mirror of
https://github.com/outbackdingo/optimclaw.git
synced 2026-08-26 23:50:17 +00:00
Merge remote-tracking branch 'origin/staging' into feat/db-user-management
# Conflicts: # Cargo.lock
This commit is contained in:
+132
@@ -7,6 +7,138 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
## [0.22.0](https://github.com/nearai/ironclaw/compare/ironclaw-v0.21.0...ironclaw-v0.22.0) - 2026-03-25
|
||||
|
||||
### Added
|
||||
|
||||
- *(agent)* thread per-tool reasoning through provider, session, and all surfaces ([#1513](https://github.com/nearai/ironclaw/pull/1513))
|
||||
- *(cli)* show credential auth status in tool info ([#1572](https://github.com/nearai/ironclaw/pull/1572))
|
||||
- multi-tenant auth with per-user workspace isolation ([#1118](https://github.com/nearai/ironclaw/pull/1118))
|
||||
- *(cli)* add ironclaw models subcommands (list/status/set/set-provider) ([#1043](https://github.com/nearai/ironclaw/pull/1043))
|
||||
- *(workspace)* multi-scope workspace reads ([#1117](https://github.com/nearai/ironclaw/pull/1117))
|
||||
- *(ux)* complete UX overhaul — design system, onboarding, web polish ([#1277](https://github.com/nearai/ironclaw/pull/1277))
|
||||
- *(gemini_oauth)* full Gemini CLI OAuth integration with Cloud Code API ([#1356](https://github.com/nearai/ironclaw/pull/1356))
|
||||
- *(shell)* add Low/Medium/High risk levels for graduated command approval (closes #172) ([#368](https://github.com/nearai/ironclaw/pull/368))
|
||||
- *(agent)* queue and merge messages during active turns ([#1412](https://github.com/nearai/ironclaw/pull/1412))
|
||||
- *(cli)* add `ironclaw hooks list` subcommand ([#1023](https://github.com/nearai/ironclaw/pull/1023))
|
||||
- *(extensions)* support text setup fields in web configure modal ([#496](https://github.com/nearai/ironclaw/pull/496))
|
||||
- *(llm)* add GitHub Copilot as LLM provider ([#1512](https://github.com/nearai/ironclaw/pull/1512))
|
||||
- *(workspace)* layered memory with sensitivity-based privacy redirect ([#1112](https://github.com/nearai/ironclaw/pull/1112))
|
||||
- *(webhooks)* add public webhook trigger endpoint for routines ([#736](https://github.com/nearai/ironclaw/pull/736))
|
||||
- *(llm)* Add OpenAI Codex (ChatGPT subscription) as LLM provider ([#1461](https://github.com/nearai/ironclaw/pull/1461))
|
||||
- *(web)* add light theme with dark/light/system toggle ([#1457](https://github.com/nearai/ironclaw/pull/1457))
|
||||
- *(agent)* activate stuck_threshold for time-based stuck job detection ([#1234](https://github.com/nearai/ironclaw/pull/1234))
|
||||
- chat onboarding and routine advisor ([#927](https://github.com/nearai/ironclaw/pull/927))
|
||||
|
||||
### Fixed
|
||||
|
||||
- ensure LLM calls always end with user message (closes #763) ([#1259](https://github.com/nearai/ironclaw/pull/1259))
|
||||
- restore owner-scoped gateway startup ([#1625](https://github.com/nearai/ironclaw/pull/1625))
|
||||
- remove stale stream_token gate from channel-relay activation ([#1623](https://github.com/nearai/ironclaw/pull/1623))
|
||||
- *(agent)* case-insensitive channel match and user_id filter for event triggers ([#1211](https://github.com/nearai/ironclaw/pull/1211))
|
||||
- *(routines)* normalize status display across web and CLI ([#1469](https://github.com/nearai/ironclaw/pull/1469))
|
||||
- *(tunnel)* managed tunnels target wrong port and die from SIGPIPE ([#1093](https://github.com/nearai/ironclaw/pull/1093))
|
||||
- *(agent)* persist /model selection to .env, TOML, and DB ([#1581](https://github.com/nearai/ironclaw/pull/1581))
|
||||
- post-merge review sweep — 8 fixes across security, perf, and correctness ([#1550](https://github.com/nearai/ironclaw/pull/1550))
|
||||
- generate Mistral-compatible 9-char alphanumeric tool call IDs ([#1242](https://github.com/nearai/ironclaw/pull/1242))
|
||||
- *(mcp)* handle empty 202 notification acknowledgements ([#1539](https://github.com/nearai/ironclaw/pull/1539))
|
||||
- *(tests)* eliminate env mutex poison cascade ([#1558](https://github.com/nearai/ironclaw/pull/1558))
|
||||
- *(safety)* escape tool output XML content and remove misleading sanitized attr ([#1067](https://github.com/nearai/ironclaw/pull/1067))
|
||||
- *(oauth)* reject malformed ic2.* states in decode_hosted_oauth_state ([#1441](https://github.com/nearai/ironclaw/pull/1441)) ([#1454](https://github.com/nearai/ironclaw/pull/1454))
|
||||
- parameter coercion and validation for oneOf/anyOf/allOf schemas ([#1397](https://github.com/nearai/ironclaw/pull/1397))
|
||||
- persist startup-loaded MCP clients in ExtensionManager ([#1509](https://github.com/nearai/ironclaw/pull/1509))
|
||||
- *(deps)* patch rustls-webpki vulnerability (RUSTSEC-2026-0049)
|
||||
- *(routines)* add missing extension_manager field in trigger_manual EngineContext
|
||||
- *(ci)* serialize env-mutating OAuth wildcard tests with ENV_MUTEX ([#1280](https://github.com/nearai/ironclaw/pull/1280)) ([#1468](https://github.com/nearai/ironclaw/pull/1468))
|
||||
- *(setup)* remove redundant LLM config and API keys from bootstrap .env ([#1448](https://github.com/nearai/ironclaw/pull/1448))
|
||||
- resolve wasm broadcast merge conflicts with staging ([#395](https://github.com/nearai/ironclaw/pull/395)) ([#1460](https://github.com/nearai/ironclaw/pull/1460))
|
||||
- skip credential validation for Bedrock backend ([#1011](https://github.com/nearai/ironclaw/pull/1011))
|
||||
- register sandbox jobs in ContextManager for query tool visibility ([#1426](https://github.com/nearai/ironclaw/pull/1426))
|
||||
- prefer execution-local message routing metadata ([#1449](https://github.com/nearai/ironclaw/pull/1449))
|
||||
- *(security)* validate embedding base URLs to prevent SSRF ([#1221](https://github.com/nearai/ironclaw/pull/1221))
|
||||
- f32→f64 precision artifact in temperature causes provider 400 errors ([#1450](https://github.com/nearai/ironclaw/pull/1450))
|
||||
- *(routines)* surface errors when sandbox unavailable for full_job routines ([#769](https://github.com/nearai/ironclaw/pull/769))
|
||||
