_repo' when
project_root is None, instead of the misleading 'clean' which
implied a git repo was present with zero changes.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
bootstrap-plan --output-format json now returns phases as structured
objects with id, label, description, and order fields instead of
raw Rust enum variant name strings. Also exposes total_phases count.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
--cwd now validates the path exists and is a directory before passing
it to the system prompt renderer. --date rejects values with newlines
or >20 chars to prevent prompt injection.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
Changed resumed_help_command_emits_structured_json to assert 'message'
field instead of 'text', matching the #338 fix for help JSON field
consistency.
Also marked ROADMAP #340 and #345 DONE with direct runtime evidence:
340: resume /session help now routes JSON to stdout (verified)
345: resume /config <section> now returns section-specific JSON (verified)
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
#327: mcp help now includes .claw.json in documented sources list
#328: agents help now includes ~/.codex/agents in documented sources list
#408: added is_clean boolean to status JSON workspace for unambiguous
dirty-state detection; changed_files documented as total non-clean count
#338: resume help field consistency (committed earlier)
Also marked 52 items with explicit done/verified evidence as DONE
in ROADMAP.md, including product principles (1-6) and items with
confirmed fix text (13-75, 96, 200).
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
#410: Added field to mcp list and skills list JSON for
polymorphic consumption parity with agents list. All three sibling
list commands now expose a canonical integer field alongside
their command-specific details.
#338: Changed resume JSON from to field for
consistency with top-level .
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
#683-#692: help topic JSON now includes usage, purpose, formats,
related, local_only, requires_credentials, and aliases extracted
from help prose. Export and doctor keep their custom structured
responses.
#466: new check_base_url_health() validates ANTHROPIC_BASE_URL,
OPENAI_BASE_URL, XAI_BASE_URL, and DASHSCOPE_BASE_URL for basic
HTTP(S) URL format. Non-http schemes and empty values produce a
warn-level diagnostic.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
status --output-format json now exposes duplicate_flags array listing
any --model, --output-format, or --permission-mode flags specified
more than once. Uses a module-level static for cross-function access.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
render_config_json now includes a 'merged' object with actual
key-value pairs from the resolved runtime configuration, not just
the count.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
check_auth_health data fields now include openai_key_present alongside
api_key_present and auth_token_present. any_auth_present already
includes OPENAI_API_KEY for prompt_ready status.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
__SYSTEM_PROMPT_DYNAMIC_BOUNDARY__ is now filtered from the sections
array in JSON output. boundary_index field exposed for callers that
need the static/dynamic split point.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
The catch-all in render_mcp_report_json_for now returns
render_mcp_unsupported_action_json with ok:false and
error_kind:unsupported_action instead of help JSON with exit 0.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
Only fire the slash-command guard for multi-word commands when the
first token is a known CLI subcommand (help, version, status, etc.).
Slash commands with additional arguments (explain this, cost list)
are treated as prompts.
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>
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>
Bellman
AbdullahFageehandOz
Ming LiuandClaude Opus 4.6
黄云龙
gaebal-gajae
YeonGyu-Kim
nankingjing
Aneesh
bellman
Your NameandClaude Opus 4.8
