Merge branch 'codex/goal-commands' into codex/ralph-tool

# Conflicts: # examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md # examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json # examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md # examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json # examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md # examples/acp-agent/tests/snapshots/model-switching/tool-schemas.expected.json # examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.expected.json # examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json # examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json # examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.expected.md # examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.expected.json # scripts/gen-tool-catalog.ts
2026-07-20 21:05:05 +08:00
parent 60926e3257 d121f87def
commit 30d2ec4a95
466 changed files with 13130 additions and 8908 deletions
@@ -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`, `tool-ralph` | the worker-thread engine, general model-written `workflow` tool, and separate fixed fresh-agent `ralph` consumer, with children routed through spawn |
@@ -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`.