feat(memory): P1 memory improvements — MMR, temporal decay, chunked compaction, compact skills

CHANGELOG.md

@@ -7,6 +7,14 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 ## [Unreleased]
 
 ### Added
+- Temporal decay scoring in `SemanticMemory::recall()` — time-based score attenuation with configurable half-life (#745)
+- MMR (Maximal Marginal Relevance) re-ranking in `SemanticMemory::recall()` — post-processing for result diversity (#744)
+- Compact XML skills prompt format (`format_skills_prompt_compact`) for low-budget contexts (#747)
+- `SkillPromptMode` enum (`full`/`compact`/`auto`) with auto-selection based on context budget (#747)
+- Adaptive chunked context compaction — parallel chunk summarization via `join_all` (#746)
+- `with_ranking_options()` builder for `SemanticMemory` to configure temporal decay and MMR
+- `message_timestamps()` method on `SqliteStore` for Unix epoch retrieval via `strftime`
+- `get_vectors()` method on `EmbeddingStore` for raw vector fetch from SQLite `vector_points`
 - SQLite-backed `SqliteVectorStore` as embedded alternative to Qdrant for zero-dependency vector search (#741)
 - `vector_backend` config option to select between `qdrant` and `sqlite` vector backends
 - Credential scrubbing in LLM context pipeline via `scrub_content()` — redacts secrets and paths before LLM calls (#743)

README.md

@@ -23,7 +23,7 @@ Most AI agent frameworks dump every tool description, skill, and raw output into
 
 - **Semantic skill selection** — embeds skills as vectors, retrieves only top-K relevant per query instead of injecting all
 - **Smart output filtering** — command-aware filters strip 70-99% of noise before context injection
-- **Two-tier context pruning** — selective eviction + LLM compaction keeps the window clean
+- **Two-tier context pruning** — selective eviction + adaptive chunked compaction with parallel summarization keeps the window clean
 - **Proportional budget allocation** — context space distributed by purpose, not arrival order
 
 ## Installation
@@ -61,8 +61,8 @@ zeph --tui         # run with TUI dashboard
 | | |
 |---|---|
 | **Hybrid inference** | Ollama, Claude, OpenAI, Candle (GGUF), any OpenAI-compatible API. Multi-model orchestrator with fallback chains |
-| **Skills-first architecture** | YAML+Markdown skill files with semantic matching, self-learning evolution, and 4-tier trust model |
-| **Semantic memory** | SQLite + Qdrant (or embedded SQLite vector search) with summarization, credential scrubbing, cross-session recall, and vector retrieval |
+| **Skills-first architecture** | YAML+Markdown skill files with semantic matching, self-learning evolution, 4-tier trust model, and compact prompt mode for small-context models |
+| **Semantic memory** | SQLite + Qdrant (or embedded SQLite vector search) with MMR re-ranking, temporal decay scoring, adaptive chunked compaction, credential scrubbing, cross-session recall, and vector retrieval |
 | **Multi-channel I/O** | CLI, Telegram, Discord, Slack, TUI — all with streaming. Vision and speech-to-text input |
 | **Protocols** | MCP client (stdio + HTTP), A2A agent-to-agent communication, sub-agent orchestration |
 | **Defense-in-depth** | Shell sandbox, tool permissions, secret redaction, SSRF protection, skill trust quarantine, audit logging |

crates/zeph-core/README.md

@@ -24,7 +24,7 @@ Core orchestration crate for the Zeph agent. Manages the main agent loop, bootst
 | `bootstrap` | `AppBuilder` — fluent builder for application startup |
 | `channel` | `Channel` trait defining I/O adapters; `LoopbackChannel` / `LoopbackHandle` for headless daemon I/O; `Attachment` / `AttachmentKind` for multimodal inputs |
 | `config` | TOML config with `ZEPH_*` env overrides; typed `ConfigError` (Io, Parse, Validation, Vault) |
-| `context` | LLM context assembly from history, skills, memory |
+| `context` | LLM context assembly from history, skills, memory; adaptive chunked compaction with parallel summarization |
 | `cost` | Token cost tracking and budgeting |
 | `daemon` | Background daemon mode with PID file lifecycle (optional feature) |
 | `metrics` | Runtime metrics collection |
@@ -48,6 +48,14 @@ Key `AgentConfig` fields (TOML section `[agent]`):
 | `summary_model` | string? | `null` | — | Model used for context summarization |
 | `auto_update_check` | bool | `true` | `ZEPH_AUTO_UPDATE_CHECK` | Check GitHub releases for a newer version on startup / via scheduler |
 
+Key `MemoryConfig` fields (TOML section `[memory]`):
+
+| Field | Type | Default | Description |
+|-------|------|---------|-------------|
+| `vector_backend` | `"qdrant"` / `"sqlite"` | `"qdrant"` | Vector search backend |
+| `token_safety_margin` | f32 | `1.0` | Safety multiplier for token budget estimation (validated: must be >= 1.0) |
+| `redact_credentials` | bool | `true` | Scrub secrets and paths before LLM context injection |
+
 ```toml
 [agent]
 auto_update_check = true   # set to false to disable update notifications

crates/zeph-core/src/agent/builder.rs

@@ -67,6 +67,12 @@ impl<C: Channel> Agent<C> {
         self
     }
 
+    #[must_use]
+    pub fn with_skill_prompt_mode(mut self, mode: crate::config::SkillPromptMode) -> Self {
+        self.skill_state.prompt_mode = mode;
+        self
+    }
+
     #[must_use]
     pub fn with_shutdown(mut self, rx: watch::Receiver<bool>) -> Self {
         self.shutdown = rx;