diff --git a/Cargo.lock b/Cargo.lock
index 16dc21b540..00d4d3ac32 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -7204,7 +7204,7 @@ dependencies = [
 
 [[package]]
 name = "tinyagents"
-version = "2.1.0"
+version = "2.1.1"
 dependencies = [
  "async-trait",
  "bytes",
@@ -7317,7 +7317,7 @@ source = "git+https://github.com/tinyhumansai/sdk.git?rev=3ee4123ba3b7a76c5f167d
 dependencies = [
  "base64 0.22.1",
  "percent-encoding",
- "reqwest 0.12.28",
+ "reqwest",
  "serde",
  "serde_json",
  "thiserror 2.0.18",
diff --git a/app/src-tauri/Cargo.lock b/app/src-tauri/Cargo.lock
index cee8aea064..b6a7d25127 100644
--- a/app/src-tauri/Cargo.lock
+++ b/app/src-tauri/Cargo.lock
@@ -5601,6 +5601,7 @@ dependencies = [
  "tinychannels",
  "tinycortex",
  "tinyflows",
+ "tinyhumans-sdk",
  "tinyjuice",
  "tinyplace",
  "tokio",
@@ -8924,7 +8925,7 @@ dependencies = [
 
 [[package]]
 name = "tinyagents"
-version = "2.1.0"
+version = "2.1.1"
 dependencies = [
  "async-trait",
  "bytes",
@@ -9025,6 +9026,20 @@ dependencies = [
  "tracing",
 ]
 
+[[package]]
+name = "tinyhumans-sdk"
+version = "0.1.0"
+source = "git+https://github.com/tinyhumansai/sdk.git?rev=3ee4123ba3b7a76c5f167d7bc2c72fca86671292#3ee4123ba3b7a76c5f167d7bc2c72fca86671292"
+dependencies = [
+ "base64 0.22.1",
+ "percent-encoding",
+ "reqwest 0.12.28",
+ "serde",
+ "serde_json",
+ "thiserror 2.0.18",
+ "url",
+]
+
 [[package]]
 name = "tinyjuice"
 version = "0.2.1"
diff --git a/docs/specs/2026-07-28-agent-runtime-into-tinyagents-design.md b/docs/specs/2026-07-28-agent-runtime-into-tinyagents-design.md
new file mode 100644
index 0000000000..bd73e893c1
--- /dev/null
+++ b/docs/specs/2026-07-28-agent-runtime-into-tinyagents-design.md
@@ -0,0 +1,348 @@
+# Moving `agent/` into TinyAgents
+
+**Status:** spec + plan. Direction decided by the maintainer on 2026-07-28
+after two rounds of pushback; this document plans the move rather than
+re-arguing it. The open questions below are *how*, not *whether*.
+**Scope:** relocate `src/openhuman/agent/` (152 files, 70,530 LOC) into
+`vendor/tinyagents` as a generic agent runtime, with OpenHuman's coupling
+expressed as trait injection.
+**Supersedes:** the "permanent host" dispositions for `builder/`, `turn/`,
+`runtime.rs`, and `types.rs` in
+[`2026-07-28-agent-session-transcript-to-tinyagents-design.md`](2026-07-28-agent-session-transcript-to-tinyagents-design.md)
+§6 (verified 2026-07-28: those four rows carry the literal "Permanent host"
+verdict at §6), and the `agent/ remainder — STAYS` row in
+[`../tinyagents-migration-plan-2026-07-22.md`](../tinyagents-migration-plan-2026-07-22.md)
+§7. Both are reopened by this decision; the reopen rows are recorded in
+[`../tinyagents-drift-ledger.md`](../tinyagents-drift-ledger.md) (section
+"Agent-Relocation Reopen Rows (2026-07-28)").
+
+> **Corrections (2026-07-28).** Every count below was re-derived from the
+> worktree on 2026-07-28 with
+> `rg -o 'crate::openhuman::<domain>::' src/openhuman/agent --no-filename | wc -l`
+> (outbound) and a word-boundary `agent::<symbol>` grep over `src/` +
+> `app/src-tauri/src/` excluding `src/openhuman/agent/` (inbound). Changes from
+> the first draft: outbound domain count 45 → **48**; inbound domain count
+> 48 → **50** (47 counting code references only, excluding doc-comment-only
+> mentions); `tinyagents` 91 → 90, `tools` 84 → 83, `context` 52 → 51,
+> `approval` 10 → 9, `subconscious` 8 → 7, `web_chat` 6 → 5, `tool_status`
+> 5 → 4, `memory_store` 41 → 39; `util` promoted out of the "≤ 4 refs"
+> remainder bucket (it has 8) and `migrations` dropped from it (0 refs);
+> inbound `agent::harness::*` 275 → 300, `agent::triage` 24 → 34, `agent::bus`
+> 14 → 25; the Phase 4 exit figure ~2,000 → **547**; "~20–25k LOC stays"
+> confirmed by measurement at **22,121 LOC**. The headline `152 files,
+> 70,530 LOC` is exact and unchanged. No argument in this document changes as
+> a result — every correction moves a number, not a conclusion, and the three
+> inbound corrections all move *upward*, reinforcing §6's "inbound coupling is
+> the real cost".
+
+---
+
+## 1. Why this is feasible (the enabling fact)
+
+The earlier objection was dependency direction: `agent/` reaches 48 OpenHuman
+domains, so relocating it appeared to force a GPL-redistributed crate to import
+Composio, `SecurityPolicy`, and `memory_store`.
+
+That objection assumes the code moves *as written*. It does not have to,
+because **the crate is already generic over a host-supplied state type**:
+
+```rust
+pub struct AgentHarness<State: Send + Sync, Ctx: Send + Sync = ()> { … }
+pub trait Tool<State: Send + Sync>: Send + Sync { … }
+pub trait ChatModel<State: Send + Sync>: Send + Sync { … }
+pub trait Middleware<State: Send + Sync, Ctx: Send + Sync = ()>: Send + Sync { … }
+```
+
+`State` is the injection vehicle. A relocated agent runtime does not import
+`crate::openhuman::memory` — it is generic over a `State` that *provides*
+memory, and OpenHuman supplies the impl. The crate already ships **18 extension
+traits** on exactly this pattern (`ChatModel`, `Tool`, `ChatHistory`, `Store`,
+`AppendStore`, `Summarizer`, `EmbeddingModel`, `VectorStore`, `ResponseCache`,
+`WorkspaceIsolation`, `HarnessEventJournal`, `HarnessStatusStore`,
+`EventListener`, `Middleware`, `ModelMiddleware`, `ToolMiddleware`,
+`ModelBaseCall`, `ToolBaseCall`). This move adds ~10 more of the same kind. It
+is not a new architecture; it is more of the one already in use.
