When a provider returns a JSON error (e.g., {"error":{"message":"..."}})
without SSE framing (no "data:" prefix), the SSE parser was silently
ignoring it and hanging. Now detects and surfaces these errors.
Also handles HTML responses that lack SSE framing.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
When a provider returns HTML (e.g., error page, wrong endpoint) instead
of JSON in an SSE stream, provide a clear error message instead of
hanging or failing with a cryptic parse error.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Some OpenAI-compatible providers (e.g., GLM-5) omit the `id` field in
streaming and non-streaming responses. Adding #[serde(default)] allows
the parser to accept these responses instead of failing with
"missing field `id`".
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
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>
Some providers/proxies return HTTP 400 with bodies like "no parseable
body" or "connection reset" during transient network blips. These are
not real bad requests — they're gateway errors wearing a 400 mask.
Detect known gateway error phrases in 400 response bodies and mark
them as retryable so the existing exponential backoff handles them.
- 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
- Remove retry_after: None from ApiError::Api structs in openai_compat.rs (field was removed)
- Remove SlashCommand::Team parse arm (variant was removed from enum)
- Add config_load_error_kind: None to doctor path StatusContext initializer
- Add Thinking arm to all ContentBlock match blocks in trident.rs
- Remove cargo fmt drift across commands, config, compact, tools, trident
Adds aspect-rs AOP-style logging to execute_tool_with_enforcer, providing cross-cutting arg/result logging for all tool dispatches. Introduces aspect-core, aspect-macros, and aspect-std dependencies.
Fixes bundled_root() to resolve the bundled plugins directory relative to the executable path at runtime instead of using a compile-time CARGO_MANIFEST_DIR path that may be root-owned. Resolution order: standard FHS layout, adjacent layout, then dev/source-tree fallback. Includes proper tests for override, nonexistent, and auto-detection scenarios.
Instead of re-nesting prior highlights under '- Previously compacted context:', flatten them directly into the top-level list with '- ' prefix. This prevents each compaction cycle from adding a nesting layer, which inflated the summary by ~depth * overhead per turn.
Adds early return in wire_model_for_base_url for Gemini/Gemma/XAI/Kimi/Grok model prefixes to ensure the provider prefix is preserved correctly when routing through the OpenAI-compatible provider path.
Threads reasoning_content back into Thinking blocks for DeepSeek V4 multi-turn calls. Adds pending_thinking accumulator to capture thinking/signature delta events during streaming, and converts ContentBlock::Thinking to InputContentBlock::Thinking in convert_messages to preserve reasoning between turns, fixing the 'reasoning_content must be passed back' error.
Fixes alias resolution ordering: aliases (opus/sonnet/haiku) are now resolved to their full provider/model form BEFORE syntax validation. Previously, aliases bypassed validation via an early-return check. Also adds the 'log' crate for debug tracing of alias resolution and wraps PermissionsExt import in #[cfg(unix)] for portability.
Adds MAX_GIT_DIFF_CHARS (50_000) limit and truncate_diff() function to prevent oversized git diffs from blowing up the system prompt. Truncation respects UTF-8 character boundaries and appends a clear truncation notice. Includes unit tests.
Changes the catch-all arm in model_token_limit() from None to conservative defaults (max_output_tokens: 16_384, context_window_tokens: 131_072) to prevent crashes when an unknown model is used.
Adds OPENAI_API_KEY detection to check_auth_health() alongside existing api_key and auth_token checks, creating a combined any_auth_present variable. Also displays openai_key presence in the environment details.
Sets user_agent on both build_http_client_or_default() and build_http_client_with() to 'clawd-rust-tools/0.1' for consistent HTTP client identification.
Resolve the G012 evidence gate by fixing permission-mode regressions, platform-sensitive tests, and the clippy surface that blocked an all-targets verification run.
Constraint: G012 final gate required docs, board, full workspace tests, and clippy -D warnings evidence before checkpointing.
Rejected: documenting the worker-2 gate failure as an accepted gap | the failing tests and lints were locally reproducible and fixable.
Confidence: high
Scope-risk: moderate
Directive: Preserve read-only permission requirements for read/glob/grep tools; write/edit remain workspace-write or danger-full-access when outside the workspace.
Tested: python3 .github/scripts/check_doc_source_of_truth.py; python3 .github/scripts/check_release_readiness.py; python3 scripts/validate_cc2_board.py --board .omx/cc2/board.json; python3 .omx/cc2/validate_issue_parity_intake.py .omx/cc2/issue-parity-intake.json; cargo fmt --manifest-path rust/Cargo.toml --all -- --check; cargo check --manifest-path rust/Cargo.toml --workspace; cargo test --manifest-path rust/Cargo.toml --workspace -- --nocapture; cargo clippy --manifest-path rust/Cargo.toml --workspace --all-targets -- -D warnings
Not-tested: live network provider smoke tests and remote PR/issue mutations.
The resumed session command matcher now owns every /session variant in one arm so adding supported actions does not leave a redundant fallback that triggers unreachable-pattern warnings.\n\nConstraint: G010 session hygiene verification requires clean focused tests around resume/session recovery UX.\nRejected: Leave the warning in place | it obscures real regressions in the focused recovery checks.\nConfidence: high\nScope-risk: narrow\nDirective: Keep new /session resume-mode actions inside run_resumed_session_command rather than duplicating match arms.\nTested: cargo test -p rusty-claude-cli context_window_preflight_errors_render_recovery_steps\nNot-tested: full workspace test suite
Co-authored-by: OmX <omx@local>
