Port the team-enhancement feature layer from feat/multi-tool-exec onto
feat/team-test so the agent-teams stack is buildable and testable on top
of the current CLI/runtime.
Subagent model (config wiring):
- Add subagent_model field to RuntimeFeatureConfig + RuntimeConfig::subagent_model()
accessor + parse_optional_subagent_model() 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.
Parallel tool execution:
- Re-export ToolCall/ToolResult/TurnProgressReporter from runtime so the
CliToolExecutor::execute_batch override type-checks.
- Override execute_batch to classify read-only tools (read_file, glob/grep
search, WebFetch/WebSearch, LSP, Git*, ToolSearch, Skill, Agent*,
TeamStatus, Task*) as parallel-safe and run them concurrently via
std:🧵:scope; everything else stays sequential. Results return in
original model order.
Team coordination layer (cherry-picked from feat/multi-tool-exec):
- AgentMessage, TaskClaim, TeamStatus tools + shared mailbox directory +
mode presets (tiny/1x ... mega/6x) + enriched TeamCreate/Agent tool
descriptions + background team watcher.
- /team slash command: on/off/status/toggle of CLAWD_AGENT_TEAMS (the flag
TeamCreate requires), replacing the info-only stub. Spec updated to
[on|off|status].
- resolve_conflicts resolved: de-duplicated SlashCommand::Team/Setup arms
and ReadOutcome::TeamToggle arms that the cherry-picks overlapped with
the existing /team parse fix.
Verification:
- cargo build --workspace OK
- cargo test -p tools --lib: 111 passed (1 env failure: repl_executes_python_code)
- cargo test -p runtime --lib team_cron: 17 passed
- cargo test -p commands --lib: 42 passed (incl /team parse regression)
- cargo test -p rusty-claude-cli --bin claw: 345 passed
- scripts/fmt.sh --check OK
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
When the model returns multiple tool_use blocks in a single response,
read-only tools (read_file, glob_search, grep_search, WebFetch,
WebSearch, LSP, Git*) now execute concurrently via std:🧵:scope
instead of sequentially.
Architecture:
- Add ToolCall/ToolResult types to ToolExecutor trait
- Add execute_batch() with default sequential fallback
- CliToolExecutor overrides execute_batch to classify tools as
parallel-safe or sequential, then runs parallel-safe tools
concurrently via thread scopes
- run_turn refactored into 3 phases:
1. Pre-hooks + permission checks (sequential, hooks may mutate state)
2. Tool execution (batch, parallel for read-only tools)
3. Post-hooks + session updates (sequential, preserves ordering)
Safety guarantees:
- Pre/post hooks always run sequentially
- Permission checks complete before any tool executes
- Tool results pushed to session in original model order
- Fallback to sequential for single-tool batches
Extend auto-compaction error detection to handle additional error patterns
from llama.cpp backends: 'Context size has been exceeded',
'exceed_context_size_error', 'exceeds the available context size'. Also
recover from reqwest 'error decoding response body' errors — some
llama.cpp instances return a non-SSE plaintext HTTP 500 on context overflow,
causing the SSE deserializer to fail.
Add dynamic threshold adaptation: parse server-reported context window
size from error messages (e.g., '(81920 tokens)') and set the auto-
compaction trigger at 70% of that value. This replaces the need for a
hardcoded threshold, adapting automatically to any backend's limits.
This patch was developed with assistance from OpenCode and local Qwen 3.6
API server.
Five interrelated fixes from parallel Hephaestus sessions:
1. fix(repl): display assistant text after spinner (#2981, #2982, #2937)
- Added final_assistant_text() call after run_turn spinner completes
- REPL now shows response text like run_prompt_json does
2. fix(compact): handle Thinking content blocks (#2985)
- Added ContentBlock::Thinking variant throughout compact summarizer
- Prevents panic when /compact encounters thinking blocks
3. fix(prompt): provider-aware model identity (#2822)
- New ModelFamilyIdentity enum (Claude vs Generic)
- Non-Anthropic models no longer say 'I am Claude'
- model_family_identity_for() detects provider and sets identity
4. fix(openai): preserve DeepSeek reasoning_content (#2821)
- Stream parser now captures reasoning_content from OpenAI-compat
- Emits ThinkingDelta/SignatureDelta events for reasoning models
- Thinking blocks included in conversation history for re-send
5. feat(runtime): Thinking block support across codebase
- AssistantEvent::Thinking variant in conversation.rs
- ContentBlock::Thinking in session serialization
- Thinking-aware compact summarization
- Tests for thinking block ordering and content
Closes#2981, #2982, #2937, #2985, #2822, #2821
ROADMAP #38 no longer reflects current main. The runtime already runs a
post-compaction session-health probe, but the backlog lacked explicit
regression proof. This change adds focused tests for the two important
behaviors: a broken tool surface aborts a compacted session with a targeted
error, while a freshly compacted empty session does not false-positive as
dead. With that proof in place, the roadmap item can be marked done.
