boxmaker/docs/plans/M5d2/09-memoryd-summary-index.md

M5d-2 task 09: index ToolSummary as kind summary

Branch: m5d2. Check it: git branch --show-current prints m5d2 and git status --short is empty; otherwise stop. Never switch branch. Commit subject: memoryd: index ToolSummary as kind summary Log row: the Task cell is M5d2/09-memoryd-summary-index.

Goal

memoryd indexes LogRecord::ToolSummary content as kind summary, with that record's class and untrusted (spec 4.3, P26). recall finds it and tags memory or memory-tainted as for any other session hit. Raw ToolResult bodies stay unindexed.

index_record today has _ => {}. It compiles. This task adds the arm.

Every place that changes

Place	What happens there
crates/memoryd/src/index.rs	ToolSummary arm (edit I1); module doc
crates/memoryd/tests/tool_summary_index.rs	new, given
everything else	no change: not recall.rs headers (role "summary" uses the existing "the assistant said" branch)

Files

• Copy, from docs/plans/M5d2/files/ (the same path under it): the new test crates/memoryd/tests/tool_summary_index.rs.
• Modify: crates/memoryd/src/index.rs, docs/implementer-log.md.
• Do not touch: any other file. Do not edit tests/support/logs.rs.

Facts you need

• Kind summary. Set kind: "summary".to_string() on the Source, not the log's "session". Role "summary". Time from the record. class / untrusted from the ToolSummary, not from base (the rolling session label). Skip when summary.class > self.max_class, even if base.class is still Private. Skip when content.trim() is empty.
• The existing if base.class > self.max_class stays. A secret ToolResult raises the rolling label before the next record, so a following secret summary is also skipped that way. Still check the summary's own class.
• Do not add ToolSummary to the rolling-label update in index_log (that loop still looks at ToolResult only). The result already carried the same labels.
• Recall headers. kind "summary" is not moved / dropped / noted, so the tag is memory or memory-tainted. Role "summary" is not owner or call, so the line says the assistant said. The given tests look for memory · session mm-a and memory-tainted.
• The items the edits use. This table is complete.

  Item	What it does
  self.add	FTS row plus sources
  Source	kind / role / class / untrusted

The edits, exactly

Each quoted "before" block occurs exactly once.

crates/memoryd/src/index.rs

I1. After the Assistant arm, before _ => {}. The lines

            }
            _ => {}
        }
        Ok(())
    }

become

            }
            LogRecord::ToolSummary {
                time,
                content,
                class,
                untrusted,
                ..
            } if !content.trim().is_empty() && *class <= self.max_class => {
                let src = Source {
                    kind: "summary".to_string(),
                    time: time.to_rfc3339(),
                    role: "summary".to_string(),
                    class: *class,
                    untrusted: *untrusted,
                    ..base.clone()
                };
                self.add(content, &src)?;
            }
            _ => {}
        }
        Ok(())
    }

DataClass already implements Ord (Public < Private < Secret). If <= does not compile, stop.

Optionally update the module doc "never a tool's result" to say summaries of opted-in results are indexed. A comment that does not fit its code: stop.

Steps

• 1. Copy the given test.

  cp docs/plans/M5d2/files/crates/memoryd/tests/tool_summary_index.rs crates/memoryd/tests/
  

• 2. See it fail. cargo test -p memoryd --test tool_summary_index, timeout 600000 ms: the tests compile (ToolSummary exists) and a_tool_summary_is_found_as_kind_summary fails: (no matches for "tea") or the unique phrase is missing. the_raw_tool_result_is_still_not_indexed may pass (results were already unindexed).

• 3. The edit. I1. cargo check -p memoryd prints no error and no warning.

• 4. The tests. cargo test -p memoryd --test tool_summary_index --test recall: every test passes, 5 in tool_summary_index.

• 5. Check. git diff --stat lists exactly crates/memoryd/src/index.rs.

• 6. Run the gate. cargo fmt --all, then make gate, timeout 600000 ms. Last line gate: ok. Test count 1568 (1563 before, plus 5). After gate: ok, do not add up test result: lines.

• 7. Log and commit. Task cell M5d2/09-memoryd-summary-index. Stage with git add crates/memoryd docs/implementer-log.md Cargo.lock, then commit as AGENTS.md says.

Done when

• make gate prints gate: ok with 1568 tests.
• git diff HEAD~1 --stat lists only crates/memoryd/src/index.rs, crates/memoryd/tests/tool_summary_index.rs and the log.

Stop and report if

• The branch check fails; a "before" block is not found exactly once; step 2 differs; cargo check warns; a test fails; the gate's last line is not gate: ok; you index ToolResult content; you leave kind as "session"; a secret summary is searchable on a private index.

What the given tests pin

A summary's content is found and tagged memory · session …; the raw tool body is not; an untrusted summary taints the recall (memory-tainted); a trusted summary does not taint; a secret summary is skipped when max_class is Private.