* chore(ci): retrigger PR checks after intake body update
* fix(ci): stabilize local quality gates on rebased main
---------
Co-authored-by: Chummy <chumyin0912@gmail.com>
Co-authored-by: xj <gh-xj@users.noreply.github.com>
- Fix MD036: convert bold text to proper heading at line 197
- Add Vietnamese localization (cron-scheduling.md)
- Update Vietnamese SUMMARY.md with cron-scheduling link
Add SiliconFlow provider factory support and alias/env handling.
Normalize onboarding UX to volcengine while preserving doubao/ark runtime aliases.
Add integration registry entries and provider resolution coverage tests.
Expand provider and command docs with setup and validation examples.
Reduce PR CI critical path from ~80min to ~30min and total runner
pressure by ~40% through job parallelization, deduplication, and
cache unification.
Changes:
- ci-run.yml: run lint, test, and build in parallel (remove lint→test
serial dependency); merge flake-probe retry logic into test job;
unify rust-cache prefix-key for lint/test; simplify ci-required gate
- ci-build-fast.yml: delete redundant workflow (cargo build --release
with lto=fat, codegen-units=1 duplicated ci-run.build's release-fast)
- feature-matrix.yml: skip 4 compilation lanes on PRs by default (only
trigger on ci:full or ci:feature-matrix label); remove unnecessary
fetch-depth: 0 from checkout
- docs/ci-map.md: update documentation to reflect new job topology,
parallel execution model, and label-gated feature matrix behavior
- Add non-loopback auth guard to /v1/chat/completions (matching /api/chat)
- Fix migration guide references to non-existent files (api_chat.rs,
openai_compat_shim.rs, mod_patch.rs) — endpoints live in openclaw_compat.rs
- Remove phantom `provider` field from /api/chat response docs
- Add TOML string escaping to config converter to handle special chars
- Add proper JSON parse error handling in config converter
- Update deployment checklist and troubleshooting to match actual file layout
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add a complete OpenClaw → ZeroClaw migration toolkit:
- POST /api/chat: ZeroClaw-native endpoint with full agent loop (tools, memory,
context enrichment). Supports session_id scoping and context[] injection for
conversation history. Same code path as Linq/WhatsApp/Nextcloud handlers.
- POST /v1/chat/completions: OpenAI-compatible shim that routes through
run_gateway_chat_with_tools instead of the simple provider.chat_with_history
path. Extracts last user message + up to 10 messages of conversation context
from the messages[] array. Supports streaming (simulated SSE). Drop-in
replacement for OpenClaw callers with zero code changes.
Both endpoints include full observability instrumentation (AgentStart, LlmRequest,
LlmResponse, RequestLatency, AgentEnd), auth (pairing + webhook secret), rate
limiting, auto-save to memory, and response sanitization.
Also adds:
- scripts/convert-openclaw-config.py: Converts openclaw.json → config.toml with
provider mapping, channel detection, and migration notes
- docs/migration/openclaw-migration-guide.md: Full migration walkthrough with
endpoint reference, config mapping, callsite examples, and deployment checklist
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- report api_key_configured via provider credential resolution (env + overrides)\n- set agent.compact_context default to true for new configs\n- align docs and tests with the new default\n\nRefs: #1983\nRefs: #1984\nContext: #1358\n\nCo-authored-by: Argenis <144828210+theonlyhennygod@users.noreply.github.com>
Implements a plugin system for ZeroClaw modeled after OpenClaw's architecture.
Key components:
- Plugin trait and PluginApi for registering tools/hooks
- Plugin manifest (zeroclaw.plugin.toml) for metadata
- Plugin discovery from bundled, global, and workspace directories
- PluginRegistry managing loaded plugins, tools, and hooks
- Error isolation via panic catching in register()
- Config integration via [plugins] section
Example plugin included in extensions/hello-world/.
Closes#1414
# Conflicts:
# src/config/mod.rs
# src/config/schema.rs
Set AgentConfig compact_context default to true and align config defaults/tests/docs so daemon conversations recover from context pressure out of the box.
Closes#1984
Document the agents_ipc configuration section (enabled, db_path,
staleness_secs) and the five IPC tools registered when enabled.
Closes the documentation gap from PR #1668 (agents IPC feature).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove the manual Homebrew-core publishing workflow and related docs references.
Signed-off-by: Rui Chen <rui@chenrui.dev>
(cherry picked from commit bc8b721b7e)
Replace vague placeholders with descriptive ones:
- cli_xxx → your_lark_app_id
- xxx → your_lark_app_secret
Makes it clearer what values users need to substitute.