+
+The GPL/crates.io concern also narrows correctly: the constraint is that no
+*OpenHuman product logic* is published, not that no agent runtime is. Traits and
+a generic loop are publishable; `provider_role_for`'s `subconscious` routing and
+the `integrations_agent` dispatcher override are not — they become host impls.
+
+---
+
+## 2. Ground truth: the coupling to invert
+
+### 2.1 Outbound — what `agent/` imports (48 domains)
+
+By reference count:
+
+| Refs | Domain | Becomes |
+| ---: | --- | --- |
+| 195 | `config` (`Config` 53, `AgentConfig` 45, `MemoryConfig` 28, `ContextConfig` 24, …) | **crate config structs**, populated host-side. The single largest blocker — see §4.1 |
+| 90 | `tinyagents` (the seam) | dissolves — becomes internal |
+| 83 | `tools` | existing `Tool<State>` + `SharedToolAdapter` |
+| 72 | `inference` | existing `ChatModel<State>` + a `ModelResolver` trait |
+| 57 + 39 + 16 + 11 + 5 + 3 | `memory`, `memory_store`, `memory_tree`, `agent_memory`, `memory_tools`, `memory_conversations` | **`MemoryProvider`** trait |
+| 51 | `context` | **`ContextComposer`** trait |
+| 34 + 22 | `profiles`, `agent_registry` | **`DefinitionRegistry`** trait |
+| 28 | `composio` | host `Tool` impls — no new trait |
+| 25 + 9 + 6 + 4 + 2 | `security`, `approval`, `agent_tool_policy`, `sandbox`, `prompt_injection` | **`SecurityGate`** trait |
+| 22 + 1 | `skills`, `skill_runtime` | host `Tool` impls |
+| 21 | `todos` | already crate `graph::todos` (parent spec DS-1) |
+| 19 + 7 + 4 | `tokenjuice`, `cost`, `scheduler_gate` | **`BudgetGate`** trait |
+| 11 | `learning` | **`LearningSink`** trait |
+| 7 | `subconscious` | host impl behind `LearningSink` |
+| 5 + 4 | `web_chat`, `channels` | **`ProgressSink`** trait |
+| 4 | `tool_status` | **`ToolOutcomeClassifier`** trait |
+| 5 | `thread_goals` | host impl behind `ContextComposer` |
+| 5 | `embeddings` | existing `EmbeddingModel` |
+| 5 | `agent_orchestration` | existing `graph::orchestration` |
+| 3 | `agent_experience` | **`ExperienceStore`** trait |
+| 8 | `util` | inlined generics — no trait |
+| remainder (`app_state` 3, `session_db` 2, `file_state` 2, `task_sources` 2, `mcp_registry` 2, `session_import` 2, `tinycortex` 2, `tool_timeout` 2, `threads` 1, `credentials` 1, `cwd_jail` 1, `memory_goals` 1, `memory_sync` 1) | ≤ 3 refs each | host impls or inlined generics |
+
+**~10 new traits** cover 48 domains, because most domains reach `agent/` through
+one of a few conceptual seams.
+
+### 2.2 Inbound — what imports `agent/` (50 domains)
+
+This is the half the earlier analysis under-weighted, and it is the larger risk.
+50 domains under `src/openhuman/` name `agent::`; 47 of them do so from code
+rather than a doc comment. By symbol:
+
+| Refs | Symbol | Note |
+| ---: | --- | --- |
+| 300 | `agent::harness::*` | the bulk; moves down |
+| 58 | `agent::turn_origin` | product enum — **stays host** |
+| 43 | `agent::messages` (`ChatMessage`) | durable DTO — **stays host** (WP-1) |
+| 34 | `agent::triage` | product — **stays host** |
+| 23 | `agent::progress` (`AgentProgress`) | UI contract — **stays host**, produced via `ProgressSink` |
+| 16 | `agent::prompts` | `SOUL.md`/`IDENTITY.md` — **stays host** |
+| 15 | `agent::host_runtime` | **stays host** by definition |
+| 25 | `agent::bus` | event-bus glue — **stays host** |
+| 12 | `agent::task_board` | already crate `graph::todos` |
+| 13 | `agent::message_convert` | boundary adapter — **stays host** |
+| 12 | `agent::hooks` | trait defs move; impls stay |
+| 9 | `agent::error`, 10 `agent::cost`, 8 `agent::progress_tracing`, 7 `agent::tool_policy`, 7 `agent::pformat`, 7 `agent::task_dispatcher`, 4 `agent::stop_hooks` | mixed; see §3 |
+
+**Consequence:** `agent/` does not empty out. **22,121 LOC stays** (measured
+2026-07-28 over the §3 "stays in OpenHuman" file list — inside the originally
+estimated 20–25k band) as
+the host adapter layer (`ChatMessage`, `AgentProgress`, `turn_origin`, prompts,
+triage, bus, host_runtime, message_convert, the trait impls). The deliverable is
+"the runtime moves down and OpenHuman keeps an adapter", not "the directory
+disappears".
+
+### 2.3 Honest cost
+
+48 outbound domains to invert, 50 inbound consumers to repoint, ~29k LOC of
+tests to migrate or re-home, a cross-repo change in two Cargo worlds, and an
+on-disk/behavioural surface (transcript format, progress events, cost
+accounting) that users depend on. **This is a multi-quarter program, not a
+refactor.** §5 sequences it so every phase is independently valuable and the
+program can be halted at any phase boundary without leaving the tree broken.
