fix(base): work around mempalace diary_write top-level anyOf

Anthropic's tools API rejects top-level anyOf/oneOf/allOf in
input_schema. Mempalace 3.3.x/3.4.0 advertise diary_write with
`anyOf: [{required:[entry]}, {required:[content]}]`, breaking pi
on first prompt with:

  tools.<n>.custom.input_schema: input_schema does not support
  oneOf, allOf, or anyOf at the top level

Patch the installed mcp_server.py after `uv tool install` to drop
the anyOf block and require ["agent_name", "entry"] instead. The
handler still accepts `content` server-side as a kwarg alias, so
callers using either name keep working.

The workaround is idempotent and self-deactivating: once upstream
ships the fix the regex no longer matches and the RUN is a silent
no-op.

Also pin mempalace to 3.4.0 via a new MEMPALACE_VERSION build arg
so future bumps are a deliberate, reviewable diff rather than an
implicit pull of latest (an implicit upgrade is what swept the
broken schema in unannounced).

Refs MemPalace/mempalace#1728, MemPalace/mempalace#1735

CHANGELOG.md

@@ -13,7 +13,38 @@ Pre-v1.0.0 tags followed the pi npm version (`v{pi_version}[letter]`).
 
 ## Unreleased
 
-_(no changes since v1.0.0)_
+_(no changes since v1.0.1)_
+
+## v1.0.1 — 2026-06-10
+
+Patch release. Works around an upstream MemPalace bug that broke pi at
+first prompt against the Anthropic Claude API.
+
+### Fixed
+
+- **`mempalace_diary_write` schema rejected by Anthropic API.** Mempalace
+  3.3.x and 3.4.0 advertise `diary_write`'s `input_schema` with a
+  top-level `anyOf: [{required:[entry]}, {required:[content]}]` to
+  express "either `entry` or `content` must be supplied". Anthropic's
+  tools API rejects top-level `anyOf` / `oneOf` / `allOf` outright, so
+  pi failed to register tools at session start with
+  `tools.<n>.custom.input_schema: input_schema does not support oneOf,
+  allOf, or anyOf at the top level`. `Dockerfile.base` now patches the
+  installed `mcp_server.py` after `uv tool install` to drop the `anyOf`
+  block and require `["agent_name", "entry"]` instead. The mempalace
+  handler still accepts `content` server-side as a kwarg alias, so
+  callers using either name keep working. Tracked upstream:
+  [issue #1728](https://github.com/MemPalace/mempalace/issues/1728),
+  [PR #1735](https://github.com/MemPalace/mempalace/pull/1735).
+  The workaround is idempotent + self-deactivating and will be removed
+  once a fixed mempalace release lands on PyPI.
+
+### Changed
+
+- **Mempalace pinned to 3.4.0** via `MEMPALACE_VERSION` build arg.
+  Future bumps must be a reviewable diff rather than an implicit pull
+  of `latest` (the broken 3.3.x/3.4.0 schema slipping in unannounced
+  is what caused this release).
 
 ## v1.0.0 — 2026-06-09
 

Dockerfile.base

@@ -273,14 +273,49 @@ RUN ARCH=$(case "${TARGETARCH}" in amd64) echo "x86_64" ;; arm64) echo "aarch64"
 # Always installed in the base. Set INSTALL_MEMPALACE=false at base-build
 # time to shave ~300 MB.
 ARG INSTALL_MEMPALACE=true
+# Pin to a known-good version. Bump deliberately, not implicitly: an
+# unpinned install silently swept in mempalace 3.3.x/3.4.0 with a broken
+# diary_write schema (see workaround RUN below + issue #1728). Pinning
+# makes mempalace upgrades a reviewable diff rather than a surprise.
+ARG MEMPALACE_VERSION=3.4.0
 ENV UV_TOOL_DIR=/opt/uv-tools
 ENV UV_TOOL_BIN_DIR=/usr/local/bin
 RUN if [ "${INSTALL_MEMPALACE}" = "true" ]; then \
       mkdir -p /opt/uv-tools && \
-      uv tool install --no-cache mempalace && \
+      uv tool install --no-cache "mempalace==${MEMPALACE_VERSION}" && \
       /opt/uv-tools/mempalace/bin/python -c "import mempalace; print('mempalace', mempalace.__version__ if hasattr(mempalace, '__version__') else 'installed')" ; \
     fi
 
+# ── workaround: strip top-level anyOf from mempalace_diary_write schema ──
+# Mempalace 3.3.x/3.4.0 advertise diary_write's input_schema with a
+# top-level `anyOf: [{required:[entry]}, {required:[content]}]` to express
+# "either entry or content must be supplied". Anthropic's tools API rejects
+# top-level anyOf/oneOf/allOf, so pi/Claude fail at session start with
+# `tools.<n>.custom.input_schema: input_schema does not support oneOf,
+# allOf, or anyOf at the top level`.
+#
+# Patch the advertised schema to require ["agent_name", "entry"] and remove
+# the anyOf block. The handler keeps accepting `content` server-side as a
+# kwarg alias so existing callers still work.
+#
+# Idempotent and self-deactivating: once upstream releases the fix the
+# regex no longer matches and this RUN is a silent no-op.
+# Upstream tracking:
+#   https://github.com/MemPalace/mempalace/issues/1728
+#   https://github.com/MemPalace/mempalace/pull/1735
+# TODO: remove this RUN once a mempalace release containing PR #1735 is on
+# PyPI and installed by the line above.
+RUN if [ "${INSTALL_MEMPALACE}" = "true" ]; then \
+      MP_FILE="$(find /opt/uv-tools/mempalace -path '*/mempalace/mcp_server.py' | head -n1)" && \
+      if [ -z "$MP_FILE" ]; then echo "mempalace mcp_server.py not found" >&2; exit 1; fi && \
+      perl -0777 -i -pe 's/(?:[ \t]*\#[^\n]*\n)*[ \t]*"required":\s*\[\s*"agent_name"\s*\]\s*,\s*\n[ \t]*"anyOf":\s*\[\s*\n[ \t]*\{\s*"required":\s*\[\s*"entry"\s*\]\s*\}\s*,\s*\n[ \t]*\{\s*"required":\s*\[\s*"content"\s*\]\s*\}\s*,?\s*\n[ \t]*\]\s*,\s*\n/            "required": ["agent_name", "entry"],\n/s' "$MP_FILE" && \
+      if grep -q '"required": \["agent_name", "entry"\]' "$MP_FILE"; then \
+        echo "mempalace diary_write anyOf workaround: applied (or already clean)"; \
+      else \
+        echo "WARN: mempalace diary_write anyOf workaround did not match expected schema — upstream may have changed shape" >&2; \
+      fi ; \
+    fi
+
 # ── mempalace-toolkit — bash wrappers for session/docs mining ────────
 ARG INSTALL_MEMPALACE_TOOLKIT=true
 ARG MEMPALACE_TOOLKIT_REF=main