basic-memory 0.21.5__tar.gz → 0.22.0__tar.gz

basic_memory-0.22.0/.agents/plugins/marketplace.json

@@ -0,0 +1,20 @@
+{
+  "name": "basic-memory-local",
+  "interface": {
+    "displayName": "Basic Memory Local"
+  },
+  "plugins": [
+    {
+      "name": "codex",
+      "source": {
+        "source": "local",
+        "path": "./plugins/codex"
+      },
+      "policy": {
+        "installation": "AVAILABLE",
+        "authentication": "ON_INSTALL"
+      },
+      "category": "Developer Tools"
+    }
+  ]
+}

basic_memory-0.22.0/.agents/skills/adversarial-review/SKILL.md

@@ -0,0 +1,159 @@
+---
+name: adversarial-review
+description: Cross-vendor adversarial code review of the current branch. Two different model families (Claude + Codex/GPT) review the diff independently, then try to refute each other's findings; survivors are reported by confidence. Runs from either Claude Code or Codex. Use when the user asks for an adversarial review, a cross-model / second-opinion review, or wants high-confidence findings before merging. Report-only — never auto-applies fixes.
+license: MIT
+---
+
+# Adversarial code review
+
+Two reviewers from **different model families** — **Claude** and **Codex/GPT** — review the
+same diff independently, then each tries to **refute** the other's findings. A finding's
+confidence comes from whether it survives that cross-examination. This kills the two failure
+modes of solo LLM review: self-ratification (a model won't critique its own work) and
+confident false positives.
+
+## You are the orchestrator — and one of the two reviewers
+
+This skill runs from **either** Claude Code **or** Codex. First, **identify which model
+family you are** (Claude or Codex/GPT). Then:
+
+- **You** are reviewer #1. You review **natively**, in this session, using your own tools.
+- **The other family** is reviewer #2. You invoke it as a **subprocess CLI** for an
+  independent pass: a fresh process, no shared context — that independence is the point.
+
+The CLI for "the other model":
+
+| If you are… | Invoke the other via… |
+|-------------|------------------------|
+| **Claude**  | `codex exec` (GPT)     |
+| **Codex**   | `claude -p` (Claude)   |
+
+Everything else in the flow is symmetric. Resolve the `prompts/` and `schemas/` paths
+below relative to **this skill's own directory** (where this SKILL.md lives).
+
+## Inputs
+
+Two independent, optional inputs:
+
+- `BASE` — the ref to diff against. Default `main`.
+- `SCOPE` — a pathspec to narrow the review (e.g. `src/basic_memory`). Default: none (whole diff).
+
+These are separate: a ref and a pathspec are not interchangeable. Build the **canonical diff
+command** once in preflight and reuse it everywhere below — never re-spell the diff inline
+(the scattered, inconsistent spelling is what broke earlier). Build it as an **argv array**,
+not a string, so a `$SCOPE` containing spaces or glob characters survives intact:
+
+```bash
+BASE="${BASE:-main}"
+DIFF=(git diff "$BASE...HEAD")          # argv array — never a scalar string
+[ -n "$SCOPE" ] && DIFF+=(-- "$SCOPE")  # pathspec stays one argument even with spaces
+DIFF_STR=$(printf '%q ' "${DIFF[@]}")   # shell-quoted rendering, for embedding in a prompt
+```
+
+To **run** it, use `"${DIFF[@]}"` (quoted, no word-splitting). To **embed** it as text inside
+a subprocess prompt, use `$DIFF_STR`.
+
+## Preflight
+
+0. Set `SKILL_DIR` to the directory this SKILL.md lives in. Canonical location is
+   `.agents/skills/adversarial-review` (the shared agent-skills store); Claude Code reaches it
+   via the `.claude/skills/adversarial-review` symlink, Codex via its own skills path. The
+   `prompts/` and `schemas/` subdirs are siblings of this file in every case.
+1. Confirm the *other* model's CLI is on PATH (`codex` if you're Claude, `claude` if you're
+   Codex). If it's missing, tell the user the panel falls back to single-model (which loses
+   the cross-vendor benefit) and ask whether to proceed or stop.
+2. Run `"${DIFF[@]}"`. If it prints nothing, report "nothing to review against $BASE"
+   (mention `$SCOPE` if set) and stop.
+3. `RUN=$(mktemp -d)` — scratch dir for the other model's output. Transient, never committed.
+   No persisted artifacts, no state file.
+
+## Phase 0 — Deterministic gates (before the models)