- restore libSQL vector search with dynamic dimensions ([#1393](https://github.com/nearai/ironclaw/pull/1393))
|
||||
- staging CI triage — consolidate retry parsing, fix flaky tests, add docs ([#1427](https://github.com/nearai/ironclaw/pull/1427))
|
||||
|
||||
### Other
|
||||
|
||||
- Merge branch 'main' into staging-promote/455f543b-23329172268
|
||||
- Merge pull request #1655 from nearai/codex/fix-staging-promotion-1451-version-bumps
|
||||
- Merge pull request #1499 from nearai/staging-promote/9603fefd-23364438978
|
||||
- Fix libsql prompt scope regressions ([#1651](https://github.com/nearai/ironclaw/pull/1651))
|
||||
- Normalize cron schedules on routine create ([#1648](https://github.com/nearai/ironclaw/pull/1648))
|
||||
- Fix MCP lifecycle trace user scope ([#1646](https://github.com/nearai/ironclaw/pull/1646))
|
||||
- Fix REPL single-message hang and cap CI test duration ([#1643](https://github.com/nearai/ironclaw/pull/1643))
|
||||
- extract AppEvent to crates/ironclaw_common ([#1615](https://github.com/nearai/ironclaw/pull/1615))
|
||||
- Fix hosted OAuth refresh via proxy ([#1602](https://github.com/nearai/ironclaw/pull/1602))
|
||||
- *(agent)* optimize approval thread resolution (UUID parsing + lock contention) ([#1592](https://github.com/nearai/ironclaw/pull/1592))
|
||||
- *(tools)* auto-compact WASM tool schemas, add descriptions, improve credential prompts ([#1525](https://github.com/nearai/ironclaw/pull/1525))
|
||||
- Default new lightweight routines to tools-enabled ([#1573](https://github.com/nearai/ironclaw/pull/1573))
|
||||
- Google OAuth URL broken when initiated from Telegram channel ([#1165](https://github.com/nearai/ironclaw/pull/1165))
|
||||
- add gitcgr code graph badge ([#1563](https://github.com/nearai/ironclaw/pull/1563))
|
||||
- Fix owner-scoped message routing fallbacks ([#1574](https://github.com/nearai/ironclaw/pull/1574))
|
||||
- *(tools)* remove unconditional params clone in shared execution (fix #893) ([#926](https://github.com/nearai/ironclaw/pull/926))
|
||||
- *(llm)* move transcription module into src/llm/ ([#1559](https://github.com/nearai/ironclaw/pull/1559))
|
||||
- *(agent)* avoid preview allocations for non-truncated strings (fix #894) ([#924](https://github.com/nearai/ironclaw/pull/924))
|
||||
- Expand AGENTS.md with coding agents guidance ([#1392](https://github.com/nearai/ironclaw/pull/1392))
|
||||
- Fix CI approval flows and stale fixtures ([#1478](https://github.com/nearai/ironclaw/pull/1478))
|
||||
- Use live owner tool scope for autonomous routines and jobs ([#1453](https://github.com/nearai/ironclaw/pull/1453))
|
||||
- use Arc in embedding cache to avoid clones on miss path ([#1438](https://github.com/nearai/ironclaw/pull/1438))
|
||||
- Add owner-scoped permissions for full-job routines ([#1440](https://github.com/nearai/ironclaw/pull/1440))
|
||||
|
||||
## [0.21.0](https://github.com/nearai/ironclaw/compare/v0.20.0...v0.21.0) - 2026-03-20
|
||||
|
||||
### Added
|
||||
|
||||
- structured fallback deliverables for failed/stuck jobs ([#236](https://github.com/nearai/ironclaw/pull/236))
|
||||
- LRU embedding cache for workspace search ([#1423](https://github.com/nearai/ironclaw/pull/1423))
|
||||
- receive relay events via webhook callbacks ([#1254](https://github.com/nearai/ironclaw/pull/1254))
|
||||
|
||||
### Fixed
|
||||
|
||||
- bump Feishu channel version for promotion
|
||||
- *(approval)* make "always" auto-approve work for credentialed HTTP requests ([#1257](https://github.com/nearai/ironclaw/pull/1257))
|
||||
- skip NEAR AI session check when backend is not nearai ([#1413](https://github.com/nearai/ironclaw/pull/1413))
|
||||
|
||||
### Other
|
||||
|
||||
- Make hosted OAuth and MCP auth generic ([#1375](https://github.com/nearai/ironclaw/pull/1375))
|
||||
|
||||
## [0.20.0](https://github.com/nearai/ironclaw/compare/v0.19.0...v0.20.0) - 2026-03-19
|
||||
|
||||
### Added
|
||||
|
||||
- *(self-repair)* wire stuck_threshold, store, and builder ([#712](https://github.com/nearai/ironclaw/pull/712))
|
||||
- *(testing)* add FaultInjector framework for StubLlm ([#1233](https://github.com/nearai/ironclaw/pull/1233))
|
||||
- *(gateway)* unified settings page with subtabs ([#1191](https://github.com/nearai/ironclaw/pull/1191))
|
||||
- upgrade MiniMax default model to M2.7 ([#1357](https://github.com/nearai/ironclaw/pull/1357))
|
||||
|
||||
### Fixed
|
||||
|
||||
- navigate telegram E2E tests to channels subtab ([#1408](https://github.com/nearai/ironclaw/pull/1408))
|
||||
- add missing `builder` field and update E2E extensions tab navigation ([#1400](https://github.com/nearai/ironclaw/pull/1400))
|
||||
- remove debug_assert guards that panic on valid error paths ([#1385](https://github.com/nearai/ironclaw/pull/1385))
|
||||
- address valid review comments from PR #1359 ([#1380](https://github.com/nearai/ironclaw/pull/1380))
|
||||
- full_job routine runs stay running until linked job completion ([#1374](https://github.com/nearai/ironclaw/pull/1374))
|
||||
- full_job routine concurrency tracks linked job lifetime ([#1372](https://github.com/nearai/ironclaw/pull/1372))
|
||||
- remove -x from coverage pytest to prevent suite-blocking failures ([#1360](https://github.com/nearai/ironclaw/pull/1360))
|
||||
- add debug_assert invariant guards to critical code paths ([#1312](https://github.com/nearai/ironclaw/pull/1312))
|
||||
- *(mcp)* retry after missing session id errors ([#1355](https://github.com/nearai/ironclaw/pull/1355))
|
||||
- *(telegram)* preserve polling after secret-blocked updates ([#1353](https://github.com/nearai/ironclaw/pull/1353))
|
||||
- *(llm)* cap retry-after delays ([#1351](https://github.com/nearai/ironclaw/pull/1351))
|
||||
- *(setup)* remove nonexistent webhook secret command hint ([#1349](https://github.com/nearai/ironclaw/pull/1349))
|
||||
- Rate limiter returns retry after None instead of a duration ([#1269](https://github.com/nearai/ironclaw/pull/1269))
|
||||
|
||||
### Other
|
||||
|
||||
- bump telegram channel version to 0.2.5 ([#1410](https://github.com/nearai/ironclaw/pull/1410))
|
||||
