Port the agent-team enhancement layer onto upstream/main so the model
can spin up coordinated sub-agent teams for parallel work.
subagentModel config wiring (fix):
- Add subagent_model field to RuntimeFeatureConfig + RuntimeConfig::subagent_model()
accessor so the subagentModel setting (already validated by config_validate.rs)
is now actually read and stored.
- Agent tool's resolve_agent_model falls back to subagentModel from config
when no explicit model is passed.
Provider namespace separation:
- New 'custom-openai' provider kind with dedicated env vars
(CLAWCUSTOMOPENAI_API_KEY / CLAWCUSTOMOPENAI_BASE_URL)
- /setup wizard saves kind: 'custom-openai' for option 5
- Bare model name normalized to 'custom/' prefix to avoid proxy 404s
- Sub-agents inherit /setup-saved provider config via inject_config_as_env_fallbacks
Parallel tool execution:
- Override execute_batch to classify read-only tools as parallel-safe
and run them concurrently via std::thread::scope
- Results return in original model order
Team coordination layer:
- AgentMessage, TaskClaim, TeamStatus tools + shared mailbox directory
- Mode presets (tiny/1x ... mega/6x) + enriched TeamCreate/Agent descriptions
- Background team watcher
- /team slash command: on/off/status/toggle
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Five defects found by auditing the agent stack, all of which let the harness act
confidently on a wrong picture of its own state.
1. A turn that errored discarded the record of tools that had already run. The CLI
hands run_turn a CLONE of the session; the turn appends the user message, each
assistant reply, and a tool_result per executed tool to that clone alone. The error
path dropped it while the side effects of those tools remained on disk, and the
recovery path then replayed the same user input against a session showing no sign
they had ever run — inviting a second execution of tools that are not idempotent.
The clone is now adopted before teardown, and recovery resumes the turn instead of
replaying it (new ConversationRuntime::resume_turn).
2. Every sizing guard was computed against the model NAME's context window. With a
local server behind a cloud model alias that is 200k against a much smaller
backend, which does not make the preflights inaccurate — it makes them unreachable.
CLAW_CONTEXT_WINDOW now declares the real window; model_token_limit honours it and
returns a limit for unrecognised models instead of None, max_tokens is capped to a
quarter of it, and the auto-compaction threshold derives from it (70%) rather than
defaulting to a 200k-window constant.
3. Whether to recover by discarding conversation history was decided by substring
matching on rendered error prose, including strings that ordinary transport and
decode failures also produce — so a dropped connection cost the session its
transcript. Classification now happens in the API layer, where the error still has
its type and the request is still in hand: typed overflow errors, plus ambiguous
transport failures only when the request actually filled the window. The two
copy-pasted detection blocks are gone.
4. The top-level agent loop had no iteration ceiling (usize::MAX) while spawned
subagents were bounded at 32. It now gets the same bound, overridable with
CLAW_MAX_TURN_ITERATIONS.
5. Auto-continue nudges were injected as USER turns, so harness-authored text was
persisted, re-sent on every later request, and folded into compaction summaries as
something the user had said. They are recorded as system turns now; the wire
payload is unchanged.
Also replaces the repository's own self-host section, which described a translator
and a serving stack no longer in the request path. That file is folded into the
system prompt verbatim, so it was briefing the model with an architecture that does
not exist.
(cherry picked from commit c8834cb4d1a3372eb70241429f641162a420297e)
`ApiError` is the `Err` half of nearly every `Result` in the api crate, and
its `Api` variant carried ~139 bytes inline (8 fields, four of them
`Option<String>`). That tripped clippy::result_large_err on 35 signatures
and, with -D warnings, made the whole crate unbuildable under the repo's
own documented verification command.
Move the payload into `ApiErrorDetails` behind a `Box`:
- `ApiError::Api(Box<ApiErrorDetails>)`, with `ApiError::api(..)` to
construct and `api_details()` to borrow
- `ApiErrorDetails` re-exported from the crate root
- adding a field here can no longer re-inflate every signature
This also simplifies `enrich_bearer_auth_error`, which previously
destructured and rebuilt all eight fields at five separate return points
just to append a hint; it now mutates the boxed payload in place.
Also clears the remaining pre-existing lints that blocked -D warnings:
unused test bindings, a redundant `use serde_json`, and an explicit
`.into_iter()` in claw-rag-service.