+
+Models are statistically blind to negation ("never do X"). Enforce mechanical house rules
+with tools, not prompts, and treat hits as high-confidence facts (reported separately from
+model findings):
+
+- `just lint` and `just typecheck` if the diff touches `src/`.
+- Grep the diff for catchable house-rule violations: `getattr(.*,.*,` defaults, bare
+  `except:` / `except Exception: pass`, function-scope imports.
+
+## Phase 1 — Independent review (you + the other model, concurrently)
+
+Both reviewers get the same brief: `prompts/review.md` + the repo's `CLAUDE.md` house rules,
+reviewing the diff from `"${DIFF[@]}"`. Both emit findings matching `schemas/findings.schema.json`.
+
+**Your native pass:** review as yourself, following `prompts/review.md`. Hold your findings
+as that JSON shape.
+
+**The other model's pass** — run, from the repo root, the row that matches you:
+
+Always redirect `codex` stdin from `/dev/null` — if stdin is a pipe (e.g. the call gets
+backgrounded), `codex exec` blocks "Reading additional input from stdin..." and fails.
+
+```bash
+# You are Claude → run Codex:
+codex exec -s read-only \
+  --output-schema "$SKILL_DIR/schemas/findings.schema.json" \
+  -o "$RUN/other_findings.json" \
+  "$(cat "$SKILL_DIR/prompts/review.md")
+
+Review the diff: $DIFF_STR" </dev/null
+
+# You are Codex → run Claude (read-only via plan mode; parse the JSON block it returns):
+claude -p --permission-mode plan --output-format json \
+  "$(cat "$SKILL_DIR/prompts/review.md")
+
+Review the diff: $DIFF_STR
+Return ONLY a JSON object matching this schema:
+$(cat "$SKILL_DIR/schemas/findings.schema.json")" </dev/null > "$RUN/other_raw.json"
+# claude --output-format json output shape varies by CLI version: it may be a JSON ARRAY
+# of event objects, OR a single result object. Normalize before reading: if it's an array,
+# take the element with type=='result'; otherwise use the object as-is. Then read its
+# .result string, strip the ```json fence if present, and parse that.
+# (Verified empirically: the CLI in this environment emits the array form.)
+```
+
+> Runtime note for Codex orchestrating: `claude -p` needs network access, which Codex's
+> default sandbox blocks. Run it from a Codex session whose project is trusted with network
+> allowed (or approve the `claude` call when prompted). Keep Codex's own sandbox on — do not
+> bypass it just to reach the network.
+
+Tag each finding with its origin (`claude` / `codex`).
+
+## Phase 2 — Cross-refute
+
+Each model tries to refute the *other's* findings, per `prompts/refute.md`
+(verdicts match `schemas/verdicts.schema.json`).
+
+- **You** refute the other model's findings natively.
+- **The other model** refutes *your* findings — invoke it again the same way (swap
+  `prompts/review.md` for `prompts/refute.md`, append your findings JSON **and `$DIFF_STR`**
+  so it judges against the right base and scope, and for Codex use
+  `--output-schema "$SKILL_DIR/schemas/verdicts.schema.json"`).
+
+Match verdicts to findings by `id`.
+
+## Phase 3 — Synthesize and report (no auto-fix)
+
+Merge, dedupe (same file + overlapping lines + same root cause = one finding), assign
+confidence from provenance:
+
+- **High** — both models raised it independently, OR one raised it and the other upheld it.
+- **Medium** — one raised it; the other could not refute it but did not independently find it.
+- **Low / contested** — one raised it and the other **refuted** it. Keep it, show both sides,
+  let the human judge. Never silently drop a contested finding.
+- Deterministic-gate hits are reported as facts, separate from the model panel.
+
+Rank by `severity × confidence`. Present a compact table: `severity | confidence | file:line
+| claim | found-by / upheld-or-refuted-by`. Expand the high-confidence ones with `why` and
+any suggested fix.
+
+End by asking which findings, if any, to fix. **Do not edit code until the user picks.**
+Convergence between the models is not correctness — your job is to surface a ranked,
+cross-examined list, not to declare the branch clean.
+
+## Deliberately NOT done
+
+- No loop-until-both-agree (models converge by going silent, not by being right).
+- No persisted artifacts / state machine — the scratch dir is thrown away.
+- No auto-applying fixes.

