ed79902509
Wire the two forward-declared mempalace.memory_mode modes so they actually route recall/capture instead of silently behaving as `augment`: - kg_backend: the palace temporal KG is the primary knowledge-graph source; native .planning/graphs/ is the fallback. Non-KG drawer recall stays additive. - replace: recall resolves through the palace as the source of truth; native artifacts are the fallback. Every mode stays onError:skip and default-resilient — an unreachable palace degrades to native memory and GSD keeps writing .planning/graphs/, so no memory is lost. Cross-mode .planning/graphs/ migration remains a documented open question (PRD/ADR §17), out of scope here. Surfaces updated (instruction-only contract): recall/capture commands (+ generated skills), discuss/wave fragments, curator agent, capability.json schema. Docs: how-to Step 3, CONFIGURATION, FEATURES, CONTEXT glossary. Regenerated capability-registry, golden install-parity fixtures (mempalace hashes only), agent-size-baseline. Added a routing-contract + cross-surface parity test. Incidental (folded per no-defer rule): removed pre-existing unused imports (spawnSync in capability-registry.test.cjs; fs in issue-498-package-identity.test.cjs) that eslint flagged in/alongside the touched files. Closes #2007 Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
23 lines
2.3 KiB
Markdown
23 lines
2.3 KiB
Markdown
<!--
|
||
MemPalace capability — contribution fragment.
|
||
Rendered into the discuss:pre orchestrator prompt when `mempalace.recall_on_discuss` is true.
|
||
Contributes DATA (recall instructions), not control flow. onError: skip — never blocks discussion.
|
||
-->
|
||
### Memory recall (MemPalace)
|
||
|
||
**Gate first.** Read `.planning/config.json`. If `mempalace.enabled` is not `true`, or `mempalace.recall_on_discuss` is `false`, **skip this entire section** and continue the discussion unchanged. (This contribution is only injected when the capability is enabled; the `recall_on_discuss` check lets you turn discuss-time recall off without disabling the rest of the capability.)
|
||
|
||
Otherwise — before gathering new context, surface what you already know. This is read-only and side-effect-free; if MemPalace is unreachable, note "memory unavailable" and continue — recall never blocks discussion.
|
||
|
||
1. **Resolve the wing.** Use `mempalace.wing` if set; otherwise derive it from `project_code` (fall back to the project directory name).
|
||
2. **Wake up (cheap, ~600–900 tokens).**
|
||
- Interactive run → call `mempalace_search` after a wake-up read of the wing.
|
||
- Headless/cron run (no MCP server) → run `mempalace wake-up --wing <wing>` via the CLI.
|
||
3. **Targeted recall.** Search the palace for prior work on this phase's topic:
|
||
- Interactive → `mempalace_search(query=<phase topic>, wing=<wing>)` and, when `mempalace.mirror_kg` is on, `mempalace_kg_query` / `mempalace_kg_timeline` for decision facts and their validity windows.
|
||
- Headless → `mempalace search "<phase topic>" --wing <wing>`.
|
||
4. **Mode awareness** (`mempalace.memory_mode`). `augment` (default): the palace is an *additional* layer — never skip `.planning/graphs/` or STATE. `kg_backend`: query the palace's temporal KG as the *primary* graph source, with `.planning/graphs/` as fallback. `replace`: resolve recall *through the palace as the source of truth*, native memory as fallback. In every mode an unreachable palace falls back to native memory — recall never blocks.
|
||
5. **Surface, don't dump.** Fold the top relevant drawers, decisions, patterns, and *surprises* into the discussion as prior context — cite drawer/fact provenance. Do not paste raw search output.
|
||
|
||
If any MemPalace call errors or times out, skip the rest of recall and proceed with discussion as normal.
|