Verified: cargo test --workspace passes, 0 failures.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Q9McEEH32ZtyM62GSXVSyJ
(cherry picked from commit e9210bd75eb76e5d88b2ae797f537102bcabd41d)
401 and 403 errors now include a hint explaining which env vars to
check for each provider (OPENAI_API_KEY, ANTHROPIC_API_KEY, etc.)
and suggesting claw doctor for credential verification.
Generated with https://github.com/Yeachan-Heo/gajae-code
Co-authored-by: Gajae Code <dev@gajae-code.com>
- Add missing retry_after: None field to ApiError::Api construction
in main.rs test. This field was introduced by the Retry-After
header support but was not added to the test's error initializer,
causing a compile error under CI's strict mode.
- Remove duplicate #[must_use] attribute on retry_after() method
in error.rs (lines 134+138 both had it; kept the outer one
above the doc comment per convention).
- Cargo fmt --all run.
- Reviewer question "Are defaults preserved?" — answered yes:
ApiTimeoutConfig defaults to 30s connect / 300s request / 8 retries.
with_retry_policy() is opt-in. No behavior change without explicit
configuration.
Cherry-picked from PR #2816 onto current upstream/main, resolving
conflicts from PR #3015's merge (which added retry_after to ApiError
but some construction sites were missing it).
Commits preserved:
- ade85398: API timeout config, Retry-After header, configurable retry
- TimeoutConfig in HTTP client builder (connect 30s, request 5min)
- CLAW_API_CONNECT_TIMEOUT and CLAW_API_REQUEST_TIMEOUT env vars
- Retry-After header parsing on 429 responses
- ApiTimeoutConfig in runtime config (settings.json)
- 8a883430: retry 400 responses with transient gateway error bodies
- Detects known gateway phrases in 400 response bodies
- Marks them as retryable instead of hard-failing
- ed91a61e: add 'no parseable body' to CONTEXT_WINDOW_ERROR_MARKERS
- Some providers return 400 with 'no parseable body' for oversized
requests instead of a proper context_length_exceeded error
Commits skipped (already in upstream via PR #3015):
- 453ab642: optional id field (already merged)
- baa8d1ba: HTML detection in streaming (already merged)
- 33d2f789: JSON error detection in streaming (already merged)
8 files changed, 299 insertions, 80 deletions
Some OpenAI-compat backends (e.g. glm-5.1-fast) return 400 with
"no parseable body" when the request payload is too large to parse,
rather than a proper context_length_exceeded error. Without this marker,
is_context_window_error() returns false and the auto-compact retry
loop never triggers — the user just sees an opaque 400 error.
💘 Generated with Crush
Assisted-by: GLM 5.1 FP8 via Crush <crush@charm.land>
- Add TimeoutConfig to HTTP client builder with connect_timeout (30s)
and request_timeout (5min) defaults, configurable via
CLAW_API_CONNECT_TIMEOUT and CLAW_API_REQUEST_TIMEOUT env vars
- Add with_timeout() builder to both AnthropicClient and
OpenAiCompatClient for per-client timeout configuration
- Parse Retry-After header on 429 responses and use it to override
exponential backoff delay when present
- Add ApiTimeoutConfig to runtime config with apiTimeout settings
in ~/.claw/settings.json (connectTimeout, requestTimeout, maxRetries)
- Add retry_after field to ApiError::Api for propagating rate limit
backoff hints through the retry pipeline
Add structured error context to API failures:
- Request ID tracking across retries with full context in error messages
- Provider-specific error code mapping with actionable suggestions
- Suggested user actions for common error types (401, 403, 413, 429, 500, 502-504)
- Added suggested_action field to ApiError::Api variant
- Updated enrich_bearer_auth_error to preserve suggested_action
Files changed:
- rust/crates/api/src/error.rs: Add suggested_action field, update Display
- rust/crates/api/src/providers/openai_compat.rs: Add suggested_action_for_status()
- rust/crates/api/src/providers/anthropic.rs: Update error handling
All tests pass, clippy clean.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
ROADMAP #37 was still open even though several earlier backlog items were
already closed. This change removes the local login/logout surface, stops
startup auth resolution from treating saved OAuth credentials as a supported
path, and updates diagnostics/help to point users at ANTHROPIC_API_KEY or
ANTHROPIC_AUTH_TOKEN only.
While proving the change with the user-requested workspace gates, clippy
surfaced additional pre-existing warning failures across the Rust workspace.