basic_memory-0.22.0/.agents/skills/adversarial-review/prompts/refute.md

@@ -0,0 +1,22 @@
+# Refute the other reviewer
+
+A different reviewer (a different model family) produced the findings below against the
+same diff under review (the exact `git diff` command is provided with the findings). Your
+job is to try to **refute** each one.
+
+Default to skepticism: assume a finding is wrong until the code proves it right. A finding
+that survives a genuine attempt to disprove it is worth far more than one nobody checked.
+
+For each finding, read the actual code it points at and return a verdict:
+
+- **refuted** — the claim is wrong, the code does not do what the finding says, the case
+  cannot occur, or it is pure style with no correctness impact. Cite the specific code or
+  fact that disproves it.
+- **upheld** — you tried to refute it and could not; the finding is real.
+- **partial** — the underlying issue is real but the finding mis-states the severity or
+  scope. Explain, and set `corrected_severity` if the severity should change.
+
+Do not be agreeable for its own sake, and do not refute for its own sake. Follow the code.
+
+Return ONLY the structured verdicts object conforming to the provided schema. Every
+verdict's `id` must match the `id` of the finding it judges.

basic_memory-0.22.0/.agents/skills/adversarial-review/prompts/review.md

@@ -0,0 +1,39 @@
+# Adversarial reviewer
+
+You are an independent, skeptical code reviewer. Another agent wrote this code; your
+job is to find what is actually wrong with it — not to praise it, not to rubber-stamp it.
+
+You are reviewing a specific diff — the exact `git diff` command to run is provided at the
+end of this prompt by the orchestrator. Run it, then read the changed files in full for
+context, not just the hunks.
+
+## What to look for, in priority order
+
+1. **Correctness** — logic errors, wrong conditions, off-by-one, unhandled `None`,
+   broken async/await, races, resource leaks, incorrect error handling.
+2. **Security** — injection, path traversal, secret leakage, missing authz, unsafe
+   deserialization.
+3. **House rules** (this repo's `CLAUDE.md`/`AGENTS.md` — these are hard rules):
+   - No swallowed exceptions / no silent fallback logic. Code must fail fast.
+   - Imports at the top of the file unless deferral is justified in a comment.
+   - No speculative `getattr(obj, "attr", default)` to paper over unknown attributes.
+   - Repository pattern for data access; MCP tools talk to API routers via the httpx
+     ASGI client, not directly to services.
+   - 100-char lines; full type annotations; async SQLAlchemy 2.0; Pydantic v2.
+   - New code needs tests (coverage stays at 100%).
+4. **Performance** — N+1 queries, work inside hot loops, sync I/O on the async path.
+5. **Maintainability** — only when it materially risks a bug. Do not report pure style.
+
+## Rules of engagement
+
+- Every finding MUST be falsifiable: cite the specific file, line, and the code that
+  triggers it. "This could be cleaner" is not a finding.
+- Do not invent issues to seem thorough. An empty findings list is a valid, good result.
+- Watch your own negation blindness: when a rule says "never do X," check the diff for X
+  explicitly rather than trusting a gestalt impression.
+- Prefer few high-confidence findings over many speculative ones.
+- Assign severity honestly: `critical` = data loss/security/crash in normal use;
+  `high` = wrong behavior on a common path; `medium` = wrong on an edge case or a real
+  house-rule violation; `low` = minor.
+
+Return ONLY the structured findings object conforming to the provided schema.

