Commit Graph
21 Commits
Author SHA1 Message Date
clawdbot f021597942 Revert "Merge pull request #3318 from ultraworkers/pr-3292"
This reverts commit 2d920ce915, reversing
changes made to 80bfe94b77.
2026-10-12 23:09:13 +00:00
reacechalmers 7c38d78759 fix(runtime): auto-continue a turn the model stalled without a tool call
A reply carrying no tool_use ended the turn unconditionally. Small local
models routinely narrate the next tool call in prose — "Now running the
EEC-V probe:" — and then emit EOS, so the announced work never happened
and the user was dropped back at the prompt. The same failure wears a
second hat mid-task: stopping to ask for a go-ahead on work already
requested.

The loop now inspects the final line of a tool-less reply. If it
announces a pending action, or asks a question after tools have already
run this turn, a short nudge is pushed as a user message and the loop
continues instead of breaking. The budget is bounded (default 3 per
turn, CLAW_MAX_STALL_NUDGES, 0 disables) so a model that really is
finished still gets to stop.

Prevention pairs with recovery: the "Doing tasks" system-prompt section
now tells the model to act in the turn it plans in.

Tests cover the auto-continue, the bound, a plain completion that must
NOT be nudged, the disable switch, and last-line-only detection. The
behavioural pair was mutation-checked: reverting the continue to a break
fails both.

(cherry picked from commit 9035fe6f4bf4a8d4cb70d7a3baf1f3748c757498)
2026-10-12 22:58:32 +00:00
reacechalmers cb572811e1 fix(runtime): bound the git diff snapshot to a configurable budget
The git diff snapshot is rendered into the *system prompt*, so its cost is
paid again by every session whose working tree has changed -- and a diff
changes on essentially every edit. The 50_000-char budget was four times the
entire instruction-file budget (12_000) and unbounded in practical effect: a
single modified file added ~15_000 tokens to the prompt.

Measured against a self-hosted backend, one uncommitted change took the
prompt from 8_302 to 23_457 tokens and a one-word reply from ~3 s to 296 s.
With the new default the same session is 7_911 tokens and 36 s. That cost is
absorbable against a hosted frontier model and ruinous against a local one.

Default is now 4_000 chars, matching MAX_INSTRUCTION_FILE_CHARS, and is
overridable with CLAW_MAX_GIT_DIFF_CHARS following the same pattern as
CLAW_MAX_READ_CHARS. A budget of 0 omits the snapshot entirely rather than
emitting an empty section with a truncation marker; git status and the
recent-commit list are unaffected either way.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RNKqVB2JE9UnCkz8FC9HPy
(cherry picked from commit e01c6ea43d56a97e284ab80fa7a90a479997ed74)
2026-10-12 22:58:32 +00:00
Ming LiuandClaude Opus 4.6 43d68dba75 feat: add persistent auto-memory system (#3241)
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>
2026-10-13 07:13:36 +09:00
bellmanandGajae Code 10fe72498a fix: bound parent memory discovery
Generated with https://github.com/Yeachan-Heo/gajae-code

Co-authored-by: Gajae Code <dev@gajae-code.com>
2026-06-04 17:07:00 +09:00
bellmanandGajae Code 5b22bc0480 fix: load Claw and Agents memory files
Generated with https://github.com/Yeachan-Heo/gajae-code

Co-authored-by: Gajae Code <dev@gajae-code.com>
2026-06-04 16:36:04 +09:00
bellman 9c8375da99 feat: import project instruction rules 2026-06-03 21:01:48 +09:00
bellman e752b05425 fix: load common instruction files and typed unknown commands 2026-06-03 18:54:36 +09:00
Heo, Sung 1c62116e25 feat: truncate oversized git diff in system prompt
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.
2026-05-25 11:21:30 +09:00
YeonGyu-Kim 75c08bc982 fix: REPL display, /compact panic, identity leak, DeepSeek reasoning, thinking blocks
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
2026-05-06 15:32:34 +09:00
YeonGyu-Kim c7b3296ef6 style: cargo fmt — fix CI formatting failures
Pre-existing formatting issues in anthropic.rs surfaced by CI cargo fmt check.
No functional changes.
2026-04-08 11:21:13 +09:00
YeonGyu-Kim cae11413dd fix(dead-code): remove stale constants + dead function; add workspace_sessions_dir tests
Three dead-code warnings eliminated from cargo check:

1. KNOWN_TOP_LEVEL_KEYS / DEPRECATED_TOP_LEVEL_KEYS in config.rs
   - Superseded by config_validate::TOP_LEVEL_FIELDS and DEPRECATED_FIELDS
   - Were out of date (missing aliases, providerFallbacks, trustedRoots)
   - Removed

2. read_git_recent_commits in prompt.rs
   - Private function, never called anywhere in the codebase
   - Removed

3. workspace_sessions_dir in session.rs
   - Public API scaffolded for session isolation (#41)
   - Genuinely useful for external consumers (clawhip enumerating sessions)
   - Added 2 tests: deterministic path for same CWD, different path for different CWDs
   - Annotated with #[allow(dead_code)] since it is external-facing API

cargo check --workspace: 0 warnings remaining
430 runtime tests passing, 0 failing
2026-04-08 04:04:54 +09:00
YeonGyu-Kim 8f4651a096 fix: resolve git_context field references after cherry-pick merge 2026-04-07 15:20:20 +09:00
YeonGyu-Kim ef0b870890 feat: b5-git-aware — batch 5 wave 2 2026-04-07 15:19:45 +09:00
YeonGyu-Kim d089d1a9cc feat: b5-retry-backoff — batch 5 upstream parity 2026-04-07 14:51:27 +09:00
Yeachan-Heo 22ad54c08e docs: describe the runtime public API surface
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
2026-04-04 15:23:29 +00:00
YeonGyu-Kim 0bd0914347 fix: stabilize merge fallout test fixtures 2026-04-02 11:31:53 +09:00
YeonGyu-Kim 543b7725ee fix: add env_lock guard to git discovery tests 2026-04-01 19:02:12 +09:00
YeonGyu-KimandSisyphus c2e41ba205 fix: post-plugins-merge cleanroom fixes and workspace deps
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-01 18:48:39 +09:00
Yeachan-Heo 799ee3a4ee wip: plugins progress 2026-04-01 07:09:06 +00:00
Yeachan-Heo 6b5331576e fix: auto compaction threshold default 200k tokens 2026-04-01 03:55:00 +00:00