Commit Graph

5 Commits

Author SHA1 Message Date
Tom Boucher
529480b4a5 fix(#3895): delete the mempalace-curator's model frontmatter pin — the fleet's only hardcoded model (#4048)
* test(#3895): no shipped agent may hardcode a model frontmatter pin (failing first)

* fix(#3895): delete the mempalace-curator's model frontmatter pin — the fleet's only hardcoded model

Exactly one of the 34 shipped agents carried 'model: sonnet' in its
frontmatter; every other agent resolves through the model-profile
system. The ship:post dispatch (#2684) resolves per-hook and — per
#2517 — deliberately OMITS model= on inherit so the agent inherits the
orchestrator's model; the frontmatter pin intercepted that inherit
case, silently forcing sonnet where all 33 siblings would inherit, and
operators could not durably remove it (install rewrites live copies
wholesale).

Deleting the line changes nothing for default profiles — the catalog
entry (model-catalog.json agents.gsd-mempalace-curator:
golden/balanced sonnet, budget haiku) preserves today's behavior —
while restoring model_overrides and inherit authority. Pinned by a new
agent-frontmatter guard: no shipped agent may hardcode a model pin,
and the catalog entry must keep existing so the pin's deletion can
never orphan the agent.

* chore(#3895): changeset fragment (pr number backfilled after PR creation)

* chore(#3895): backfill changeset PR number (4048)

---------

Co-authored-by: sim <sim@local>
2026-08-29 14:11:39 -04:00
Tom Boucher
3c61b4a838 enh(#3565): sentinel/contract registry + check:contract-drift lint (#3571)
* enh(#3565): sentinel/contract registry + check:contract-drift lint

* fix(#3565): report artifact-row markers once and dedupe per marker

* docs(#3565): backfill changeset pr number

---------

Co-authored-by: sim <sim@local>
2026-08-16 12:59:08 -04:00
Tom Boucher
d2fa696a30 fix(#3479): treat absent default-true mempalace keys as enabled in every prose gate (#3527)
* fix(#3479): treat absent default-true mempalace keys as enabled in every prose gate

The #2982 absent-key fix (capture_artifacts === false) was applied to only
one of the sibling gates. Five more hand-written gates in the mempalace
skill/command mirrors and the curator agent still used positive presence
('when <key> is true'), silently skipping default-enabled behavior
(mirror_kg, diary_journal) whenever the key was absent from
.planning/config.json — inverted from the registry-declared defaults.

Corrected sites, each now disabled only on an explicit false:
- skills/gsd-mempalace-capture/SKILL.md step 3 (mirror_kg)
- commands/gsd/mempalace-capture.md step 3 (mirror_kg)
- skills/gsd-mempalace-recall/SKILL.md step 3 (mirror_kg)
- commands/gsd/mempalace-recall.md step 3 (mirror_kg)
- agents/gsd-mempalace-curator.md tasks 1+2 (diary_journal, mirror_kg)

Default-false keys (mempalace.enabled, cross_project_tunnels) keep their
positive-presence gates. New #3479 regression cases in
tests/mempalace-capture-gate-default.test.cjs lock each site's absent/explicit-false
boundary and add a registry-parity guard: no gate file may positively gate
any mempalace boolean whose registry-declared default is true.

* chore(#3479): acknowledge curator size growth from the gate rewording

* chore(#3479): add changeset fragment for PR #3527

---------

Co-authored-by: sim <sim@local>
2026-08-14 23:01:15 -04:00
Tom Boucher
ed79902509 feat(#2007): implement mempalace memory_mode kg_backend and replace routing (#2010)
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>
2026-07-05 15:01:22 -04:00
Tom Boucher
a375c4b354 feat(#956): add MemPalace memory capability (ADR-857 feature plug-in) (#1201)
* feat(#956): add MemPalace memory capability (ADR-857 feature plug-in)

Adds an opt-in, default-resilient ADR-857 feature capability that wires
MemPalace (local-first memory: MCP server + CLI) into the GSD loop:
deliberate recall before discuss/plan and verbatim + temporal-KG capture
at phase boundaries. Three memory modes (augment default; kg_backend and
replace forward-declared). Master gate mempalace.enabled (default off);
every hook onError:skip, zero gates; absent/disabled MemPalace => loop
unchanged. Transport is rendered-markdown only — MemPalace runs
out-of-process, no third-party code in gsd-core (ADR-857 §7).

Capability: capabilities/mempalace/ (manifest + 2 fragments), skills
commands/gsd/mempalace-{recall,capture}.md, agent
agents/gsd-mempalace-curator.md. Registration: ns-context router,
utility cluster, KNOWN_SKILLS, help full.md, model-catalog, copilot
install list, size baselines; regenerated capability-registry +
inventory manifest. ship:post wired into ship.md (wire-on-demand).

HELD on #1196: this capability also declares hooks at discuss:pre and
discuss:post, which are structurally un-wireable until the host-loop
conformance model covers the discuss phase (discuss-phase.md is not in
HOST_LOOP_FILES). The phase6-capstone-conformance gate therefore fails
on exactly those two orphaned points by design — see #1196. Once #1196
lands, rebase onto next and the gate goes green with no further change.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs(#956): backfill changeset PR number (#1201)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 02:09:10 -04:00