basic_memory-0.22.0/.agents/skills/adversarial-review/schemas/findings.schema.json

@@ -0,0 +1,52 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "AdversarialReviewFindings",
+  "description": "Structured output for one reviewer's pass over a diff.",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["findings"],
+  "properties": {
+    "findings": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": ["id", "file", "line", "severity", "category", "claim", "why", "suggested_fix"],
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Short stable slug for this finding, e.g. 'swallowed-exc-sync-service'."
+          },
+          "file": {
+            "type": "string",
+            "description": "Path relative to repo root."
+          },
+          "line": {
+            "type": "integer",
+            "description": "Best line number in the new file, or 0 if not line-specific."
+          },
+          "severity": {
+            "type": "string",
+            "enum": ["critical", "high", "medium", "low"]
+          },
+          "category": {
+            "type": "string",
+            "enum": ["correctness", "security", "house-rule", "performance", "maintainability"]
+          },
+          "claim": {
+            "type": "string",
+            "description": "One sentence: what is wrong."
+          },
+          "why": {
+            "type": "string",
+            "description": "Concrete reasoning + the specific code that triggers it. Must be falsifiable, not vibes."
+          },
+          "suggested_fix": {
+            "type": ["string", "null"],
+            "description": "The smallest change that resolves it, or null if none is obvious."
+          }
+        }
+      }
+    }
+  }
+}

basic_memory-0.22.0/.agents/skills/adversarial-review/schemas/verdicts.schema.json

@@ -0,0 +1,38 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "AdversarialReviewVerdicts",
+  "description": "One reviewer's attempt to refute another reviewer's findings.",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["verdicts"],
+  "properties": {
+    "verdicts": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": ["id", "verdict", "reasoning", "corrected_severity"],
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The id of the finding being judged (must match the input finding's id)."
+          },
+          "verdict": {
+            "type": "string",
+            "enum": ["upheld", "refuted", "partial"],
+            "description": "upheld = the finding is real; refuted = it is wrong or a non-issue; partial = real but mis-scoped/wrong-severity."
+          },
+          "reasoning": {
+            "type": "string",
+            "description": "Why. For refuted, cite the specific code or fact that disproves the claim."
+          },
+          "corrected_severity": {
+            "type": ["string", "null"],
+            "enum": ["critical", "high", "medium", "low", null],
+            "description": "Set only when verdict is 'partial' and severity should change; otherwise null."
+          }
+        }
+      }
+    }
+  }
+}

basic_memory-0.22.0/.agents/skills/code-review/SKILL.md

@@ -0,0 +1,68 @@
+---
+name: code-review
+description: Use when reviewing Basic Machines code for house style, architecture risk, pre-merge hardening, or whether a change fits basic-memory/basic-memory-cloud conventions.
+license: MIT
+---
+
+# Basic Machines Review
+
+Use this skill for repo-local review passes where ordinary code review needs Basic Machines
+house style and architecture judgment. Report findings only; do not edit code unless the user
+asks you to fix specific findings.
+
+## Scope
+
+Review the current diff or named files against:
+
+- The repo's `AGENTS.md` / `CLAUDE.md`
+- `docs/ENGINEERING_STYLE.md`
+- The touched code paths and tests
+
+Apply only the guidance for the active repo. In `basic-memory`, prioritize local-first
+file/database/MCP boundaries. In `basic-memory-cloud`, prioritize tenant/workspace isolation,
+cloud worker behavior, and web-v2 state/runtime boundaries.
+
+## Review Rubric
+
+Report only concrete, falsifiable risks:
+
+- **Cognitive load:** Is the change harder to understand than the problem requires?
+- **Change propagation:** Will one product change force edits across unrelated layers?
+- **Knowledge duplication:** Is the same rule encoded in multiple places that can drift?
+- **Accidental complexity:** Did the change add abstractions, fallbacks, or state without need?
+- **Dependency direction:** Are API/MCP/CLI, services, repositories, and UI stores respecting
+  their intended boundaries?
+- **Domain model distortion:** Do names and types still match the product concept, or did a
+  transport/storage detail leak into the domain?
+- **Test oracle quality:** Would the tests fail for the bug or regression the change claims to
+  protect against?
+
+## House Rules To Check Explicitly
+
+- No speculative `getattr(obj, "attr", default)` for unknown model shapes.
+- No broad exception swallowing, warning-only failure paths, or hidden fallback behavior.
+- No casts or `Any` that hide an unclear type relationship.
+- Dataclasses for internal value/result objects; Pydantic at validation/serialization
+  boundaries.
+- Narrow `Protocol`s when only a capability is needed.
+- Explicit async/resource ownership, cancellation, and cleanup.
+- Meaningful regression tests or verification for risky changes.
+- Comments explain why, not what.
+
+## Reporting Format
+
+Lead with findings ordered by severity. Each finding should include:
+
+| Severity | Use for |
+| -------- | ------- |
+| `high` | A likely correctness, security, data-loss, or tenant/workspace isolation failure |
+| `medium` | A concrete maintainability or boundary risk that can cause future defects |
+| `low` | A minor consistency issue, ambiguous guidance, or review-only cleanup |
+
+```text
+severity | file:line | risk category | claim
+Why: concrete behavior or code path that proves the risk.
+Fix: smallest practical change, or "none obvious" if the risk needs product input.
+```
+
+If there are no findings, say so and note any verification gaps that remain.

