Merge remote-tracking branch 'origin/master' into fix/subagent-depth-budget

# Conflicts:
#	website/zh-CN/api/harness/agents.md
#	website/zh-CN/api/harness/events.md
#	website/zh-CN/api/harness/sessions.md
#	website/zh-CN/api/harness/subagents.md

examples/package.json

@@ -14,6 +14,7 @@
     "@deepseek-ai/dsh-cli-demo": "workspace:*",
     "@deepseek-ai/dsh-code-runtime-worker": "workspace:*",
     "@deepseek-ai/dsh-compact-basic": "workspace:*",
+    "@deepseek-ai/dsh-compact-tool-result-prune": "workspace:*",
     "@deepseek-ai/dsh-fs-local": "workspace:*",
     "@deepseek-ai/dsh-fs-policy": "workspace:*",
     "@deepseek-ai/dsh-fs-sandbox": "workspace:^",

examples/repl-agent/README.md

@@ -50,6 +50,7 @@ This example is a thin leaf `cordis.yml`: it picks the swappable backends, loads
 | `llm-deepseek` | real `LlmAdapter` via config (`!!js process.env.…` secrets); swap one line to `@deepseek-ai/dsh-llm-pi-ai` for the library-backed twin |
 | `bash` (`dsh-bash-local`) | the executor implementation — the swappable half of the bash seam. The model-facing `bash` schema (`tool-bash`) and generic `task_*` controls (`tool-tasks`) come from `dsh-agent-spine-demo`, so only the executor is a leaf choice |
 | `stdio-agent` (`@deepseek-ai/dsh-stdio-demo`) | the app bundle: the agent-spine demo + JSONL persistence + the configured terminal channel + a pre-created `main` agent. This leaf fixes `ui.mode` to `readline`; `tui-agent` owns the corresponding TUI leaf |
+| `token-meter`, `tool-result-prune`, `compact-basic` | replay-aware pressure, model-free oversized tool-result pruning, and LLM summary compaction. Pruning runs only after a compaction trigger qualifies and can avoid the summarization call |
 | `subagent`, `subagent-spawn`, `subagent-fork` | the subagent provider registry plus the two in-process backends: a fresh child and a child seeded with the parent's completed-turn prefix |
 | `tool-subagent`, `tool-subagent-fork` | two model-facing `dsh-tool-subagent` loads, each bound to a different provider and exposed under a distinct tool name (`subagent`, `subagent_fork`) |
 | `workflow-workerthread`, `tool-workflow` | the worker-thread workflow engine and its model-facing `workflow` tool, with child calls routed through the spawn backend |
@@ -61,7 +62,7 @@ This example is a thin leaf `cordis.yml`: it picks the swappable backends, loads
 - `tests/full-loop.e2e.ts` — the canary: real model runs `echo e2e-ok` through the real bash tool; asserts `tool/call`/`tool/result` session events and the final answer.
 - `tests/coding-task.e2e.ts` — the swebench-style smoke: a temp dir holds `add.js` (with `a - b` where `a + b` belongs) and a failing `add.test.js`; the agent must fix the bug and verify. The test re-runs `node add.test.js` ITSELF and inspects the files — agent claims are not trusted.
 - `tests/resume.e2e.ts` — durable continuity across processes: run 1 tells the real model a secret code and persists the turn to a temp JSONL root, then the whole context is disposed; run 2 is a fresh context over the same root that RESUMES the session id and asks the model to recall the code. The recall can only come from the rehydrated log.
-- `tests/compaction.e2e.ts` — the compaction smoke: a real multi-step bash task runs with a deliberately tiny context window so the auto-compaction listener fires MID-SESSION. Verifies the WORLD — a `compact/start…end` pair landed in the real log, the surface shrank (a replace node shadowed older nodes), and the agent still produced a correct final answer after compaction.
+- `tests/compaction.e2e.ts` — the compaction smoke: a real multi-step bash task runs with a deliberately tiny context window so automatic pruning or summary compaction fires mid-session. It verifies the world: a replayable surface replacement lands, summary brackets are complete when summarization is needed, the surface shrinks, and the agent still produces a correct final answer.
 - `tests/todo-write.e2e.ts` — a real model drives the real `todo_write` tool and the test verifies the resulting `todo/write` session event.
 