+
+---
+
+## 3. Disposition
+
+### Moves into `tinyagents` (generic over `State`)
+
+| Host area | Prod LOC | Lands as |
+| --- | ---: | --- |
+| `harness/session/{runtime,types,builder}` — session lifecycle & assembly | ~3,700 | `harness::session` — `Session<State>` + builder over capability traits |
+| `harness/session/turn/*` — turn orchestration shell | ~4,476 | `harness::session::turn` — generic loop + `TurnPreparation` pipeline |
+| `harness/subagent_runner/` | ~5,541 | merges into existing `harness::subagent` + `graph::orchestration` |
+| `harness/session/transcript.rs` + `turn_checkpoint.rs` | ~2,100 | `harness::memory::JsonlChatHistory` (this is Option B of the transcript spec — **the move decision selects B**) |
+| `harness/{parse,definition,definition_loader,tool_filter,required_output,graph,agent_graph,fork_context}.rs` | ~3,300 | `harness::{tool_calling, definition, graph}` — merges with #55/#57 |
+| `harness/artifact_offload/`, `tool_result_artifacts/` | ~1,400 | `harness::artifacts` |
+| `harness/run_queue/`, `harness/memory_context*.rs` | ~1,000 | `harness::runtime`, behind `MemoryProvider` |
+| `task_dispatcher/`, `dispatcher.rs` (parse half), `pformat.rs`, `stop_hooks.rs`, `hooks.rs` (trait defs) | ~3,000 | `harness::{tool_calling, hooks}` |
+| `progress_tracing/` | ~3,186 | deleted, not moved — crate observability already covers it (parent spec DS-5) |
+
+### Stays in OpenHuman as the adapter layer
+
+`messages.rs` (`ChatMessage`), `message_convert.rs`, `progress.rs`
+(`AgentProgress`), `turn_origin.rs`, `prompts/`, `triage/`, `bus.rs`,
+`host_runtime.rs`, `error.rs`, `cost.rs`, `tool_policy.rs`, `multimodal.rs`,
+`agent/tools/`, `archivist/`, `schemas.rs`, plus **every impl of the ~10 new
+traits**. Measured 22,121 LOC including tests (2026-07-28).
+
+---
+
+## 4. The two decisions that gate everything
+
+### 4.1 Config (195 refs — the real blocker)
+
+`agent/` reads `Config`, `AgentConfig` (742-line schema), `MemoryConfig`,
+`ContextConfig` directly. A generic runtime cannot import OpenHuman's config
+schema. Options:
+
+- **A — Crate-owned config structs.** The crate defines `SessionConfig`,
+  `TurnConfig`, `ToolConfig`; OpenHuman maps its schema into them at build time.
+  Explicit, versionable, and mirrors how `MemoryConfig` is derived for TinyCortex
+  (`tinycortex/config.rs::memory_config_from`). **Recommended.**
+- **B — `ConfigProvider` trait** with ~40 getters. Avoids a mapping layer but
+  turns every config read into a virtual call and makes the trait a dumping
+  ground.
+- **C — Generic `State` carries config.** Least code, worst discoverability;
+  every crate-side read needs a bound.
+
+Pick A. It is the pattern the org already uses successfully one crate over.
+
+### 4.2 `ChatMessage` and the transcript format
+
+Moving the session runtime down forces the transcript decision to **Option B**
+of the transcript spec: the `session_raw` JSONL format becomes crate-owned
+public API, and `ChatMessage`'s durable fields must survive as crate `Message` +
+a `raw` passthrough (the `ToolResult::raw` precedent). This is the change with
+real user-visible risk — existing installs have live transcripts and resume must
+keep working. Phase 2 exists solely to de-risk it.
+
+---
+
+## 5. Phased plan
+
+Each phase is independently valuable and leaves the tree green. Stop-anywhere is
+a hard requirement, not a nicety.
+
+**Execution status (2026-07-28): Phases 0 and 1 are COMPLETE. Phases 2–7 were
+deliberately NOT executed.** The program is parked at the Phase 1/2 boundary,
+which is a legitimate stopping point: nothing has moved, no host file changed,
+and the crate carries only additive, inert seams. Phase 2 is the gate — it is
+the only phase with on-disk transcript risk and requires a shadow-read soak
+release before it can start, so it must be scheduled deliberately rather than
+picked up as the "next" task.
+
+**Phase 0 — Ledger + trait catalogue (no code). ✅ COMPLETE (2026-07-28).**
+Reopen the superseded rows (§ header). Write the ~10 trait signatures up as an
+upstream design doc. Nothing moves until the trait catalogue is accepted
+upstream — otherwise the first mover defines the seams by accident.
+*Note:* the original wording said "an upstream RFC in `vendor/tinyagents/docs/`".
+That violates the crate's documented convention — `vendor/tinyagents/docs/spec/README.md`
+and `vendor/tinyagents/AGENTS.md` forbid standalone spec files dropped directly
+in `docs/` and require a per-topic file under `docs/modules/<surface>/` linked
+from that module's `README.md`, capped at 500 lines. The catalogue therefore
+landed as `vendor/tinyagents/docs/modules/harness/host.md`, not as an RFC file.
+*Exit (met):* trait catalogue documented upstream in the crate's own format;
+ledger rows reopened in `docs/tinyagents-drift-ledger.md`; the plan's ground-truth
+numbers re-derived from the tree (see the Corrections note in the header).
+
+**Phase 1 — Land the traits upstream, empty. ✅ COMPLETE (2026-07-28).**
+Add the traits + no-op/in-memory default impls to the crate. No host change.
+*Exit (met):* the ten host-capability seams (`MemoryProvider`, `ContextComposer`,
+`SecurityGate`, `BudgetGate`, `DefinitionRegistry`, `ExperienceStore`,
+`LearningSink`, `ProgressSink`, `ToolOutcomeClassifier`, `ModelResolver`) plus
+inert default impls are committed in `vendor/tinyagents` on branch
+`agent-to-tinyagents`. **The submodule gitlink bump is a separate, later step and
+is intentionally not part of the host commits for Phase 0/1** — the host tree is
+unchanged apart from these docs.