basic_memory-0.22.0/.agents/skills/fix-pr-issues/SKILL.md

@@ -0,0 +1,48 @@
+---
+name: fix-pr-issues
+description: Use when addressing Basic Memory pull request feedback, failed checks, or BM Bossbot blockers from Codex.
+---
+
+# Fix Basic Memory PR Issues
+
+Resolve PR feedback and failed checks, then wait for BM Bossbot to approve the
+new head SHA. This skill never merges a PR.
+
+## Gather
+
+1. Identify the PR:
+   - `gh pr view --json number,url,headRefOid,mergeStateStatus,statusCheckRollup`
+
+2. Collect feedback:
+   - PR comments and review summaries
+   - inline review comments and unresolved review threads
+   - failed GitHub Actions jobs and relevant logs
+   - the managed `BM_BOSSBOT_SUMMARY` block in the PR body
+
+3. Build a short issue ledger:
+   - source
+   - concrete problem
+   - expected fix
+   - verification needed
+
+## Fix
+
+1. Address one ledger item at a time.
+2. Read each file in full before editing it.
+3. Keep diffs narrow and preserve unrelated user changes.
+4. Run the smallest meaningful verification first, then widen as needed.
+5. Commit with `git commit -s` when code or docs changed.
+
+## Push And Recheck
+
+1. Push the branch.
+2. Watch checks for the new `headRefOid`.
+3. Wait for the required `BM Bossbot Approval` status to pass on that exact SHA.
+4. If BM Bossbot reviews an older SHA, treat the approval as stale and keep
+   waiting for the current one.
+
+## Reply
+
+For each addressed comment or blocker, reply with the fix commit, verification
+run, and current BM Bossbot status. Do not resolve or dismiss substantive
+feedback without evidence.

basic_memory-0.22.0/.agents/skills/fix-pr-issues/agents/openai.yaml

@@ -0,0 +1,7 @@
+interface:
+  display_name: "Fix PR Issues"
+  short_description: "Address PR feedback and BM Bossbot blockers"
+  icon_small: "./assets/icon.svg"
+  icon_large: "./assets/icon.svg"
+  brand_color: "#2563EB"
+  default_prompt: "Use $fix-pr-issues to address PR feedback and wait for BM Bossbot Approval on the latest head SHA."

basic_memory-0.22.0/.agents/skills/fix-pr-issues/assets/icon.svg

@@ -0,0 +1,5 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="128" height="128" viewBox="0 0 24 24" fill="none" stroke="#111827" stroke-width="1.8" stroke-linecap="round" stroke-linejoin="round">
+  <path d="M3 12h4l2-6 4 12 2-6h6"/>
+  <path d="M4 20h16"/>
+</svg>
+