matevip 07eb625d11 fix(agent): collapse SystemMessages at egress to fix LM Studio 400 (#218) ... Some OpenAI-compatible providers (LM Studio's built-in server, certain strict-mode vLLM / SGLang deployments) reject 400 "System message must be at the beginning" when SystemMessages appear after user / assistant / tool messages. The reasoning loop currently emits four SystemMessage segments — main prompt at index 0, skill catalog inserted at index 1, progress-ledger snapshot and stale-reminder appended at the end of nonHistoryPrefix after the runtime-context UserMessage. The latter two violate the strict shape, so conversations on LM Studio 400 on the first turn (reported in #218). Add MessageNormalizer: collects every SystemMessage in the outbound prompt regardless of position, joins their text with a blank-line separator, and emits a single SystemMessage at index 0. Non-system messages keep their relative order, so AssistantMessage(tool_calls) ↔ ToolResponseMessage adjacency is preserved verbatim (required by strict pair validators). Wire it into doStreamCall as the first pre-egress step so every node (reasoning, step-execution, summarizing, plan-generation, limit-exceeded) inherits the fix without per-node changes, and any future node that emits multiple SystemMessages stays compliant. The transformation is semantically equivalent on permissive providers (OpenAI, DashScope, Ollama, DeepSeek, Kimi, Doubao, GLM) — the merged token sequence matches what they would have seen across N SystemMessages — and safe on non-OpenAI protocols (Anthropic, Vertex / Gemini), whose adapters already extract SystemMessages into a top-level system field and receive an identical payload. Kill switch: -Dmateclaw.llm.message-normalizer.enabled=false reverts to the prior behavior for emergency rollback. Tests: 11 unit tests on MessageNormalizer cover empty / no-system / canonical / mid-list / tail / blanks / tool-pair preservation / Prompt option-reference preservation / kill switch. 1 wiring test pins the call site in doStreamCall. Full vip.mate.agent.** suite (504 tests) stays green. Closes #218.		2026-05-25 17:57:03 +08:00
..
binding	feat(skill): automatic lifecycle archival for idle skills	2026-05-19 09:55:59 +08:00
context	feat(agent): age-based compaction of older tool-response bodies	2026-05-24 23:00:11 +08:00
delegation	chore(test): backfill mateclaw-server/src/test/ that earlier PRIVATE_ITEMS pattern accidentally excluded	2026-05-12 17:38:08 +08:00
graph	fix(agent): collapse SystemMessages at egress to fix LM Studio 400 (#218)	2026-05-25 17:57:03 +08:00
progress	feat(agent): inject stale-ledger reminder when the model stops updating	2026-05-24 23:00:35 +08:00
service	chore(test): backfill mateclaw-server/src/test/ that earlier PRIVATE_ITEMS pattern accidentally excluded	2026-05-12 17:38:08 +08:00
AgentAuthoringToolTest.java	feat(agent): digital-employee builder skill to auto-create agents and chain them into a workflow (#165)	2026-05-21 16:26:04 +08:00
AgentGraphBuilderBasePathResolutionTest.java	fix(tool): close three sandbox follow-up gaps surfaced by review	2026-05-25 17:55:56 +08:00
AgentGraphBuilderPreferenceTest.java	chore: sync multiple commits from private dev	2026-04-19 18:37:44 +08:00
AgentServiceUniquenessTest.java	chore(test): backfill mateclaw-server/src/test/ that earlier PRIVATE_ITEMS pattern accidentally excluded	2026-05-12 17:38:08 +08:00
AgentToolSetTest.java	chore(test): backfill mateclaw-server/src/test/ that earlier PRIVATE_ITEMS pattern accidentally excluded	2026-05-12 17:38:08 +08:00
BaseAgentApprovalSanitizationTest.java	chore(test): backfill mateclaw-server/src/test/ that earlier PRIVATE_ITEMS pattern accidentally excluded	2026-05-12 17:38:08 +08:00
BaseAgentCronIsolationTest.java	fix(cron): isolate scheduled-job runs from shared conversation (#142)	2026-05-17 07:58:10 +08:00
BaseAgentDirectToolHistoryScrubTest.java	chore(test): backfill mateclaw-server/src/test/ that earlier PRIVATE_ITEMS pattern accidentally excluded	2026-05-12 17:38:08 +08:00
BaseAgentHeadOrphanRepairTest.java	fix(agent): make head-orphan repair order-sensitive — a later same-id assistant does not redeem an earlier orphan	2026-05-13 09:03:16 +08:00
BaseAgentMultimodalSkipNoticeTest.java	chore(test): backfill mateclaw-server/src/test/ that earlier PRIVATE_ITEMS pattern accidentally excluded	2026-05-12 17:38:08 +08:00
BaseAgentToolCallReplayTest.java	fix(agent): structured tool-call replay + final-answer-only content (#120)	2026-05-14 07:46:30 +08:00
GraphEventPublisherIterationTest.java	chore(test): backfill mateclaw-server/src/test/ that earlier PRIVATE_ITEMS pattern accidentally excluded	2026-05-12 17:38:08 +08:00