- *(ci)* enforce test requirement for state machine and resilience changes ([#1230](https://github.com/nearai/ironclaw/pull/1230)) ([#1304](https://github.com/nearai/ironclaw/pull/1304))
|
||||
- Fix duplicate LLM responses for matched event routines ([#1275](https://github.com/nearai/ironclaw/pull/1275))
|
||||
- add Japanese README ([#1306](https://github.com/nearai/ironclaw/pull/1306))
|
||||
- *(ci)* add coverage gates via codecov.yml ([#1228](https://github.com/nearai/ironclaw/pull/1228)) ([#1291](https://github.com/nearai/ironclaw/pull/1291))
|
||||
- Redesign routine create requests for LLMs ([#1147](https://github.com/nearai/ironclaw/pull/1147))
|
||||
|
||||
## [0.19.0](https://github.com/nearai/ironclaw/compare/v0.18.0...v0.19.0) - 2026-03-17
|
||||
|
||||
### Added
|
||||
|
||||
Generated
+17
-17
@@ -157,7 +157,7 @@ version = "1.1.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "40c48f72fd53cd289104fc64099abca73db4166ad86ea0b4341abe65af83dadc"
|
||||
dependencies = [
|
||||
"windows-sys 0.61.2",
|
||||
"windows-sys 0.60.2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -168,7 +168,7 @@ checksum = "291e6a250ff86cd4a820112fb8898808a366d8f9f58ce16d1f538353ad55747d"
|
||||
dependencies = [
|
||||
"anstyle",
|
||||
"once_cell_polyfill",
|
||||
"windows-sys 0.61.2",
|
||||
"windows-sys 0.60.2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -2136,7 +2136,7 @@ dependencies = [
|
||||
"libc",
|
||||
"option-ext",
|
||||
"redox_users 0.5.2",
|
||||
"windows-sys 0.61.2",
|
||||
"windows-sys 0.59.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -2323,7 +2323,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb"
|
||||
dependencies = [
|
||||
"libc",
|
||||
"windows-sys 0.61.2",
|
||||
"windows-sys 0.59.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -3150,7 +3150,7 @@ dependencies = [
|
||||
"libc",
|
||||
"percent-encoding",
|
||||
"pin-project-lite",
|
||||
"socket2 0.6.3",
|
||||
"socket2 0.5.10",
|
||||
"system-configuration",
|
||||
"tokio",
|
||||
"tower-service",
|
||||
@@ -3390,7 +3390,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "ironclaw"
|
||||
version = "0.19.0"
|
||||
version = "0.22.0"
|
||||
dependencies = [
|
||||
"aes-gcm",
|
||||
"aho-corasick",
|
||||
@@ -3497,7 +3497,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "ironclaw_safety"
|
||||
version = "0.1.0"
|
||||
version = "0.2.0"
|
||||
dependencies = [
|
||||
"aho-corasick",
|
||||
"regex",
|
||||
@@ -3524,7 +3524,7 @@ checksum = "3640c1c38b8e4e43584d8df18be5fc6b0aa314ce6ebf51b53313d4306cca8e46"
|
||||
dependencies = [
|
||||
"hermit-abi",
|
||||
"libc",
|
||||
"windows-sys 0.61.2",
|
||||
"windows-sys 0.59.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -4144,7 +4144,7 @@ version = "0.50.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7957b9740744892f114936ab4a57b3f487491bbeafaf8083688b16841a4240e5"
|
||||
dependencies = [
|
||||
"windows-sys 0.61.2",
|
||||
"windows-sys 0.59.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -4930,7 +4930,7 @@ dependencies = [
|
||||
"quinn-udp",
|
||||
"rustc-hash 2.1.1",
|
||||
"rustls 0.23.37",
|
||||
"socket2 0.6.3",
|
||||
"socket2 0.5.10",
|
||||
"thiserror 2.0.18",
|
||||
"tokio",
|
||||
"tracing",
|
||||
@@ -4967,9 +4967,9 @@ dependencies = [
|
||||
"cfg_aliases",
|
||||
"libc",
|
||||
"once_cell",
|
||||
"socket2 0.6.3",
|
||||
"socket2 0.5.10",
|
||||
"tracing",
|
||||
"windows-sys 0.60.2",
|
||||
"windows-sys 0.59.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -5482,7 +5482,7 @@ dependencies = [
|
||||
"errno",
|
||||
"libc",
|
||||
"linux-raw-sys 0.12.1",
|
||||
"windows-sys 0.61.2",
|
||||
"windows-sys 0.59.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -6164,7 +6164,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "3a766e1110788c36f4fa1c2b71b387a7815aa65f88ce0229841826633d93723e"
|
||||
dependencies = [
|
||||
"libc",
|
||||
"windows-sys 0.61.2",
|
||||
"windows-sys 0.60.2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -6389,7 +6389,7 @@ dependencies = [
|
||||
"getrandom 0.4.2",
|
||||
"once_cell",
|
||||
"rustix 1.1.4",
|
||||
"windows-sys 0.61.2",
|
||||
"windows-sys 0.59.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -7190,7 +7190,7 @@ checksum = "f2f6fb2847f6742cd76af783a2a2c49e9375d0a111c7bef6f71cd9e738c72d6e"
|
||||
dependencies = [
|
||||
"memoffset",
|
||||
"tempfile",
|
||||
"windows-sys 0.61.2",
|
||||
"windows-sys 0.60.2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -8040,7 +8040,7 @@ version = "0.1.11"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22"
|
||||
dependencies = [
|
||||
"windows-sys 0.61.2",
|
||||
"windows-sys 0.48.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
||||
+2
-2
@@ -20,7 +20,7 @@ exclude = [
|
||||
|
||||
[package]
|
||||
name = "ironclaw"
|
||||
version = "0.19.0"
|
||||
version = "0.22.0"
|
||||
edition = "2024"
|
||||
rust-version = "1.92"
|
||||
description = "Secure personal AI assistant that protects your data and expands its capabilities on the fly"
|
||||
@@ -105,7 +105,7 @@ cron = "0.13"
|
||||
ironclaw_common = { path = "crates/ironclaw_common", version = "0.1.0" }
|
||||
|
||||
# Safety/sanitization
|
||||
ironclaw_safety = { path = "crates/ironclaw_safety", version = "0.1.0" }
|
||||
ironclaw_safety = { path = "crates/ironclaw_safety", version = "0.2.0" }
|
||||
regex = "1"
|
||||
aho-corasick = "1"
|
||||
|
||||
|
||||
@@ -8,7 +8,6 @@ authors = ["NEAR AI <[email protected]>"]
|
||||
license = "MIT OR Apache-2.0"
|
||||
homepage = "https://github.com/nearai/ironclaw"
|
||||
repository = "https://github.com/nearai/ironclaw"
|
||||
publish = false
|
||||
|
||||
[package.metadata.dist]
|
||||
dist = false
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "ironclaw_safety"
|
||||
version = "0.1.0"
|
||||
version = "0.2.0"
|
||||
edition = "2024"
|
||||
rust-version = "1.92"
|
||||
description = "Prompt injection defense, input validation, secret leak detection, and safety policy enforcement"
|
||||
@@ -8,7 +8,6 @@ authors = ["NEAR AI <[email protected]>"]
|
||||
license = "MIT OR Apache-2.0"
|
||||
homepage = "https://github.com/nearai/ironclaw"