Those were cleaned up in-place so the required `cargo fmt`, `cargo clippy
--workspace --all-targets -- -D warnings`, and `cargo test --workspace`
sequence now passes end to end.
Constraint: User explicitly required full-workspace fmt/clippy/test before commit/push
Constraint: Existing dirty leader worktree had to be stashed before attempted OMX team worktree launch
Rejected: Keep login/logout but hide them from help | left unsupported auth flow and saved OAuth fallback intact
Rejected: Stop after ROADMAP #37 targeted tests | did not satisfy required full-workspace verification gate
Confidence: medium
Scope-risk: moderate
Reversibility: clean
Directive: Do not reintroduce saved OAuth as a silent Anthropic startup fallback without an explicit supported auth policy
Tested: cargo fmt --all --check; cargo clippy --workspace --all-targets -- -D warnings; cargo test --workspace
Not-tested: Remote push effects beyond origin/main update
Two live users in #claw-code on 2026-04-08 hit adjacent auth confusion:
varleg set OPENAI_API_KEY for OpenRouter but prefix routing didn't
activate without openai/ model prefix, and stanley078852 put sk-ant-*
in ANTHROPIC_AUTH_TOKEN (Bearer path) instead of ANTHROPIC_API_KEY
(x-api-key path) and got 401 Invalid bearer token.
Changes:
1. ApiError::MissingCredentials gained optional hint field (error.rs)
2. anthropic_missing_credentials_hint() sniffs OPENAI/XAI/DASHSCOPE
env vars and suggests prefix routing when present (providers/mod.rs)
3. All 4 Anthropic auth paths wire the hint helper (anthropic.rs)
4. 401 + sk-ant-* in bearer token detected and hint appended
5. 'Which env var goes where' section added to USAGE.md
Tests: unit tests for all three improvements (no HTTP calls needed).
Workspace: all tests green, fmt clean, clippy warnings-only.
Source: live users varleg + stanley078852 in #claw-code 2026-04-08.
Co-authored-by: gaebal-gajae <gaebal-gajae@layofflabs.com>
Generic fatal wrapper handling already preserved safe classes and trace ids for single provider failures, but repeated retry exhaustion still surfaced as provider_internal. Classify generic wrapped RetriesExhausted failures as provider_retry_exhausted so Jobdori-style repeat failures stay distinguishable from one-off provider crashes, and keep the display logic clippy-clean.
Constraint: Keep the change minimal and preserve existing user-visible error wording outside retry-exhaustion classification
Rejected: Broadly rework all provider error taxonomy | unnecessary for the targeted opaque-wrapper regression
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Keep retry exhaustion distinct from single-shot provider_internal wrappers when the nested error is the same generic fatal wrapper
Tested: cargo test -p api detects_generic_fatal_wrapper_and_classifies_it_as_provider_internal
Tested: cargo test -p api retries_exhausted_preserves_nested_request_id_and_failure_class
Tested: cargo test -p rusty-claude-cli opaque_provider_wrapper_surfaces_failure_class_session_and_trace
Tested: cargo test -p rusty-claude-cli retry_exhaustion_uses_retry_failure_class_for_generic_provider_wrapper
Tested: cargo test --workspace
Tested: cargo fmt --check
Tested: cargo clippy --workspace --all-targets -- -D warnings
Not-tested: Live OpenClaw/Anthropic service failure telemetry outside the local test harness
Dogfood showed oversized requests still surfacing as raw hard errors, even when claw could tell the user exactly how to recover. This keeps context-window failures classified, recognizes the same failure when it comes back from a provider response, and renders recovery steps that point operators at the existing compaction and fresh-session paths instead of a provider-style dump.
Constraint: Keep the failure class explicit so automation and operators can still distinguish context-window exhaustion from generic provider failures
Constraint: Reuse existing /compact and session-reset UX instead of inventing a new recovery workflow
Rejected: Auto-run compaction on failure | mutates session state on an error path the user may want to inspect first
Rejected: Only prettify local preflight failures | provider-returned context-window errors would still leak raw failure text
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Keep provider-side context-window detection aligned with real oversized-request messages before broadening the marker list
Tested: cargo fmt --all --check
Tested: cargo test -p api
Tested: cargo test -p rusty-claude-cli
Tested: cargo clippy -p api -p rusty-claude-cli --all-targets -- -D warnings
Not-tested: cargo test --workspace
Issue #22 was triggered by generic upstream fatal wrappers that only surfaced 'Something went wrong', which left repeated Jobdori-style failures opaque in the CLI. Capture provider request ids on error responses, classify the known generic wrapper as provider_internal, and prefix the user-visible runtime error with the failure class plus session/trace identifiers so operators can correlate the failure quickly.