* feat(providers): implement Qwen OAuth quota tracking
Add static quota display for Qwen OAuth provider (portal.qwen.ai).
Qwen OAuth API does not return rate-limit headers, so this provides
a static quota indicator based on known OAuth free-tier limits.
Changes:
- Add QwenQuotaExtractor in quota_adapter.rs
- Parses rate-limit errors for retry backoff
- Registered for all Qwen aliases (qwen, qwen-code, dashscope, etc.)
- Add Qwen OAuth detection in quota_cli.rs
- Auto-detects ~/.qwen/oauth_creds.json
- Displays static quota: ?/1000 (unknown remaining, 1000/day total)
- Improve quota display formatting
- Shows "?/total" when only total limit is known
- Add comprehensive test report and testing scripts
- Full integration test report: docs/qwen-provider-test-report.md
- Model availability, context window, and latency tests
- Reusable test scripts in scripts/ directory
Test results:
- Available model: qwen3-coder-plus (verified)
- Context window: ~32K tokens
- Average latency: ~2.8s
- All 15 quota tests passing
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
(cherry picked from commit fa91b6a170)
* docs: satisfy markdownlint spacing in qwen docs
---------
Co-authored-by: ZeroClaw Bot <zeroclaw_bot@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
`supports_vision` is currently hardcoded per-provider. The same Ollama instance can run `llava` (vision) or
`codellama` (no vision), but the code fixes vision support at the provider level with no user override.
This adds a top-level `model_support_vision: Option<bool>` config key — tri-state:
- **Unset (default):** provider's built-in value, zero behavior change
- **`true`:** force vision on (e.g. Ollama + llava)
- **`false`:** force vision off
Follows the exact same pattern as `reasoning_enabled`. Override is applied at the wrapper layer (`ReliableProvider` /
`RouterProvider`) — no concrete provider code is touched.
## Changes
**Config surface:**
- Top-level `model_support_vision` field in `Config` struct with `#[serde(default)]`
- Env override: `ZEROCLAW_MODEL_SUPPORT_VISION` / `MODEL_SUPPORT_VISION`
**Provider wrappers (core logic):**
- `ReliableProvider`: `vision_override` field + `with_vision_override()` builder + `supports_vision()` override
- `RouterProvider`: same pattern
**Wiring (1-line each):**
- `ProviderRuntimeOptions` struct + factory functions
- 5 construction sites: `loop_.rs`, `channels/mod.rs`, `gateway/mod.rs`, `tools/mod.rs`, `onboard/wizard.rs`
**Docs (i18n parity):**
- `config-reference.md` — Core Keys table
- `providers-reference.md` — new "Ollama Vision Override" section
- Vietnamese sync: `docs/i18n/vi/` + `docs/vi/` (4 files)
## Non-goals
- Does not change any concrete provider implementation
- Does not auto-detect model vision capability
## Test plan
- [x] `cargo fmt --all -- --check`
- [x] `cargo clippy --all-targets -- -D warnings` (no new errors)
- [x] 5 new tests passing:
- `model_support_vision_deserializes` — TOML parse + default None
- `env_override_model_support_vision` — env var override + invalid value ignored
- `vision_override_forces_true` — ReliableProvider override
- `vision_override_forces_false` — ReliableProvider override
- `vision_override_none_defers_to_provider` — passthrough behavior
## Risk and Rollback
- **Risk:** Low. `None` default = zero behavior change for existing users.
- **Rollback:** Revert commit. Field is `#[serde(default)]` so old configs without it will deserialize fine.
(cherry picked from commit a1b8dee785)
Add comprehensive Docker documentation covering:
- Bootstrap and onboarding in Docker mode
- Running ZeroClaw as a daemon or interactively
- Common commands and troubleshooting
- Environment variables and configuration options
This addresses user confusion where `zeroclaw` commands don't work
on the host after Docker bootstrap, and no containers are started.
Closes#1364
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* ci(homebrew): prefer HOMEBREW_UPSTREAM_PR_TOKEN with fallback
* ci(homebrew): handle existing upstream remote and main base
* feat(tools): Use system default browser instead of hard-coded Brave Browser
---------
Co-authored-by: Will Sarg <12886992+willsarg@users.noreply.github.com>
Adds a `/new` runtime chat command for Telegram and Discord that clears
the sender's conversation history without changing provider or model.
Useful for starting a fresh session when stale context causes issues.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