|
||||
repository = "https://github.com/nearai/ironclaw"
|
||||
publish = false
|
||||
|
||||
[package.metadata.dist]
|
||||
dist = false
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"name": "feishu",
|
||||
"display_name": "Feishu / Lark Channel",
|
||||
"kind": "channel",
|
||||
"version": "0.1.1",
|
||||
"version": "0.1.3",
|
||||
"wit_version": "0.3.0",
|
||||
"description": "Talk to your agent through a Feishu or Lark bot",
|
||||
"keywords": [
|
||||
@@ -19,8 +19,8 @@
|
||||
},
|
||||
"artifacts": {
|
||||
"wasm32-wasip2": {
|
||||
"sha256": "5fca74022264d1c8e78a0853766276f7ffa3cf0d8065b2f51ca10985acad4714",
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/v0.19.0/channel-feishu-0.1.1-wasm32-wasip2.tar.gz"
|
||||
"sha256": "a66ff0dafb67d2216d8161bb7e96e724a94acb0ab993b85d2782d30412f8fe94",
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/ironclaw-v0.22.0/channel-feishu-0.1.3-wasm32-wasip2.tar.gz"
|
||||
}
|
||||
},
|
||||
"auth_summary": {
|
||||
|
||||
@@ -18,8 +18,8 @@
|
||||
},
|
||||
"artifacts": {
|
||||
"wasm32-wasip2": {
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/v0.19.0/channel-telegram-0.2.4-wasm32-wasip2.tar.gz",
|
||||
"sha256": "a7cb300ec1c946831cfceaa95c1dc8f30d0f42a3924f3cb5de8098821573f4b8"
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/v0.20.0/channel-telegram-0.2.5-wasm32-wasip2.tar.gz",
|
||||
"sha256": "1ef20a538f55b379e049356e4d6758006251846bc3365ceaa1c87eba8379a329"
|
||||
}
|
||||
},
|
||||
"auth_summary": {
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"name": "github",
|
||||
"display_name": "GitHub",
|
||||
"kind": "tool",
|
||||
"version": "0.2.1",
|
||||
"version": "0.2.2",
|
||||
"wit_version": "0.3.0",
|
||||
"description": "GitHub integration for issues, PRs, repos, and code search",
|
||||
"keywords": [
|
||||
@@ -19,8 +19,8 @@
|
||||
},
|
||||
"artifacts": {
|
||||
"wasm32-wasip2": {
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/v0.19.0/tool-github-0.2.1-wasm32-wasip2.tar.gz",
|
||||
"sha256": "92c530b3ad172e2372d819744b5233f1d8f65768e26eb5a6c213eba3ce1de758"
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/ironclaw-v0.22.0/tool-github-0.2.2-wasm32-wasip2.tar.gz",
|
||||
"sha256": "70b55af593193d8fa495c0f702ea23284d83a624124f8a5f7564916ec5032c3f"
|
||||
}
|
||||
},
|
||||
"auth_summary": {
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"name": "gmail",
|
||||
"display_name": "Gmail",
|
||||
"kind": "tool",
|
||||
"version": "0.2.0",
|
||||
"version": "0.2.1",
|
||||
"wit_version": "0.3.0",
|
||||
"description": "Read, send, and manage Gmail messages and threads",
|
||||
"keywords": [
|
||||
@@ -18,8 +18,8 @@
|
||||
},
|
||||
"artifacts": {
|
||||
"wasm32-wasip2": {
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/v0.18.0/gmail-0.2.0-wasm32-wasip2.tar.gz",
|
||||
"sha256": "ee9574e02e92bc1d481f1310eb88afd99ee52bf6971074ab33bd76bf99b34b1d"
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/ironclaw-v0.22.0/tool-gmail-0.2.1-wasm32-wasip2.tar.gz",
|
||||
"sha256": "79025b40ee70ce1120acc4320bae50da095d7afb0ef67bd56d99b064b72ea779"
|
||||
}
|
||||
},
|
||||
"auth_summary": {
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"name": "google-calendar",
|
||||
"display_name": "Google Calendar",
|
||||
"kind": "tool",
|
||||
"version": "0.2.0",
|
||||
"version": "0.2.1",
|
||||
"wit_version": "0.3.0",
|
||||
"description": "Create, read, update, and delete Google Calendar events",
|
||||
"keywords": [
|
||||
@@ -18,8 +18,8 @@
|
||||
},
|
||||
"artifacts": {
|
||||
"wasm32-wasip2": {
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/v0.18.0/google-calendar-0.2.0-wasm32-wasip2.tar.gz",
|
||||
"sha256": "2fa47150ea222e787c122182ad6f4dfa2ffaf5fe490d05e8de887a76445f8d2d"
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/ironclaw-v0.22.0/tool-google-calendar-0.2.1-wasm32-wasip2.tar.gz",
|
||||
"sha256": "86bcc075010b08f5ab2f98f504cec1c6c9e0ca144857d185cbecf72a11f504bf"
|
||||
}
|
||||
},
|
||||
"auth_summary": {
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"name": "google-docs",
|
||||
"display_name": "Google Docs",
|
||||
"kind": "tool",
|
||||
"version": "0.2.0",
|
||||
"version": "0.2.1",
|
||||
"wit_version": "0.3.0",
|
||||
"description": "Create and edit Google Docs documents",
|
||||
"keywords": [
|
||||
@@ -18,8 +18,8 @@
|
||||
},
|
||||
"artifacts": {
|
||||
"wasm32-wasip2": {
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/v0.18.0/google-docs-0.2.0-wasm32-wasip2.tar.gz",
|
||||
"sha256": "40e134a1c1564f832ca861c3396895d4e33ec67b99313fc1f97baf8d971423a9"
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/ironclaw-v0.22.0/tool-google-docs-0.2.1-wasm32-wasip2.tar.gz",
|
||||
"sha256": "39d476029764949498a53a6a223f9952b5f4df151be7b8b19bf3fe4d401a57cd"
|
||||
}
|
||||
},
|
||||
"auth_summary": {
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"name": "google-drive",
|
||||
"display_name": "Google Drive",
|
||||
"kind": "tool",
|
||||
"version": "0.2.0",
|
||||
"version": "0.2.1",
|
||||
"wit_version": "0.3.0",
|
||||
"description": "Upload, download, search, and manage Google Drive files and folders",
|
||||
"keywords": [
|
||||
@@ -18,8 +18,8 @@
|
||||
},
|
||||
"artifacts": {
|
||||
"wasm32-wasip2": {
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/v0.18.0/google-drive-0.2.0-wasm32-wasip2.tar.gz",
|
||||
"sha256": "002a341a1d58125563a7c69561b26fbc2629b04ea723cade744102bdc0fbb71f"
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/ironclaw-v0.22.0/tool-google-drive-0.2.1-wasm32-wasip2.tar.gz",
|
||||
"sha256": "6e9a700fab93865c852af718666af64c5b534ad6a419fb4b736e07740188f494"
|
||||
}
|
||||
},
|
||||
"auth_summary": {
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"name": "google-sheets",
|
||||
"display_name": "Google Sheets",
|
||||
"kind": "tool",
|
||||
"version": "0.2.0",
|
||||
"version": "0.2.1",
|
||||
"wit_version": "0.3.0",
|
||||
"description": "Read and write Google Sheets spreadsheet data",
|
||||
"keywords": [
|
||||
@@ -18,8 +18,8 @@
|
||||
},
|
||||
"artifacts": {
|
||||
"wasm32-wasip2": {
