Pre release fixups - #5
Merged
Merged
Conversation
added 20 commits
February 10, 2025 12:11
6 tasks
phernandez
added a commit
that referenced
this pull request
May 29, 2026
Resolves the 8 self-review findings on PR #865: session-start.sh: - Wire recallTimeframe into a new "Recent sessions" query (--after_date) — it was parsed but unused after the Phase 4 rewrite. The brief now surfaces recent session checkpoints (the resume cursor), which is the one query the recency window legitimately applies to. (#1) - Guard secondaryProjects/teamProjects JSON types — a string value was iterated character-by-character into bogus per-char queries. (#3) - A configured-but-unreachable/misnamed primaryProject now emits a one-line "couldn't read" signal instead of a silent blank brief. (#7) pre-compact.sh: - Filter transcript turns by the `isMeta` and `toolUseResult` flags instead of a `text.startswith("<")` heuristic. This stops dropping legitimate user messages that start with "<" (#4) and stops capturing tool-result/meta frames as human turns (#8) — verified against a real transcript (25 human turns cleanly separated from 8 meta + 288 tool-result frames). - Title now uses second precision so rapid same-minute compactions don't collide and silently drop/overwrite a checkpoint; removed the unused stamp/slug. (#2) - Empty-checkpoint guard now requires at least one real user turn, not just any turn, so an assistant-only transcript can't produce a dangling-title note. (#5) validate_skills.py: - parse_frontmatter now skips indented lines, capturing only top-level keys, so a schema note's nested schema:/settings: children can't overwrite a top-level type/entity via last-write-wins. Documented its single-line-only limitation. (#6) All verified end-to-end; `just package-check-claude-code` and `package-check-skills` pass; ruff clean. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Signed-off-by: phernandez <paul@basicmachines.co>
phernandez
added a commit
that referenced
this pull request
May 30, 2026
Resolves the 8 self-review findings on PR #865: session-start.sh: - Wire recallTimeframe into a new "Recent sessions" query (--after_date) — it was parsed but unused after the Phase 4 rewrite. The brief now surfaces recent session checkpoints (the resume cursor), which is the one query the recency window legitimately applies to. (#1) - Guard secondaryProjects/teamProjects JSON types — a string value was iterated character-by-character into bogus per-char queries. (#3) - A configured-but-unreachable/misnamed primaryProject now emits a one-line "couldn't read" signal instead of a silent blank brief. (#7) pre-compact.sh: - Filter transcript turns by the `isMeta` and `toolUseResult` flags instead of a `text.startswith("<")` heuristic. This stops dropping legitimate user messages that start with "<" (#4) and stops capturing tool-result/meta frames as human turns (#8) — verified against a real transcript (25 human turns cleanly separated from 8 meta + 288 tool-result frames). - Title now uses second precision so rapid same-minute compactions don't collide and silently drop/overwrite a checkpoint; removed the unused stamp/slug. (#2) - Empty-checkpoint guard now requires at least one real user turn, not just any turn, so an assistant-only transcript can't produce a dangling-title note. (#5) validate_skills.py: - parse_frontmatter now skips indented lines, capturing only top-level keys, so a schema note's nested schema:/settings: children can't overwrite a top-level type/entity via last-write-wins. Documented its single-line-only limitation. (#6) All verified end-to-end; `just package-check-claude-code` and `package-check-skills` pass; ruff clean. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Signed-off-by: phernandez <paul@basicmachines.co>
phernandez
added a commit
that referenced
this pull request
May 31, 2026
Resolves the 8 self-review findings on PR #865: session-start.sh: - Wire recallTimeframe into a new "Recent sessions" query (--after_date) — it was parsed but unused after the Phase 4 rewrite. The brief now surfaces recent session checkpoints (the resume cursor), which is the one query the recency window legitimately applies to. (#1) - Guard secondaryProjects/teamProjects JSON types — a string value was iterated character-by-character into bogus per-char queries. (#3) - A configured-but-unreachable/misnamed primaryProject now emits a one-line "couldn't read" signal instead of a silent blank brief. (#7) pre-compact.sh: - Filter transcript turns by the `isMeta` and `toolUseResult` flags instead of a `text.startswith("<")` heuristic. This stops dropping legitimate user messages that start with "<" (#4) and stops capturing tool-result/meta frames as human turns (#8) — verified against a real transcript (25 human turns cleanly separated from 8 meta + 288 tool-result frames). - Title now uses second precision so rapid same-minute compactions don't collide and silently drop/overwrite a checkpoint; removed the unused stamp/slug. (#2) - Empty-checkpoint guard now requires at least one real user turn, not just any turn, so an assistant-only transcript can't produce a dangling-title note. (#5) validate_skills.py: - parse_frontmatter now skips indented lines, capturing only top-level keys, so a schema note's nested schema:/settings: children can't overwrite a top-level type/entity via last-write-wins. Documented its single-line-only limitation. (#6) All verified end-to-end; `just package-check-claude-code` and `package-check-skills` pass; ruff clean. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Signed-off-by: phernandez <paul@basicmachines.co>
DonaldoDes
added a commit
to DonaldoDes/basic-memory
that referenced
this pull request
Jun 23, 2026
…P4 US-3) BP4-C-01..06 + adversarial suite for ADR-006 Gap basicmachines-co#5: lambda iterators any(list, lambda)/filter(list, lambda) OUTSIDE an aggregate, and FLATTEN on a computed list expression (file.links AS link). Live-path tests go through process_note -> BasesExecutor via the faithful provider builder. [ADVERSARIAL] 8 security tests: no eval/exec/getattr/__import__ introduced, predicate error -> inert block, cardinality bound -> inert (no partial eval). Tests fail (RED): any/filter not in the whitelist, flatten rejects the expression mapping. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Signed-off-by: Donaldo <donaldo.desousa@icloud.com>
DonaldoDes
added a commit
to DonaldoDes/basic-memory
that referenced
this pull request
Jun 23, 2026
… US-3) ADR-006 Gap basicmachines-co#5. Extend the Bases executor for two constructs that kept areas.md x3 and the Basic Memory index x3 on dataview: - formula_eval._FUNCTIONS + formula_parser.ALLOWED_FUNCTIONS: any(list, lambda) -> bool and filter(list, lambda) -> sub-list, used OUTSIDE an aggregate. They reuse the SAME sandboxed lambda mechanism as P2 (_eval_lambda's closed-env closure) — no second evaluator. file.links/ file.outlinks resolve to the row's outlinks in the sandbox (dataset only). - parser/aggregate/schema: FLATTEN on a computed list EXPRESSION (flatten: {expression: file.links, as: link}) via a closed _FLATTEN_FILE_EXPRESSIONS whitelist — unfolds one row per element under the alias. The Phase 2 plain-field FLATTEN is unchanged. Security (constitution "Zones sensibles" / ADR-006 Invariants): closed dispatch only, no eval/exec/getattr/__import__; iterator cardinality bound MAX_ITERATOR_CARDINALITY (500, provisoire NC-4) -> block inert over the bound, NO partial evaluation; predicate error -> typed BasesError -> inert, MCP handler never crashes. Diff confined to src/basic_memory/bases/, zero core upstream change. [TDD-GREEN] 26/26 new tests pass. [BUILD] bases suite 603/603 (was 577), ruff clean, pyright 0 errors. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Signed-off-by: Donaldo <donaldo.desousa@icloud.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.