Agent Memory (typed)

Issue #97 introduces a structured agent-memory layer. Memory stays as plain markdown files inside each agent's memory/ directory — no vector DB, no external service. The schema just declares three named types and the runner / aide memory CLI knows how to manage them.

The three types

Type	Field	Default path	Purpose	Pruned after
`core`	`core_files`	(explicit list)	Always-loaded persona, standing rules, project invariants	never
`procedural`	`procedural_dir`	`memory/procedural`	Append-only logs: skill records, failure notes, patterns	90 days
`episodic`	`episodic_dir`	`memory/episodic`	Per-task scratch, transient observations	7 days

Configure in your Aidefile:

[memory]
compact_after  = "200k"
core_files     = ["memory/persona.md", "memory/rules.md"]
procedural_dir = "memory/procedural"
episodic_dir   = "memory/episodic"

All three are optional and backward-compatible — existing Aidefiles keep working with the documented defaults.

Pruning

aide memory prune              # apply defaults across every registered agent
aide memory prune --dry-run    # preview only

Type-specific defaults:

episodic → delete files with mtime older than 7 days
procedural → delete files with mtime older than 90 days
core → never touched

.lock sentinel files are skipped. Errors on individual files are swallowed so one bad file does not abort the whole pass.

Failure distillation

When aide run exits with a non-success status (partial or timeout), the runner appends a structured note to <procedural_dir>/failures.md:

## 2026-04-18T12:00:00+00:00
- **Issue**: local
- **Task snippet**: <first 200 chars of task>
- **Tokens**: 12345
- **Why it failed**: partial

The append is best-effort — it never fails the run itself. This forms the substrate for ReMe-style failure distillation: cron-fed jobs can later summarize failures.md into longer-term procedural notes.

Typed memory ops (text2mem-style)

The memory_ops module provides five free functions over a single agent's memory/ dir. All ops are markdown-aware and stay file-local.

Op	Behavior
`merge(path, content, dedupe)`	Append + dedupe (`none`, `line_hash`, `section_replace`)
`promote(src, dst)`	Atomic rename — typically episodic → core
`demote(src, dst)`	Atomic rename — opposite direction
`expire(path, max_age)`	Delete if `mtime` older than `max_age`; missing file = no-op
`lock(path)` / `unlock(path)`	Advisory `<path>.lock` sentinel (cooperative; not OS-enforced)

Dedupe strategies

none — straight append.
line_hash — skip lines whose exact text is already present.
section_replace — for markdown with ## headings, replace any block whose heading matches; preserve everything else.

Lock semantics (limitation)

lock(path) writes <path>.lock with O_CREAT|O_EXCL. A second lock on the same file fails until unlock removes the sentinel. This is purely cooperative — code that does not call lock/unlock will happily ignore the sentinel and clobber the file. It is intended for protecting batch mutations across the same agent dir, not for cross-process exclusion against arbitrary writers.

What is intentionally out of scope

Cross-agent shared memory (separate ticket, needs more design)
Token-usage benchmarks vs full context (separate eval ticket)
Vector retrieval / RAG — explicitly excluded by the issue

aide.sh