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/v0.18.0/google-sheets-0.2.0-wasm32-wasip2.tar.gz",
|
||||
"sha256": "8aa2c9d52f033edea3a6c2311b0ec694ccb6d0a54ef07e94d72bf8be1ce8009a"
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/ironclaw-v0.22.0/tool-google-sheets-0.2.1-wasm32-wasip2.tar.gz",
|
||||
"sha256": "1f8c381799a916be83263cac9d497d52946e21b1b588592a3a42ca94a73b7051"
|
||||
}
|
||||
},
|
||||
"auth_summary": {
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"name": "google-slides",
|
||||
"display_name": "Google Slides",
|
||||
"kind": "tool",
|
||||
"version": "0.2.0",
|
||||
"version": "0.2.1",
|
||||
"wit_version": "0.3.0",
|
||||
"description": "Create and edit Google Slides presentations",
|
||||
"keywords": [
|
||||
@@ -17,8 +17,8 @@
|
||||
},
|
||||
"artifacts": {
|
||||
"wasm32-wasip2": {
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/v0.18.0/google-slides-0.2.0-wasm32-wasip2.tar.gz",
|
||||
"sha256": "e931a97d4fd0b0b938e464dc7c7f2be6ea6b4d1508f5ea3cd931d44db23f05f5"
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/ironclaw-v0.22.0/tool-google-slides-0.2.1-wasm32-wasip2.tar.gz",
|
||||
"sha256": "e2528be5da02f1b8cfc8ee9b0cdd849516c53d412e2f75c6175b3bded7f512cb"
|
||||
}
|
||||
},
|
||||
"auth_summary": {
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"name": "llm-context",
|
||||
"display_name": "LLM Context",
|
||||
"kind": "tool",
|
||||
"version": "0.1.0",
|
||||
"version": "0.1.1",
|
||||
"wit_version": "0.3.0",
|
||||
"description": "Fetch pre-extracted web content from Brave Search for grounding LLM answers (RAG, fact-checking)",
|
||||
"keywords": [
|
||||
@@ -21,8 +21,8 @@
|
||||
},
|
||||
"artifacts": {
|
||||
"wasm32-wasip2": {
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/v0.19.0/tool-llm-context-0.1.0-wasm32-wasip2.tar.gz",
|
||||
"sha256": "d9ced2b1226b879135891e0ee40e072c7c95412e1b2462925a23853e1f92497e"
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/ironclaw-v0.22.0/tool-llm-context-0.1.1-wasm32-wasip2.tar.gz",
|
||||
"sha256": "9b19e2fd05dbbbe3c8bd55309a91db09124e8415eb0f767828b6e10b55771e63"
|
||||
}
|
||||
},
|
||||
"auth_summary": {
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"name": "slack-tool",
|
||||
"display_name": "Slack Tool",
|
||||
"kind": "tool",
|
||||
"version": "0.2.0",
|
||||
"version": "0.2.1",
|
||||
"wit_version": "0.3.0",
|
||||
"description": "Your agent uses Slack to post and read messages in your workspace",
|
||||
"keywords": [
|
||||
@@ -17,8 +17,8 @@
|
||||
},
|
||||
"artifacts": {
|
||||
"wasm32-wasip2": {
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/v0.19.0/tool-slack-0.2.0-wasm32-wasip2.tar.gz",
|
||||
"sha256": "ccfb0415d7a04f9497726c712d15216de36e86f498b849101283c017f5ab4efb"
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/ironclaw-v0.22.0/tool-slack-0.2.1-wasm32-wasip2.tar.gz",
|
||||
"sha256": "927519e5b7734beeb022d3b8bbd152e0e6b9f67c9452a8ad47809d3c4221a137"
|
||||
}
|
||||
},
|
||||
"auth_summary": {
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"name": "telegram-mtproto",
|
||||
"display_name": "Telegram Tool",
|
||||
"kind": "tool",
|
||||
"version": "0.2.0",
|
||||
"version": "0.2.1",
|
||||
"wit_version": "0.3.0",
|
||||
"description": "Your agent uses your Telegram account to read and send messages",
|
||||
"keywords": [
|
||||
@@ -18,8 +18,8 @@
|
||||
},
|
||||
"artifacts": {
|
||||
"wasm32-wasip2": {
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/v0.19.0/tool-telegram-0.2.0-wasm32-wasip2.tar.gz",
|
||||
"sha256": "c17065ca41fae5f2a7c43b36144686718cd310a2f22442313bb1aa82bbad0ae4"
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/ironclaw-v0.22.0/tool-telegram-0.2.1-wasm32-wasip2.tar.gz",
|
||||
"sha256": "1e57d0755fc9c7b3ec013d079f30168898b484a6919f9edd105f0cd80131c1cd"
|
||||
}
|
||||
},
|
||||
"auth_summary": {
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"name": "web-search",
|
||||
"display_name": "Web Search",
|
||||
"kind": "tool",
|
||||
"version": "0.2.1",
|
||||
"version": "0.2.2",
|
||||
"wit_version": "0.3.0",
|
||||
"description": "Search the web using Brave Search API",
|
||||
"keywords": [
|
||||
@@ -18,8 +18,8 @@
|
||||
},
|
||||
"artifacts": {
|
||||
"wasm32-wasip2": {
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/v0.19.0/tool-web-search-0.2.1-wasm32-wasip2.tar.gz",
|
||||
"sha256": "bad275ca4ec314adea5241d6b92c44ccf9cebcbca8e30ba2493cc0bcb4b57218"
|
||||
"url": "https://github.com/nearai/ironclaw/releases/download/ironclaw-v0.22.0/tool-web-search-0.2.2-wasm32-wasip2.tar.gz",
|
||||
"sha256": "47382b50c1ea7525b20d59dc02fab04e336d018665826c2f24710bdf460779ae"
|
||||
}
|
||||
},
|
||||
"auth_summary": {
|
||||
|
||||
@@ -1,7 +1,2 @@
|
||||
[workspace]
|
||||
git_release_enable = false
|
||||
|
||||
[[package]]
|
||||
name = "ironclaw_safety"
|
||||
publish = false
|
||||
release = false
|
||||
|
||||
+125
-1
@@ -10,7 +10,7 @@ use std::borrow::Cow;
|
||||
|
||||
use crate::agent::session::PendingApproval;
|
||||
use crate::error::Error;
|
||||
use crate::llm::{ChatMessage, Reasoning, ReasoningContext, RespondResult};
|
||||
use crate::llm::{ChatMessage, FinishReason, Reasoning, ReasoningContext, RespondResult};
|
||||
|
||||
/// Signal from the delegate indicating how the loop should proceed.
|
||||
pub enum LoopSignal {
|
||||
@@ -134,6 +134,9 @@ pub async fn run_agentic_loop(
|
||||
config: &AgenticLoopConfig,
|
||||
) -> Result<LoopOutcome, Error> {
|
||||
let mut consecutive_tool_intent_nudges: u32 = 0;
|
||||
// Accumulates across all iterations (not reset by text responses) so
|
||||
// non-consecutive truncations still escalate to force_text.
|
||||
let mut truncation_count: u32 = 0;
|
||||
|
||||
for iteration in 1..=config.max_iterations {
|
||||
// Check for external signals (stop, cancellation, user messages)
|
||||
@@ -215,7 +218,35 @@ pub async fn run_agentic_loop(
|
||||
tool_calls,
|
||||
content,
|
||||
} => {
|
||||
// If the response was truncated, tool call parameters are likely
|
||||
// incomplete. Discard them and tell the LLM to try a different
|
||||
// approach rather than executing malformed tool calls.