+*Design note carried into Phase 4:* the plan's §1 framing that `State` is "the
+pattern already in use" is only two-thirds true. Of the 18 harness extension
+traits, only 7 are generic over `State` (`ChatModel`, `Tool`, `Middleware`,
+`ModelMiddleware`, `ToolMiddleware`, `ModelBaseCall`, `ToolBaseCall`); the 11
+*capability* traits closest to the new seams (`ChatHistory`, `Store`,
+`AppendStore`, `Summarizer`, `EmbeddingModel`, `VectorStore`, `ResponseCache`,
+`WorkspaceIsolation`, `HarnessEventJournal`, `HarnessStatusStore`,
+`EventListener`) are plain non-generic object-safe traits. Every OpenHuman
+construction and impl today is `AgentHarness<()>` / `impl Tool<()>` — `State` is
+unexercised in the host. Whichever shape Phase 4 adopts, adopting a non-unit
+`State` is a signature change across ~30 existing `<()>` impls and every
+`invoke(&(), …)` call site, and that cost is not counted in §2.3.
+
+**Phase 2 — Transcript to crate `JsonlChatHistory` (transcript spec Option B).**
+⛔ NOT STARTED — deliberately. Do this early and alone: it is the only phase with
+on-disk risk. One release of shadow-read parity, mismatch logged never panicked,
+legacy `DDMMYYYY/` and `read_transcript_legacy_md` paths covered.
+*Exit:* resume works across upgrade on a real workspace; parity soak clean, **and
+each of the three semantics named in the transcript spec's §3.1 gap table is
+individually demonstrated over the crate-owned format: compaction-replacement
+records, skippable interrupted partials, and the display-order (dual) read path.**
+The transcript spec calls that gap table "the single most important constraint in
+this document" — a generic `ChatHistory` impl that satisfies naive round-trip
+parity but drops those three silently corrupts model context on any compacted
+thread, so they are exit criteria in their own right, not sub-cases of "parity".
+
+**Phase 3 — Config mapping (§4.1 Option A).** ⛔ NOT STARTED.
+Introduce crate config structs + a host `session_config_from(&Config)` mapper.
+Repoint `agent/` internals to the crate structs *in place*, before moving.
+*Exit:* zero `crate::openhuman::config::` references inside the code slated to
+move.
+
+**Phase 4 — Implement the traits host-side, still in place.** ⛔ NOT STARTED.
+`MemoryProvider`, `ContextComposer`, `SecurityGate`, `BudgetGate`,
+`DefinitionRegistry`, `ExperienceStore`, `LearningSink`, `ProgressSink`,
+`ToolOutcomeClassifier`, `ModelResolver`. `agent/` calls them instead of
+reaching into domains directly. **This phase delivers most of the architectural
+value with none of the relocation risk** — after it, `agent/`'s outbound
+coupling is ~10 traits instead of 48 domains, and the program can legitimately
+stop here.
+*Exit:* `rg -o "crate::openhuman::" src/openhuman/agent/harness/session/` down
+from its 2026-07-28 baseline of **547** occurrences to the adapter layer only.
+(For scale: the whole of `harness/` is 932 and the whole of `agent/` is 1,287 —
+an earlier draft of this plan cited ~2,000 for `session/`, which no scoping of
+that grep reproduces.)
+
+**Phase 5 — Relocate, module family at a time.** ⛔ NOT STARTED.
+Order by inbound coupling, lowest first: `artifact_offload` → `run_queue` →
+`parse`/`tool_calling` (merges with DS-5b) → `subagent_runner` → `session/turn`
+→ `session/{builder,runtime,types}`. Each family: move to
+`vendor/tinyagents/src/harness/`, re-export from the host adapter for one
+release, then repoint consumers.
+*Exit per family:* crate tests green; host `cargo check` both worlds; the
+family's tests live upstream.
+
+**Phase 6 — Collapse the seam and the adapter.** ⛔ NOT STARTED.
+`src/openhuman/tinyagents/` dissolves into the host adapter layer. Delete the
+compatibility re-exports.
+*Exit:* `agent/` is the adapter layer only; parent spec's DS-0 re-export gate
+allowlist is seam-free.
+
+**Phase 7 — Exit gate.** ⛔ NOT STARTED.
+Full `scripts/test-rust-with-mock.sh`, `cargo test --all-features` in both
+vendored crates, slim disabled build **and** `cargo test --lib
+--no-default-features --features tokenjuice-treesitter core::`, `pnpm
+rust:check`, deletion-ledger totals reconciled, architecture docs rewritten.
+
+---
+
+## 6. Risks
+
+- **Inbound coupling is the real cost, not outbound.** 50 domains import
+  `agent::`. Phase 5's per-family re-export window is what keeps that tractable;
+  skipping it turns every family move into a 50-domain atomic commit.
+- **On-disk transcript risk (Phase 2)** is the only user-visible data risk in
+  the program. It is deliberately isolated and sequenced first.
+- **`AgentProgress` is a UI contract.** It stays host-side and is produced
+  through `ProgressSink`. If it drifts into the crate, the frontend timeline,
+  cost footer, and citation chips break in ways unit tests will not catch.
+- **Trait-explosion.** Ten traits is the budget. If Phase 4 needs a fifteenth,
+  that is a signal a seam is wrong — re-open the RFC rather than adding it.
+- **GPL/crates.io.** Publishable: traits, generic loop, tool-calling wire
+  formats. Not publishable: `provider_role_for`'s `subconscious` routing, the
+  `integrations_agent` override, OpenHuman prompt text, backend phrasing, key
+  material. Every relocated file needs this check.
+- **≥ 80% diff-coverage gate** on a program of this size — Phases 4 and 5 touch
+  hundreds of files. Check `diff-cover` per slice.
+- **Two Cargo worlds** — every crate bump regenerates root and
+  `app/src-tauri` lockfiles (#3877).
+- **`RUST_MIN_STACK=16777216`** — the subagent runner's large futures already
+  overflow the default stack on Apple Silicon; Phase 5's subagent move is
+  exactly where that resurfaces.
+- **`GGML_NATIVE=OFF`** for local root-crate builds.