Constraint: User required fresh cargo fmt/clippy/test evidence before closing any backlog item
Rejected: Leave #38 open because the implementation already existed | backlog stays stale and invites duplicate work
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Reopen#38 only with a fresh same-turn repro that bypasses the current health-probe gate
Tested: cargo fmt --all --check; cargo clippy --workspace --all-targets -- -D warnings; cargo test --workspace
Not-tested: No live long-running dogfood session replay beyond existing automated coverage
Parse --reasoning-effort <low|medium|high> in parse_args, thread through
CliAction::Prompt and CliAction::Repl, LiveCli::set_reasoning_effort(),
AnthropicRuntimeClient.reasoning_effort field, and MessageRequest.reasoning_effort.
Changes:
- parse_args: new --reasoning-effort / --reasoning-effort=VAL flag arms
- AnthropicRuntimeClient: new reasoning_effort field + set_reasoning_effort() method
- LiveCli: new set_reasoning_effort() that reaches through BuiltRuntime -> ConversationRuntime -> api_client_mut()
- runtime::ConversationRuntime: new pub api_client_mut() accessor
- MessageRequest construction: reasoning_effort: self.reasoning_effort.clone()
- run_repl(): accepts and applies reasoning_effort parameter
- parse_direct_slash_cli_action(): propagates reasoning_effort
All 156 CLI tests pass, all api tests pass, cargo fmt clean.
This adds crate-level and type-level Rustdoc to the runtime crate's core exported types so downstream crates and contributors can understand the session, prompt, permission, OAuth, usage, and tool I/O primitives without spelunking every implementation file.
Constraint: The docs pass needed to stay focused on public runtime types without changing behavior
Rejected: Add blanket docs to every public item in one sweep | larger churn than needed for a targeted docs pass
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: When exporting new runtime primitives from lib.rs, add a short Rustdoc summary in the defining module at the same time
Tested: cargo build --workspace; cargo test --workspace
Not-tested: rustdoc HTML rendering beyond doc-test coverage
Claw already had the core slash-command and git primitives, but the UX
still made users work to discover them, understand current workspace
state, and trust what `/commit` was about to do. This change tightens
that flow in the same places Codex-style CLIs do: command discovery,
live status, typo recovery, and commit preflight/output.
The REPL banner and `/help` now surface a clearer starter path, unknown
slash commands suggest likely matches, `/status` includes actionable git
state, and `/commit` explains what it is staging and committing before
and after the model writes the Lore message. I also cleared the
workspace's existing clippy blockers so the verification lane can stay
fully green.
Constraint: Improve UX inside the existing Rust CLI surfaces without adding new dependencies
Rejected: Add more slash commands first | discoverability and feedback were the bigger friction points
Rejected: Split verification lint fixes into a second commit | user requested one solid commit
Confidence: high
Scope-risk: moderate
Directive: Keep slash discoverability, status reporting, and commit reporting aligned so `/help`, `/status`, and `/commit` tell the same workflow story
Tested: cargo fmt --all; cargo clippy --workspace --all-targets -- -D warnings; cargo test --workspace
Not-tested: Manual interactive REPL session against live Anthropic/xAI endpoints
The runtime now auto-compacts completed conversations once cumulative input usage
crosses a configurable threshold, preserving recent context while surfacing an
explicit user notice. The CLI also publishes the requested ant-only slash
commands through the shared commands crate and main dispatch, using meaningful
local implementations for commit/PR/issue/teleport/debug workflows.
Constraint: Reuse the existing Rust compaction pipeline instead of introducing a new summarization stack
Constraint: No new dependencies or broad command-framework rewrite
Rejected: Implement API-driven compaction inside ConversationRuntime now | too much new plumbing for this delivery
Rejected: Expose new commands as parse-only stubs | would not satisfy the requested command availability
Confidence: medium
Scope-risk: moderate
Reversibility: clean
Directive: If runtime later gains true API-backed compaction, preserve the TurnSummary auto-compaction metadata shape so CLI call sites stay stable
Tested: cargo test; cargo build --release; cargo fmt --all; git diff --check; LSP diagnostics directory check
Not-tested: Live Anthropic-backed specialist command flows; gh-authenticated PR/issue creation in a real repo
This threads typed hook settings through runtime config, adds a shell-based hook runner, and executes PreToolUse/PostToolUse around each tool call in the conversation loop. The CLI now rebuilds runtimes with settings-derived hook configuration so user-defined Claude hook commands actually run before and after tools.