|
||||
if output.finish_reason == FinishReason::Length {
|
||||
truncation_count += 1;
|
||||
let names: Vec<&str> = tool_calls.iter().map(|tc| tc.name.as_str()).collect();
|
||||
tracing::warn!(
|
||||
iteration,
|
||||
tools = ?names,
|
||||
truncation_count,
|
||||
"Discarding truncated tool calls (finish_reason=Length)"
|
||||
);
|
||||
if let Some(ref text) = content {
|
||||
reason_ctx.messages.push(ChatMessage::assistant(text));
|
||||
}
|
||||
reason_ctx
|
||||
.messages
|
||||
.push(ChatMessage::user(crate::llm::TRUNCATED_TOOL_CALL_NOTICE));
|
||||
// After repeated truncations, force text-only mode so the LLM
|
||||
// stops attempting tool calls it can't fit in the output budget.
|
||||
if truncation_count >= 3 {
|
||||
reason_ctx.force_text = true;
|
||||
}
|
||||
delegate.after_iteration(iteration).await;
|
||||
continue;
|
||||
}
|
||||
|
||||
consecutive_tool_intent_nudges = 0;
|
||||
truncation_count = 0;
|
||||
|
||||
if let Some(outcome) = delegate
|
||||
.execute_tool_calls(tool_calls, content, reason_ctx)
|
||||
@@ -271,6 +302,7 @@ mod tests {
|
||||
RespondOutput {
|
||||
result: RespondResult::Text(text.to_string()),
|
||||
usage: zero_usage(),
|
||||
finish_reason: FinishReason::Stop,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -281,6 +313,7 @@ mod tests {
|
||||
content: None,
|
||||
},
|
||||
usage: zero_usage(),
|
||||
finish_reason: FinishReason::ToolUse,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -622,4 +655,95 @@ mod tests {
|
||||
let result = truncate_for_preview("café", 4);
|
||||
assert_eq!(result, "caf...");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_truncated_tool_calls_discarded_on_length() {
|
||||
let truncated_tool_call = ToolCall {
|
||||
id: "call_1".to_string(),
|
||||
name: "memory_write".to_string(),
|
||||
arguments: serde_json::json!({}), // empty — truncated
|
||||
reasoning: None,
|
||||
};
|
||||
let truncated_output = RespondOutput {
|
||||
result: RespondResult::ToolCalls {
|
||||
tool_calls: vec![truncated_tool_call],
|
||||
content: Some("I'll write the report.".to_string()),
|
||||
},
|
||||
usage: zero_usage(),
|
||||
finish_reason: FinishReason::Length, // response was truncated
|
||||
};
|
||||
let delegate = MockDelegate::new(vec![truncated_output, text_output("Summarized it.")]);
|
||||
let reasoning = stub_reasoning();
|
||||
let mut ctx = ReasoningContext::new();
|
||||
let config = AgenticLoopConfig {
|
||||
max_iterations: 5,
|
||||
..Default::default()
|
||||
};
|
||||
|
||||
let outcome = run_agentic_loop(&delegate, &reasoning, &mut ctx, &config)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Tool calls should NOT have been executed
|
||||
assert_eq!(delegate.tool_exec_count.load(Ordering::SeqCst), 0);
|
||||
// The loop should have continued and returned the text response
|
||||
assert!(matches!(outcome, LoopOutcome::Response(ref t) if t == "Summarized it."));
|
||||
// A truncation notice should have been injected into context
|
||||
assert!(
|
||||
ctx.messages
|
||||
.iter()
|
||||
.any(|m| m.role == crate::llm::Role::User && m.content.contains("truncated")),
|
||||
"Should inject truncation notice into context"
|
||||
);
|
||||
// The partial assistant content should have been preserved
|
||||
assert!(
|
||||
ctx.messages
|
||||
.iter()
|
||||
.any(|m| m.role == crate::llm::Role::Assistant
|
||||
&& m.content.contains("write the report")),
|
||||
"Should preserve partial assistant content"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_repeated_truncations_force_text_mode() {
|
||||
let make_truncated = || RespondOutput {
|
||||
result: RespondResult::ToolCalls {
|
||||
tool_calls: vec![ToolCall {
|
||||
id: "call_1".to_string(),
|
||||
name: "memory_write".to_string(),
|
||||
arguments: serde_json::json!({}),
|
||||
reasoning: None,
|
||||
}],
|
||||
content: None,
|
||||
},
|
||||
usage: zero_usage(),
|
||||
finish_reason: FinishReason::Length,
|
||||
};
|
||||
// Three truncated responses, then a text response
|
||||
let delegate = MockDelegate::new(vec![
|
||||
make_truncated(),
|
||||
make_truncated(),
|
||||
make_truncated(),
|
||||
text_output("Gave up on tool calls."),
|
||||
]);
|
||||
let reasoning = stub_reasoning();
|
||||
let mut ctx = ReasoningContext::new();
|
||||
let config = AgenticLoopConfig {
|
||||
max_iterations: 5,
|
||||
..Default::default()
|
||||
};
|
||||
|
||||
let outcome = run_agentic_loop(&delegate, &reasoning, &mut ctx, &config)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert!(matches!(outcome, LoopOutcome::Response(_)));
|
||||
assert_eq!(delegate.tool_exec_count.load(Ordering::SeqCst), 0);
|
||||
// After 3 truncations, force_text should be set
|
||||
assert!(
|
||||
ctx.force_text,
|
||||
"Should escalate to force_text after repeated truncations"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -306,6 +306,8 @@ impl<'a> LoopDelegate for ChatDelegate<'a> {
|
||||
|
||||
// Update context for this iteration
|
||||
reason_ctx.available_tools = tool_defs;
|
||||
// Preserve force_text if already set (e.g. by truncation escalation).
|
||||
let force_text = force_text || reason_ctx.force_text;
|
||||
reason_ctx.system_prompt = Some(if force_text {
|
||||
self.cached_prompt_no_tools.clone()
|
||||
} else {
|
||||
|
||||
+2
-1
@@ -63,7 +63,8 @@ pub use provider::{
|
||||
};
|
||||
pub use reasoning::{
|
||||
ActionPlan, Reasoning, ReasoningContext, RespondOutput, RespondResult, SILENT_REPLY_TOKEN,
|
||||
TOOL_INTENT_NUDGE, TokenUsage, ToolSelection, is_silent_reply, llm_signals_tool_intent,
|
||||
TOOL_INTENT_NUDGE, TRUNCATED_TOOL_CALL_NOTICE, TokenUsage, ToolSelection, is_silent_reply,
|
||||
llm_signals_tool_intent,
|
||||
};
|
||||
pub use recording::RecordingLlm;
|
||||
pub use registry::{ProviderDefinition, ProviderProtocol, ProviderRegistry};
|
||||
|
||||
+200
-8
@@ -8,8 +8,8 @@ use serde::{Deserialize, Serialize};
|
||||
use crate::llm::error::LlmError;
|
||||
|
||||
use crate::llm::{
|
||||
ChatMessage, CompletionRequest, LlmProvider, Role, ToolCall, ToolCompletionRequest,
|
||||
ToolDefinition,
|
||||
ChatMessage, CompletionRequest, FinishReason, LlmProvider, Role, ToolCall,
|
||||
ToolCompletionRequest, ToolDefinition,
|
||||
};
|
||||
|
||||
/// Token the agent returns when it has nothing to say (e.g. in group chats).