+
+---
+
+## 7. Summary
+
+| | |
+| --- | --- |
+| Decision | move `agent/` into `tinyagents` (maintainer call, 2026-07-28) |
+| Enabler | the crate is already generic over `State`; 18 extension traits use the pattern today |
+| Inversion | 48 outbound domains → **~10 capability traits** |
+| Reality check | `agent/` does not empty — 22,121 LOC stays as the host adapter (`ChatMessage`, `AgentProgress`, prompts, triage, bus, trait impls) |
+| Gating decisions | config mapping (§4.1 → Option A); transcript format goes crate-owned (§4.2 → transcript spec Option B) |
+| Highest-value / lowest-risk phase | **Phase 4** — trait injection in place. Cuts coupling 45 → 10 without moving a file; a legitimate stopping point |
+| Highest-risk phase | **Phase 2** — on-disk transcript format, isolated and sequenced first |
+| Honest cost | multi-quarter program; every phase leaves the tree green and shippable |
+
diff --git a/docs/specs/2026-07-28-agent-session-transcript-to-tinyagents-design.md b/docs/specs/2026-07-28-agent-session-transcript-to-tinyagents-design.md
new file mode 100644
index 0000000000..db53121ad6
--- /dev/null
+++ b/docs/specs/2026-07-28-agent-session-transcript-to-tinyagents-design.md
@@ -0,0 +1,496 @@
+# Agent session persistence → TinyAgents
+
+**Status:** spec + plan, awaiting a shape decision (§4). Written 2026-07-28
+against `main` (`ce6c3e9b5`).
+**Scope:** `src/openhuman/agent/harness/session/` — specifically the durable
+transcript layer. Everything else in `session/` is out of scope and stays.
+**Superseded in part (2026-07-28):** the maintainer has since decided to move
+`agent/` wholesale into TinyAgents — see
+[`2026-07-28-agent-runtime-into-tinyagents-design.md`](2026-07-28-agent-runtime-into-tinyagents-design.md).
+That decision reopens this document's §6 "permanent host" rows for `builder/`,
+`turn/`, `runtime.rs`, and `types.rs`, and selects **Option B** in §4 (the
+transcript format becomes crate-owned). The state map, crate gap table, and
+§3.5 analysis below remain accurate and are the input to that program's
+Phases 2–4.
+
+**Parent spec:** `2026-07-28-deshim-agent-inference-memory-seams-design.md`
+(this document is the expansion of its DS-8).
+**Related:** `docs/tinyagents-migration-plan-2026-07-22.md` (WP-1's
+`ChatMessage` decision is the governing precedent), `99-deletion-ledger.md`.
+
+---
+
+## 1. The question this answers
+
+Should `agent/harness/session/` become a `tinyagents::sessions` module?
+
+**No — not as a unit.** But its durable transcript layer is a parallel
+implementation of an abstraction the crate already ships, and that part should
+converge. This document draws the line precisely, because drawing it wrong in
+either direction is expensive: too aggressive and a GPL crate ends up importing
+Composio; too timid and OpenHuman keeps two conversation-history models forever.
+
+---
+
+## 2. Current state
+
+### 2.1 Size and split
+
+`session/` is **18,142 LOC** across 17 files (~11,073 production, ~7,069 tests).
+The transcript layer is:
+
+| File | Prod LOC | Tests |
+| --- | ---: | ---: |
+| `transcript.rs` | 1,997 | 1,384 (`transcript_tests.rs`) |
+| `turn_checkpoint.rs` | 105 | — |
+| `migration.rs` | 373 | 170 (`migration_tests.rs`) |
+| **Total** | **2,475** | **1,554** |
+
+### 2.2 Why only these three
+
+Measured host-domain fan-out (`grep -o "crate::openhuman::[a-z_]*" | sort -u`):
+
+| File | Prod LOC | Host domains | In scope? |
+| --- | ---: | ---: | --- |
+| `transcript.rs` | 1,997 | **2** (`agent::messages::ChatMessage`, `inference::provider::ToolCall`) | **yes** |
+| `turn_checkpoint.rs` | 105 | **2** (`ChatMessage`, `hooks::ToolCallRecord`) | **yes** |
+| `migration.rs` | 373 | **0** (`anyhow`, `std::fs`, `std::path`) | **yes** |
+| `builder/factory.rs` | 1,699 | 21 — composio, security, skills, subconscious, profiles, memory_store, memory_tools, agent_registry, agent_experience, agent_memory, embeddings, tokenjuice, learning, app_state, config, context, inference, tools, agent, tinyagents, … | no |
+| `turn/core.rs` | 2,207 | 10 — mcp_registry, thread_goals, agent_orchestration, agent_experience, agent_memory, composio, memory, util, agent, tinyagents | no |
+| `turn/session_io.rs` | 854 | 7 — learning, session_import, config, context, inference, agent, tinyagents | no |
+| `runtime.rs` | 817 | 14 — channels, composio, prompt_injection, agent_tool_policy, skills, memory, … | no |
+| `builder/setters.rs` | 666 | 10 | no |
+| `turn/tools.rs` | 650 | 6 — composio, profiles, skills | no |
+| `types.rs` | 477 | 11 | no |
+| `turn/context.rs` | 343 | 7 — app_state, learning, memory | no |
+| `turn/mod.rs`, `turn/graph.rs`, `builder/*`, `mod.rs`, `tool_progress.rs` | ~840 | 3–7 each | no (see §6) |
+
+**~8,600 of 11,073 production lines are host wiring.** `builder/factory.rs`
+reaches 21 OpenHuman domains; its job is literally "assemble OpenHuman's product
+surface into a harness". Moving it down inverts the dependency and violates the
+port plan's standing GPL/crates.io rule: only genuinely generic code goes into a
+publicly redistributed crate.
+
+### 2.3 What `transcript.rs` actually implements
+
+Storage layout:
+
+```text
+{workspace}/session_raw/{stem}.jsonl        ← source of truth (flat dir)
+{workspace}/sessions/YYYY_MM_DD/{stem}.md   ← human view, never read back
+```
+
+`stem` = `{unix_ts}_{agent_id}`, or `{parent_chain}__{unix_ts}_{agent_id}` for a
+sub-agent — timestamp-first so a plain directory listing sorts by creation time
+and `find_latest_transcript` is one directory scan.
+
+Semantics, in the order they matter:
+
+1. **Append-only event log.** `append_transcript_turn` never rewrites existing
+   lines. It classifies the new logical message set against what was persisted:
+   pure extension → append the tail; reduction/rewrite → append a single
+   `{"kind":"compaction","replacement":[…]}` record carrying the full reduced
+   set, leaving earlier turns on disk.