Constraint: Hook behavior needed to match Claude-style settings.json hooks without broad plugin/MCP parity work in this change
Rejected: Delay hook loading to the tool executor layer | would miss denied tool calls and duplicate runtime policy plumbing
Confidence: medium
Scope-risk: moderate
Reversibility: clean
Directive: Keep hook execution in the runtime loop so permission decisions and tool results remain wrapped by the same conversation semantics
Tested: cargo test; cargo build --release
Not-tested: Real user hook scripts outside the test harness; broader plugin/skills parity
This threads typed hook settings through runtime config, adds a shell-based hook runner, and executes PreToolUse/PostToolUse around each tool call in the conversation loop. The CLI now rebuilds runtimes with settings-derived hook configuration so user-defined Claw hook commands actually run before and after tools.
Constraint: Hook behavior needed to match Claw-style settings.json hooks without broad plugin/MCP parity work in this change
Rejected: Delay hook loading to the tool executor layer | would miss denied tool calls and duplicate runtime policy plumbing
Confidence: medium
Scope-risk: moderate
Reversibility: clean
Directive: Keep hook execution in the runtime loop so permission decisions and tool results remain wrapped by the same conversation semantics
Tested: cargo test; cargo build --release
Not-tested: Real user hook scripts outside the test harness; broader plugin/skills parity
Extended thinking needed to travel end-to-end through the API,
runtime, and CLI so the client can request a thinking budget,
preserve streamed reasoning blocks, and present them in a
collapsed text-first form. The implementation keeps thinking
strictly opt-in, adds a session-local toggle, and reuses the
existing flag/slash-command/reporting surfaces instead of
introducing a new UI layer.
Constraint: Existing non-thinking text/tool flows had to remain backward compatible by default
Constraint: Terminal UX needed a lightweight collapsed representation rather than an interactive TUI widget
Rejected: Heuristic CLI-only parsing of reasoning text | brittle against structured stream payloads
Rejected: Expanded raw thinking output by default | too noisy for normal assistant responses
Confidence: medium
Scope-risk: moderate
Reversibility: clean
Directive: Keep thinking blocks structurally separate from answer text unless the upstream API contract changes
Tested: cargo fmt --all; cargo clippy --workspace --all-targets -- -D warnings; cargo test -q
Not-tested: Live upstream thinking payloads against the production API contract
Extended thinking needed to travel end-to-end through the API,
runtime, and CLI so the client can request a thinking budget,
preserve streamed reasoning blocks, and present them in a
collapsed text-first form. The implementation keeps thinking
strictly opt-in, adds a session-local toggle, and reuses the
existing flag/slash-command/reporting surfaces instead of
introducing a new UI layer.
Constraint: Existing non-thinking text/tool flows had to remain backward compatible by default
Constraint: Terminal UX needed a lightweight collapsed representation rather than an interactive TUI widget
Rejected: Heuristic CLI-only parsing of reasoning text | brittle against structured stream payloads
Rejected: Expanded raw thinking output by default | too noisy for normal assistant responses
Confidence: medium
Scope-risk: moderate
Reversibility: clean
Directive: Keep thinking blocks structurally separate from answer text unless the upstream API contract changes
Tested: cargo fmt --all; cargo clippy --workspace --all-targets -- -D warnings; cargo test -q
Not-tested: Live upstream thinking payloads against the production API contract
This change makes compaction summaries durable under .claude/memory,
feeds those saved memory files back into prompt context, updates /memory
to report both instruction and project-memory files, and moves TodoWrite
persistence to a human-readable .claude/todos.md file.
Constraint: Reuse existing compaction, prompt loading, and slash-command plumbing rather than add a new subsystem
Constraint: Keep persisted project state under Claude-local .claude/ paths
Rejected: Introduce a dedicated memory service module | larger diff with no clear user benefit for this task
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: Project memory files are loaded as prompt context, so future format changes must preserve concise readable content
Tested: cargo fmt --all --manifest-path rust/Cargo.toml
Tested: cargo clippy --manifest-path rust/Cargo.toml --all-targets --all-features -- -D warnings
Tested: cargo test --manifest-path rust/Cargo.toml --all
Not-tested: Long-term retention/cleanup policy for .claude/memory growth
This change makes compaction summaries durable under .claw/memory,
feeds those saved memory files back into prompt context, updates /memory
to report both instruction and project-memory files, and moves TodoWrite
persistence to a human-readable .claw/todos.md file.
Constraint: Reuse existing compaction, prompt loading, and slash-command plumbing rather than add a new subsystem
Constraint: Keep persisted project state under Claw-local .claw/ paths
Rejected: Introduce a dedicated memory service module | larger diff with no clear user benefit for this task
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: Project memory files are loaded as prompt context, so future format changes must preserve concise readable content
Tested: cargo fmt --all --manifest-path rust/Cargo.toml
Tested: cargo clippy --manifest-path rust/Cargo.toml --all-targets --all-features -- -D warnings
Tested: cargo test --manifest-path rust/Cargo.toml --all
Not-tested: Long-term retention/cleanup policy for .claw/memory growth
TheArchitectit
Petter Reinholdtsen
YeonGyu-Kim
Yeachan-Heo
Jobdori