|
||||
@@ -23,6 +23,13 @@ You said you would perform an action, but you did not include any tool calls.\n\
|
||||
Do NOT describe what you intend to do — actually call the tool now.\n\
|
||||
Use the tool_calls mechanism to invoke the appropriate tool.";
|
||||
|
||||
/// Notice injected when the LLM's response was truncated mid-tool-call,
|
||||
/// causing incomplete parameters. Tells the LLM to try a different approach.
|
||||
pub const TRUNCATED_TOOL_CALL_NOTICE: &str = "\
|
||||
Your previous response was truncated while generating tool call parameters. \
|
||||
The tool calls were discarded. Please try a different approach — \
|
||||
summarize or transform the data instead of echoing it verbatim in a tool call.";
|
||||
|
||||
/// Seed value used as the second argument to `generate_tool_call_id` when
|
||||
/// recovering tool calls from malformed LLM text responses. This must differ
|
||||
/// from the `0` seed used in `rig_adapter::normalized_tool_call_id` to avoid
|
||||
@@ -194,6 +201,8 @@ pub struct ReasoningContext {
|
||||
pub metadata: std::collections::HashMap<String, String>,
|
||||
/// When true, force a text-only response (ignore available tools).
|
||||
/// Used by the agentic loop to guarantee termination near the iteration limit.
|
||||
/// Sticky: once set, never cleared within a loop invocation. Callers must
|
||||
/// create a fresh `ReasoningContext` per `run_agentic_loop()` call.
|
||||
pub force_text: bool,
|
||||
/// Pre-built system prompt. When set, `respond_with_tools` uses this directly
|
||||
/// instead of calling `build_system_prompt_with_tools`. Allows callers to build
|
||||
@@ -349,6 +358,7 @@ pub enum RespondResult {
|
||||
pub struct RespondOutput {
|
||||
pub result: RespondResult,
|
||||
pub usage: TokenUsage,
|
||||
pub finish_reason: FinishReason,
|
||||
}
|
||||
|
||||
/// Reasoning engine for the agent.
|
||||
@@ -530,6 +540,17 @@ impl Reasoning {
|
||||
|
||||
let response = self.llm.complete_with_tools(request).await?;
|
||||
|
||||
// If the response was truncated, tool call parameters are likely incomplete.
|
||||
// Return empty so the caller can fall through to respond_with_tools() which
|
||||
// has a larger output token budget.
|
||||
if response.finish_reason == FinishReason::Length {
|
||||
tracing::warn!(
|
||||
"select_tools response truncated (finish_reason=Length), \
|
||||
discarding potentially incomplete tool selections"
|
||||
);
|
||||
return Ok(vec![]);
|
||||
}
|
||||
|
||||
let shared_reasoning = response
|
||||
.content
|
||||
.map(|c| {
|
||||
@@ -722,6 +743,7 @@ Respond in JSON format:
|
||||
content: narrative,
|
||||
},
|
||||
usage,
|
||||
finish_reason: response.finish_reason,
|
||||
});
|
||||
}
|
||||
|
||||
@@ -749,6 +771,7 @@ Respond in JSON format:
|
||||
},
|
||||
},
|
||||
usage,
|
||||
finish_reason: response.finish_reason,
|
||||
});
|
||||
}
|
||||
|
||||
@@ -774,6 +797,7 @@ Respond in JSON format:
|
||||
Ok(RespondOutput {
|
||||
result: RespondResult::Text(final_text),
|
||||
usage,
|
||||
finish_reason: response.finish_reason,
|
||||
})
|
||||
} else {
|
||||
// No tools, use simple completion
|
||||
@@ -805,6 +829,7 @@ Respond in JSON format:
|
||||
cache_read_input_tokens: response.cache_read_input_tokens,
|
||||
cache_creation_input_tokens: response.cache_creation_input_tokens,
|
||||
},
|
||||
finish_reason: response.finish_reason,
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -1345,6 +1370,49 @@ fn is_inside_code(pos: usize, regions: &[CodeRegion]) -> bool {
|
||||
regions.iter().any(|r| pos >= r.start && pos < r.end)
|
||||
}
|
||||
|
||||
/// Check whether a byte range overlaps any code region.
|
||||
fn overlaps_code_region(start: usize, end: usize, regions: &[CodeRegion]) -> bool {
|
||||
regions.iter().any(|r| start < r.end && end > r.start)
|
||||
}
|
||||
|
||||
/// Return the byte bounds of the line containing `pos`, excluding the trailing newline.
|
||||
fn line_bounds(text: &str, pos: usize) -> (usize, usize) {
|
||||
let start = text[..pos].rfind('\n').map_or(0, |idx| idx + 1);
|
||||
let end = text[pos..].find('\n').map_or(text.len(), |idx| pos + idx);
|
||||
(start, end)
|
||||
}
|
||||
|
||||
/// Only recover XML-style tool calls when they are isolated content outside
|
||||
/// markdown code and quote contexts. This avoids converting code examples or
|
||||
/// quoted snippets into executable tool calls.
|
||||
fn is_recoverable_tool_call_segment(
|
||||
text: &str,
|
||||
start: usize,
|
||||
end: usize,
|
||||
code_regions: &[CodeRegion],
|
||||
) -> bool {
|
||||
if overlaps_code_region(start, end, code_regions) {
|
||||
return false;
|
||||
}
|
||||
|
||||
let (first_line_start, first_line_end) = line_bounds(text, start);
|
||||
let first_line = &text[first_line_start..first_line_end];
|
||||
|
||||
if first_line.trim_start().starts_with('>') {
|
||||
return false;
|
||||
}
|
||||
|
||||
let (_, last_line_end) = line_bounds(text, end.saturating_sub(1));
|
||||
let first_line_prefix = &text[first_line_start..start];
|
||||
let last_line_suffix = &text[end..last_line_end];
|
||||
|
||||
if !first_line_prefix.trim().is_empty() || !last_line_suffix.trim().is_empty() {
|
||||
return false;
|
||||
}
|
||||
|
||||
true
|
||||
}
|
||||
|
||||
/// Clean up LLM response by stripping model-internal tags and reasoning patterns.