+2. **Two read paths from one log.** `read_transcript` replays for *model
+   context* (compaction records replace the accumulator; `interrupted:true`
+   partials are skipped). `read_transcript_display` returns **every** record in
+   file order so the UI can render pre-compaction history, compaction markers,
+   and interrupted partials.
+3. **Rewrite-free cumulative meta.** A fresh `{"_meta":{…}}` line is appended
+   each turn; readers take the **last** `_meta` as authoritative, with line 1 as
+   a valid fallback for older cores.
+4. **Forward/backward compatibility by construction.** `MessageLine` carries
+   `#[serde(flatten)] _extra`; `MetaPayload` does not set
+   `deny_unknown_fields`; `_meta.version` is `TRANSCRIPT_SCHEMA_VERSION`. Old
+   cores skip unknown-kind lines instead of crashing. Legacy
+   `session_raw/DDMMYYYY/` layout still resolves for resume.
+5. **Usage rollups.** `read_thread_usage_summary` →
+   `ThreadUsageSummary` + `SubagentArchetypeUsage`.
+
+Public surface: 26 items — `SessionTranscript`, `TranscriptMeta`,
+`DisplaySessionTranscript`, `DisplayRecord`, `DisplayMessage`,
+`CompactionMarker`, `TurnUsage`, `MessageUsage`, `ThreadUsageSummary`,
+`SubagentArchetypeUsage`, plus `write_transcript`, `append_transcript_turn`,
+`append_interrupted_partial`, `read_transcript`, `read_transcript_display`,
+`read_transcript_legacy_md`, `read_thread_usage_summary`,
+`find_root_transcript_for_thread(_in_dir)`, `resolve_keyed_transcript_path(_in_dir)`,
+`resolve_new_transcript_path`, `find_latest_transcript(_in_subdir)`.
+
+### 2.4 Consumers
+
+**24 files across 5 domains** import `transcript::`: `agent`, `threads`,
+`session_import`, `learning`, `migrations`. Notable non-agent callers:
+
+- `threads/transcript_view/project.rs` — the derived-view projection
+- `threads/turn_state/mirror.rs` — `find_root_transcript_for_thread`, `append_interrupted_partial`
+- `threads/ops.rs` — `read_thread_usage_summary`
+- `session_import/{ops,convert,live}.rs` — external session import
+- `learning/transcript_ingest/mod.rs` — lesson extraction
+- `migrations/phase_out_profile_md.rs`
+
+This is the **transcript-derived-view architecture**: `session_raw` JSONL is the
+source of truth, `turn_state` is a derived cache. Any change here is a change to
+that contract, not just to one module.
+
+---
+
+## 3. What the crate already ships
+
+`vendor/tinyagents` v2.1.0:
+
+| Crate capability | Module | Relevance |
+| --- | --- | --- |
+| `ChatHistory` trait — `messages(thread_id) -> Vec<Message>`, `append`, `replace`, `clear` | `harness::memory::types:48` | **The direct analogue.** Thread-scoped conversation history surviving across runs. |
+| `InMemoryChatHistory`, `StoreChatHistory<S: Store>`, `ShortTermMemory<H>` (trim policy), `MemoryScope` | `harness::memory` | Backends + short/long-term layering |
+| `Store` — kv (`get`/`put`/`delete`/`list`) **plus an append-only stream API**: `append(stream, value) -> u64`, `read_from(stream, offset)`, `len(stream)` | `harness::store` | The stream half is a closer structural match to the JSONL log than `ChatHistory` is |
+| `InMemoryStore`, `FileStore`, `StoreRegistry` | `harness::store` | Backends |
+| `Checkpointer`, `FileCheckpointer`, `SqliteCheckpointer`, `DurabilityMode` | `graph::checkpoint` | Superstep state snapshots — **different concern**, not a transcript |
+
+**So OpenHuman is not missing a home; it has a second implementation.** That is
+the whole argument for this work.
+
+### 3.1 Gap table — what crate `ChatHistory` cannot express today
+
+| OpenHuman semantic | Crate equivalent | Gap |
+| --- | --- | --- |
+| Append-only log, never rewrite | `Store::append`/`read_from` (stream API) | present on `Store`, **absent from `ChatHistory`** (`replace` is a bulk overwrite) |
+| Compaction record with `replacement` set | — | **missing** |
+| `interrupted:true` partials, skipped on model read | — | **missing** |
+| Dual read paths (model-context replay vs display-order) | — | **missing** — `messages()` is single-view |
+| Cumulative `_meta` totals appended per turn | — | **missing** |
+| Schema versioning + unknown-line tolerance | — | **missing** (a policy, easily added) |
+| `.md` companion render | — | **host** — product surface, never upstream |
+| Stem naming, latest/resume discovery, legacy dir fallback | — | **host** — OpenHuman workspace layout |
+| Thread/subagent usage rollups | `harness::usage`, `harness::cost` | partial; the archetype rollup is product |
+
+`ChatHistory` is a **strictly weaker interface** than what OpenHuman needs. A
+naive "just implement `ChatHistory`" that routes reads through `messages()`
+would silently drop compaction and interrupted-partial semantics — i.e. corrupt
+the model context on any compacted thread. This is the single most important
+constraint in this document.
+
+---
+
+## 3.5 Re-examined: `builder/factory.rs` and `turn/core.rs`
+
+The §2.2 verdict ("21 imports, therefore host") describes the *wiring*, not the
+*shape*. A shape can be generic even when every value flowing through it is
+product-specific, so both files were re-read rather than dismissed on the import
+count. Result: **the structure is already in the crate; the residue is genuinely
+product — with two concrete exceptions worth acting on.**
+
+### 3.5.1 `Agent` is not a duplicate of `AgentHarness`
+
+`AgentHarness<State, Ctx>` (`harness/runtime/types.rs:259`) has **six** fields —
+`models`, `tools`, `middleware`, `policy`, `tool_timeouts`, `response_cache` —
+and a complete builder API: `new`, `register_model`, `set_default_model`,
+`register_tool`, `push_middleware`, `push_model_middleware`,
+`push_tool_middleware`, `with_policy`, `with_tool_timeout_settings`,
+`with_response_cache`. The seam already drives exactly this API
+(`tinyagents/mod.rs:1793–2302`).