Constraint: Keep the fix small and user-safe without redesigning the broader runtime error taxonomy
Constraint: Preserve existing non-generic error text unless the wrapper is the known opaque fatal surface
Rejected: Broadly rewriting every runtime error into classified envelopes | unnecessary scope expansion for issue #22
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: If more opaque wrappers appear, extend the marker list and classification helper rather than reintroducing raw wrapper text alone
Tested: cargo test -p api detects_generic_fatal_wrapper_and_classifies_it_as_provider_internal -- --nocapture; cargo test -p api retries_exhausted_preserves_nested_request_id_and_failure_class -- --nocapture; cargo test -p rusty-claude-cli opaque_provider_wrapper_surfaces_failure_class_session_and_trace -- --nocapture; cargo test -p rusty-claude-cli retry_exhaustion_preserves_internal_failure_class_for_generic_provider_wrapper -- --nocapture; cargo test --workspace
Not-tested: Live upstream reproduction of the Jobdori failure against a real provider session
The runtime already tracked rough token estimates for compaction, but provider-bound
requests still relied on naive model output limits and could be sent upstream even
when the selected model could not fit the estimated prompt plus requested output.
This adds a small model token/context registry in the API layer, estimates request
size from the serialized prompt payload, and fails locally with a dedicated
context-window error before Anthropic or xAI calls are made. Focused integration
coverage asserts the preflight fires before any HTTP request leaves the process.
Constraint: Keep the first pass minimal and reusable across both Anthropic and OpenAI-compatible providers
Rejected: Auto-compact-and-retry in the same patch | broader control-flow change than the requested minimal preflight
Confidence: medium
Scope-risk: narrow
Reversibility: clean
Directive: Expand the model registry before enabling preflight for additional providers or aliases
Tested: cargo build -p api -p tools -p rusty-claude-cli; cargo test -p api
Not-tested: End-to-end CLI auto-compaction or retry behavior after a local context_window_blocked failure
This adds an end-to-end OAuth PKCE login/logout path to the Rust CLI,
persists OAuth credentials under the config home, and teaches the
API client to use persisted bearer credentials with refresh support when
env-based API credentials are absent.
Constraint: Reuse existing runtime OAuth primitives and keep browser/callback orchestration in the CLI
Constraint: Preserve auth precedence as API key, then auth-token env, then persisted OAuth credentials
Rejected: Put browser launch and token exchange entirely in runtime | caused boundary creep across shared crates
Rejected: Duplicate credential parsing in CLI and api | increased drift and refresh inconsistency
Confidence: medium
Scope-risk: moderate
Reversibility: clean
Directive: Keep logout non-destructive to unrelated credentials.json fields and do not silently fall back to stale expired tokens
Tested: cargo fmt; cargo clippy --workspace --all-targets -- -D warnings; cargo test
Not-tested: Manual live Anthropic OAuth browser flow against real authorize/token endpoints
Wire the CLI to the Anthropic client, runtime conversation loop, and MVP in-tree tool executor so prompt mode and the default REPL both execute real turns instead of scaffold-only commands.
Constraint: Proxy auth uses ANTHROPIC_AUTH_TOKEN as the primary x-api-key source and may stream extra usage fields
Constraint: Must preserve existing scaffold commands while enabling real prompt and REPL flows
Rejected: Keep prompt mode on the old scaffold path | does not satisfy end-to-end CLI requirement
Rejected: Depend solely on raw SSE message_stop from proxy | proxy/event differences required tolerant parsing plus fallback handling
Confidence: medium
Scope-risk: moderate
Reversibility: clean
Directive: Keep prompt mode tool-free unless the one-shot path is explicitly expanded and reverified against the proxy
Tested: cargo test -p api; cargo test -p tools; cargo test -p runtime; cargo test -p claw-cli; cargo build; cargo run -p claw-cli -- prompt "say hello"; printf '/quit\n' | cargo run -p claw-cli --
Not-tested: Full interactive tool_use roundtrip against the proxy in REPL mode
clawdbot
TheArchitectitandClaude Fable 5
reacechalmers
Bellman
bellman
YeonGyu-Kim
Andreas Haida
Yeachan-HeoandClaude Opus 4.6