|
||||
///
|
||||
/// Some models (GLM-4.7, etc.) emit XML-tagged internal state like
|
||||
@@ -1364,6 +1432,7 @@ fn recover_tool_calls_from_content(
|
||||
) -> Vec<ToolCall> {
|
||||
let tool_names: std::collections::HashSet<&str> =
|
||||
available_tools.iter().map(|t| t.name.as_str()).collect();
|
||||
let code_regions = find_code_regions(content);
|
||||
let mut calls = Vec::new();
|
||||
|
||||
for (open, close) in &[
|
||||
@@ -1372,15 +1441,23 @@ fn recover_tool_calls_from_content(
|
||||
("<function_call>", "</function_call>"),
|
||||
("<|function_call|>", "<|/function_call|>"),
|
||||
] {
|
||||
let mut remaining = content;
|
||||
while let Some(start) = remaining.find(open) {
|
||||
let mut search_from = 0;
|
||||
while let Some(offset) = content[search_from..].find(open) {
|
||||
let start = search_from + offset;
|
||||
let inner_start = start + open.len();
|
||||
let after = &remaining[inner_start..];
|
||||
let Some(end) = after.find(close) else {
|
||||
let after = &content[inner_start..];
|
||||
let Some(end_offset) = after.find(close) else {
|
||||
break;
|
||||
};
|
||||
let inner = after[..end].trim();
|
||||
remaining = &after[end + close.len()..];
|
||||
let end = inner_start + end_offset;
|
||||
let segment_end = end + close.len();
|
||||
search_from = segment_end;
|
||||
|
||||
if !is_recoverable_tool_call_segment(content, start, segment_end, &code_regions) {
|
||||
continue;
|
||||
}
|
||||
|
||||
let inner = content[inner_start..end].trim();
|
||||
|
||||
if inner.is_empty() {
|
||||
continue;
|
||||
@@ -2313,6 +2390,40 @@ That's my plan."#;
|
||||
assert_eq!(calls[0].name, "tool_list");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_recover_tool_call_in_fenced_code_block_ignored() {
|
||||
let tools = make_tools(&["tool_list"]);
|
||||
let content = "Here is the XML format:\n\n```xml\n<tool_call>tool_list</tool_call>\n```";
|
||||
let calls = recover_tool_calls_from_content(content, &tools);
|
||||
assert!(calls.is_empty());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_recover_tool_call_in_inline_code_ignored() {
|
||||
let tools = make_tools(&["tool_list"]);
|
||||
let content = "Use `<tool_call>tool_list</tool_call>` to illustrate the syntax.";
|
||||
let calls = recover_tool_calls_from_content(content, &tools);
|
||||
assert!(calls.is_empty());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_recover_tool_call_in_blockquote_ignored() {
|
||||
let tools = make_tools(&["tool_list"]);
|
||||
let content = "The page replied:\n> <tool_call>tool_list</tool_call>";
|
||||
let calls = recover_tool_calls_from_content(content, &tools);
|
||||
assert!(calls.is_empty());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_recover_multiline_json_tool_call_on_own_line() {
|
||||
let tools = make_tools(&["memory_search"]);
|
||||
let content = "Let me check.\n\n<tool_call>\n{\"name\": \"memory_search\", \"arguments\": {\"query\": \"test\"}}\n</tool_call>\n\nDone.";
|
||||
let calls = recover_tool_calls_from_content(content, &tools);
|
||||
assert_eq!(calls.len(), 1);
|
||||
assert_eq!(calls[0].name, "memory_search");
|
||||
assert_eq!(calls[0].arguments, serde_json::json!({"query": "test"}));
|
||||
}
|
||||
|
||||
// ---- System prompt building tests (issue #565) ----
|
||||
|
||||
fn make_test_reasoning() -> Reasoning {
|
||||
@@ -3229,4 +3340,85 @@ That's my plan."#;
|
||||
let cleaned = clean_response(&pre_truncated);
|
||||
assert!(cleaned.trim().is_empty());
|
||||
}
|
||||
|
||||
// ---- select_tools truncation guard ----
|
||||
|
||||
/// Mock provider that returns tool calls with a configurable finish_reason.
|
||||
struct TruncatingLlm {
|
||||
finish_reason: crate::llm::FinishReason,
|
||||
}
|
||||
|
||||
#[async_trait::async_trait]
|
||||
impl crate::llm::LlmProvider for TruncatingLlm {
|
||||
fn model_name(&self) -> &str {
|
||||
"truncating-stub"
|
||||
}
|
||||
fn cost_per_token(&self) -> (rust_decimal::Decimal, rust_decimal::Decimal) {
|
||||
(rust_decimal::Decimal::ZERO, rust_decimal::Decimal::ZERO)
|
||||
}
|
||||
async fn complete(
|
||||
&self,
|
||||
_request: crate::llm::CompletionRequest,
|
||||
) -> Result<crate::llm::CompletionResponse, crate::llm::error::LlmError> {
|
||||
unimplemented!()
|
||||
}
|
||||
async fn complete_with_tools(
|
||||
&self,
|
||||
_request: crate::llm::ToolCompletionRequest,
|
||||
) -> Result<crate::llm::ToolCompletionResponse, crate::llm::error::LlmError> {
|
||||
Ok(crate::llm::ToolCompletionResponse {
|
||||
content: Some("I'll write the report.".to_string()),
|
||||
tool_calls: vec![ToolCall {
|
||||
id: "call_1".to_string(),
|
||||
name: "memory_write".to_string(),
|
||||
arguments: serde_json::json!({}),
|
||||
reasoning: None,
|
||||
}],
|
||||
input_tokens: 5000,
|
||||
output_tokens: 1024,
|
||||
finish_reason: self.finish_reason,
|
||||
cache_read_input_tokens: 0,
|
||||
cache_creation_input_tokens: 0,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_select_tools_returns_empty_on_truncation() {
|
||||
let llm = Arc::new(TruncatingLlm {
|
||||
finish_reason: FinishReason::Length,
|
||||
});
|
||||
let reasoning = Reasoning::new(llm);
|
||||
let mut ctx = ReasoningContext::new().with_message(ChatMessage::user("Write a report"));
|
||||
ctx.available_tools.push(ToolDefinition {
|
||||
name: "memory_write".to_string(),
|
||||
description: "Write to memory".to_string(),
|
||||
parameters: serde_json::json!({"type": "object"}),
|
||||
});
|
||||
|
||||
let selections = reasoning.select_tools(&ctx).await.unwrap();
|
||||
assert!(
|
||||
selections.is_empty(),
|
||||
"Truncated tool selections should be discarded (got {} selections)",
|
||||
selections.len()
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_select_tools_returns_selections_when_not_truncated() {
|
||||
let llm = Arc::new(TruncatingLlm {
|
||||
finish_reason: FinishReason::ToolUse,
|
||||
});
|
||||
let reasoning = Reasoning::new(llm);
|
||||
let mut ctx = ReasoningContext::new().with_message(ChatMessage::user("Write a report"));
|
||||
ctx.available_tools.push(ToolDefinition {
|
||||
name: "memory_write".to_string(),
|
||||
description: "Write to memory".to_string(),
|
||||
parameters: serde_json::json!({"type": "object"}),
|
||||
});
|
||||
|
||||
let selections = reasoning.select_tools(&ctx).await.unwrap();
|
||||
assert_eq!(selections.len(), 1);
|
||||
assert_eq!(selections[0].tool_name, "memory_write");
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1158,6 +1158,7 @@ impl<'a> JobDelegate<'a> {
|
||||
Ok(crate::llm::RespondOutput {
|
||||
result: RespondResult::Text(String::new()),
|
||||
usage: crate::llm::TokenUsage::default(),
|
||||
finish_reason: crate::llm::FinishReason::Stop,
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -1283,6 +1284,7 @@ impl<'a> LoopDelegate for JobDelegate<'a> {
|
||||
content: reasoning_text,
|
||||
},
|
||||
usage: crate::llm::TokenUsage::default(),
|
||||
finish_reason: crate::llm::FinishReason::ToolUse,
|
||||
});
|
||||
}
|
||||
Ok(_) => {} // empty selections, fall through
|
||||
|
||||
Reference in New Issue
Block a user