+
+The host `Agent` (`session/types.rs:31`) has **40+ fields**, and the ones that
+define it are not execution config at all:
+
+- **Per-turn product accumulators:** `last_memory_context`,
+  `last_turn_citations`, `last_turn_usage_totals`, `last_turn_hit_cap` — read
+  by web-channel delivery to render citation chips, token/cost meters, and to
+  distinguish "paused at the iteration cap" from "asked a question".
+- **Host service handles:** `memory`, `shared_experience_memory`,
+  `memory_loader`, `tool_policy_session`, `workflows`.
+- **Product policy:** `learning_enabled`, `explicit_preferences_enabled`,
+  `subagent_tool_ceiling_names`, `visible_tool_names`.
+- **Event identity:** `event_session_id`, `event_channel`.
+
+`Agent` is OpenHuman's **session-state + turn-result object**; `AgentHarness` is
+the crate's execution configuration. They are different things that both happen
+to hold tools and a model. That single overlap is already bridged by
+`SharedToolAdapter`, which the WP-4 decision fixed as a permanent boundary. And
+`Agent` already holds a crate type directly — `workspace_descriptor:
+tinyagents::harness::workspace::WorkspaceDescriptor` — which is what convergence
+looks like in practice: adopt crate types field by field, don't relocate the
+struct.
+
+**So there are not two builders competing.** There are two builders in series
+(host `Agent::from_config` → seam → crate `AgentHarness`), building two
+different objects. Moving `factory.rs` down would require the crate to import
+Composio, OpenHuman `SecurityPolicy`, `memory_store`, `skills`, `profiles`, and
+`subconscious` — the exact GPL/crates.io boundary violation the port plan
+forbids.
+
+### 3.5.2 `turn/core.rs` is preparation, and the engine already left
+
+WP-3 established that `turn/core.rs` "performs OpenHuman turn preparation and
+calls the TinyAgents session path" — it contains no turn engine. Reading it
+confirms that: `impl Agent` starts at line 432, and everything above it is
+product gating. What `turn()` actually does before delegating:
+
+- super-context gating hard-wired to `orchestrator` + `context_scout`, with an
+  explicit carve-out so background/cron/specialist turns don't spawn it;
+- agent-experience retrieval and `prepend_experience_block`;
+- memory recall citation collection;
+- integration / MCP / skill announcement + retraction notes.
+
+None of that is framework-shaped. **But ~150 LOC of it is:**
+`tool_records_from_conversation`, `stamp_tool_failures`, `parse_tool_call_id`,
+`short_failure_detail`, `replace_last_assistant_reply` are pure message-list
+manipulation over roles and tool-call ids. Those are candidates for crate
+`harness::message` helpers — small, but genuinely generic.
+
+### 3.5.3 The one real duplicate: dispatcher-kind resolution
+
+`resolve_dispatcher_kind` (`factory.rs:1398`) picks Native / Xml / PFormat from
+`supports_native`, plus an `integrations_agent` override. The three
+`ToolDispatcher` impls then render and parse tool calls accordingly.
+
+**The crate already makes this decision.** `OpenAiModel` exposes
+`with_native_tool_calling(bool)` and internally computes
+`prompt_guided_tools = !self.profile.tool_calling && !request.tools.is_empty()`
+(`providers/openai/transport.rs:951`), replaying calls and results as text when
+prompt-guided — that is #55. So OpenHuman decides native-vs-prompt-guided at the
+session-build layer, and the crate decides it again at the model layer.
+
+This is the **same subsystem** as the parent spec's DS-5b (`harness/parse.rs`
+duplicating #55/#57 parsing). Dispatcher selection, tool-call rendering, and
+tool-call parsing are one concern split across two layers and two owners. They
+should be resolved together, and the answer is almost certainly: the crate owns
+the native-vs-prompt-guided decision and both directions of the wire format;
+OpenHuman keeps only the `integrations_agent` override as an explicit policy
+input, and the durable `to_provider_messages` serialization.
+
+### 3.5.4 The generalizable conclusion
+
+The productive question is not *"which file moves down"* but *"which extension
+point is missing upstream"*. `factory.rs` and `turn/core.rs` are large because
+the crate offers registries and middleware but no typed **turn-preparation**
+seam — so every product enrichment (experience, citations, announcements,
+super-context) is hand-written into one `turn()` body instead of registered.
+
+If the crate grew a `ContextEnricher` / `TurnPreparation` pipeline —
+ordered, fallible, each returning prompt fragments plus metadata — OpenHuman's
+enrichment becomes registrations rather than a bespoke method, and the *shape*
+moves down while the *wiring* stays up. That is worth designing (S6), and it is
+what "enrich it as a library" should mean here. It is explicitly **not** a
+licence to relocate 3,900 lines of host wiring.
+
+---
+
+## 4. The decision (§4 is the gate — pick one before writing code)
+
+### Option A — Host backend behind the crate trait *(recommended)*
+
+Keep `ChatMessage`, the `session_raw` format, and every host-only helper exactly
+as they are. Add `impl tinyagents::harness::memory::ChatHistory for
+SessionTranscriptHistory`, converting at the boundary via the existing
+`agent/message_convert.rs`. The harness talks to the crate trait; OpenHuman owns
+the format. Host-only semantics (display read, compaction markers, usage
+rollups, path resolution) stay on the concrete type, reached directly by the 24
+consumers that need them.
+
+- **On-disk change:** none. **Migration risk:** none.
+- **Removes:** ~400 LOC of parallel abstraction, plus the conceptual duplicate.
+- **Cost:** low. Reversible.
+- **Weakness:** the crate trait is only used on the narrow runtime path; most of
+  `transcript.rs` stays. Honest framing: this fixes *"two abstractions"*, not
+  *"two implementations"*.
+
+### Option B — Upstream a generic append-only history backend
+
+Add `JsonlChatHistory` to the crate beside `StoreChatHistory`, and extend
+`ChatHistory` (or add a `ReplayableChatHistory` supertrait) with the three
+missing generic semantics: compaction-replacement records, skippable partials,
+and a display-order read. `ChatMessage`'s durable fields survive as crate
+`Message` + a `raw` passthrough, mirroring how the tool-model decision preserves
+`ToolResult::raw`.