 These self-skip without `DEEPSEEK_API_KEY`. `tests/code-mode.e2e.ts` is the with-key Code Mode proof — a real model, a two-tool task, asserting the wire tool list was exactly `[run_code]`, the `tool/code-dispatch` events landed under the parent call, and the curated answer came back. The keyless Loader smokes run in the default e2e gate: `tests/keyless-smoke.e2e.ts` and `tests/code-mode-keyless-smoke.e2e.ts`.

examples/repl-agent/composition.md

@@ -3,7 +3,7 @@
 
 # REPL Agent App Composition
 
-The REPL agent demo adds the real DeepSeek adapter, filesystem tools, todo_write, compaction, and both subagent transports on top of the stdio app package.
+The REPL agent demo adds the real DeepSeek adapter, filesystem tools, todo_write, tool-result pruning, compaction, and both subagent transports on top of the stdio app package.
 
 ```mermaid
 flowchart LR
@@ -25,6 +25,8 @@ flowchart LR
   bundle_agent_core --> spine_loop["ctx.agents + ctx.agentLoop"]
   plugin_repl_token_meter["token-meter<br/>@deepseek-ai/dsh-token-meter"]
   cfg --> plugin_repl_token_meter
+  plugin_repl_tool_result_prune["tool-result-prune<br/>@deepseek-ai/dsh-compact-tool-result-prune"]
+  cfg --> plugin_repl_tool_result_prune
   plugin_repl_compact_basic["compact-basic<br/>@deepseek-ai/dsh-compact-basic"]
   cfg --> plugin_repl_compact_basic
   plugin_repl_subagent["subagent<br/>@deepseek-ai/dsh-subagent"]
@@ -66,6 +68,7 @@ flowchart LR
 | `bash` | `@deepseek-ai/dsh-bash-local` |
 | `stdio-agent` | `@deepseek-ai/dsh-stdio-demo` |
 | `token-meter` | `@deepseek-ai/dsh-token-meter` |
+| `tool-result-prune` | `@deepseek-ai/dsh-compact-tool-result-prune` |
 | `compact-basic` | `@deepseek-ai/dsh-compact-basic` |
 | `subagent` | `@deepseek-ai/dsh-subagent` |
 | `subagent-spawn` | `@deepseek-ai/dsh-subagent-spawn` |

examples/repl-agent/cordis.yml

@@ -51,6 +51,10 @@
 - id: token-meter
   name: '@deepseek-ai/dsh-token-meter'
 
+# Prune oversized tool output without a model call before summary compaction.
+- id: tool-result-prune
+  name: '@deepseek-ai/dsh-compact-tool-result-prune'
+
 # Summarize an older range after measured pressure or a canonical provider overflow.
 # Service-wide policy provides pressure, retention, and one overflow-retry default.
 - id: compact-basic

examples/repl-agent/tests/harness.ts

@@ -9,6 +9,7 @@ import * as ToolTodo from '@deepseek-ai/dsh-tool-todo'
 import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
 import TokenMeterService from '@deepseek-ai/dsh-token-meter'
 import type { TokenMeterConfig } from '@deepseek-ai/dsh-token-meter'
+import ToolResultPruneService from '@deepseek-ai/dsh-compact-tool-result-prune'
 import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
 import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic'
 import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic'
@@ -63,6 +64,7 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio
   // backend, with a lower context window so a short real session crosses the threshold.
   if (options.compact !== undefined) {
     await ctx.plugin(TokenMeterService, options.tokenMeter)
+    await ctx.plugin(ToolResultPruneService)
     await ctx.plugin(BasicCompactService, options.compact)
   }
   // Durable JSONL persistence is opt-in: only the resume e2e needs it, and the