+
+- **Removes:** ~2,100 host LOC.
+- **Cost:** high — a trait extension in a published GPL crate, a durable format
+  becoming public API, and an on-disk parity soak.
+- **Only justified if** a second host will use it. Compaction-aware append-only
+  transcripts are genuinely generic agent-framework machinery, so this is
+  defensible — but it is a crate-roadmap decision, not a cleanup.
+
+### Option C — Declare host-owned, close the question
+
+Record `transcript.rs` in the deletion ledger as HOST-OWNED (durable on-disk
+format + product read paths), same disposition as `tool_status` and
+`namespace_store`. Costs nothing, keeps two abstractions.
+
+**Recommendation: A now, B only if the crate roadmap wants a durable transcript
+primitive.** A is cheap, reversible, and removes the thing that actually
+confuses readers. B should not be smuggled in as refactoring.
+
+---
+
+## 5. Plan (Option A)
+
+Every slice: failing-before/passing-after test, small validated commit on a
+feature branch, `atomic-commit` with explicit paths.
+
+### S0 — Ledger + decision record (no code)
+
+Add a ledger row for `harness/session/` recording the §2.2 split and the §4
+choice. Without this, a future audit re-opens "why didn't session move?" — which
+has already happened twice in this migration.
+
+**Exit:** row present; this doc linked from the parent spec's DS-8.
+
+### S1 — `migration.rs` disposition
+
+Zero host imports, but it migrates *OpenHuman's* directory layout
+(`session_raw/DDMMYYYY/` → flat). Generic code for a host-specific format.
+
+Expected outcome: **stays host**, recorded with that reason. Do the 10-minute
+check rather than assuming; if it turns out to be a general "flatten a
+date-bucketed log dir" utility with no OpenHuman naming, it can go down.
+
+**Exit:** one ledger row, either way.
+
+### S2 — Extract the trait-shaped surface
+
+Introduce `SessionTranscriptHistory { workspace_dir, stem }` in
+`session/transcript_history.rs`, wrapping the existing free functions. No
+behaviour change; purely a handle where a trait impl can live.
+
+**Exit:** `cargo check` + existing `transcript_tests.rs` green, untouched.
+
+### S3 — Implement crate `ChatHistory`
+
+```rust
+impl tinyagents::harness::memory::ChatHistory for SessionTranscriptHistory {
+    async fn messages(&self, thread_id: &str) -> Result<Vec<Message>>;  // read_transcript (model-context replay) → message_convert
+    async fn append(&self, thread_id: &str, message: Message) -> Result<()>;
+    async fn replace(&self, thread_id: &str, messages: Vec<Message>) -> Result<()>;
+    async fn clear(&self, thread_id: &str) -> Result<()>;
+}
+```
+
+Hard requirements, each with its own test:
+
+- `messages()` MUST route through the **model-context** replay path, so
+  compaction records replace the accumulator and `interrupted` partials are
+  skipped. A test must construct a compacted transcript and assert
+  `messages()` == `read_transcript()`, not the raw line set.
+- `replace()` MUST map onto the compaction-record path
+  (`append_transcript_turn`'s reduction branch), **not** a file rewrite. The
+  append-only invariant is the format's core property; a trait default that
+  clears-then-appends would destroy history.
+- `clear()` semantics must be decided explicitly — truncate vs. start a new
+  stem. Whichever, write it in the doc comment.
+
+**Exit:** compaction and interrupted-partial round-trip tests green; the
+byte-identity assertion against the pre-change reader passes.
+
+### S4 — Route the harness through the trait
+
+The turn path takes `Arc<dyn ChatHistory>` instead of calling transcript free
+functions. The 24 consumers that need display records, usage rollups, or path
+resolution keep using the concrete type — that is correct, not debt.
+
+**Exit:** `agent_harness_e2e` + `scripts/test-rust-with-mock.sh` green;
+`threads/transcript_view` projection output unchanged (golden test).
+
+### S5 — Shadow soak, then remove the parallel path
+
+One release with both paths live and a read-side comparison logged on mismatch
+(never panic — a mismatch on a user's real transcript must degrade, not crash).
+Then delete the redundant abstraction and update the ledger.
+
+**Exit:** ledger row terminal; `docs/` transcript-derived-view note restated in
+terms of the crate trait.
+
+---
+
+### S6 — Follow-ups from the §3.5 re-examination
+
+Independent of S0–S5; each is separately shippable and none requires the
+transcript decision.
+
+1. **Unify dispatcher selection with the model layer** (§3.5.3). Merge with the
+   parent spec's DS-5b — dispatcher choice, tool-call rendering, and tool-call
+   parsing are one concern. Deliverable: the crate owns native-vs-prompt-guided;
+   OpenHuman passes the `integrations_agent` override as policy and keeps
+   `to_provider_messages` for the durable envelope. Est. host LOC removed when
+   combined with DS-5b: **~2,400**.
+2. **Upstream the message-list helpers** (§3.5.2): `tool_records_from_conversation`,
+   `stamp_tool_failures`, `parse_tool_call_id`, `short_failure_detail`,
+   `replace_last_assistant_reply` → crate `harness::message`. ~150 LOC. Small,
+   uncontroversial, do it alongside DS-5b's parity-test port.
+3. **Design a crate turn-preparation seam** (§3.5.4). A `ContextEnricher` /
+   `TurnPreparation` pipeline — ordered, fallible, returning prompt fragments +
+   metadata — so product enrichment registers instead of being hand-written into
+   `turn()`. This is a **crate roadmap proposal, not a refactor**: write the
+   design, get it accepted upstream, then migrate OpenHuman's four enrichers
+   (super-context, agent-experience, recall citations, announcements) onto it.
+   Do not start by moving code.
+4. **Continue adopting crate types field-by-field on `Agent`**, following the
+   `workspace_descriptor: tinyagents::harness::workspace::WorkspaceDescriptor`
+   precedent. This is how `Agent` converges without ever relocating — record
+   each adopted field in the ledger.
+
+**Exit:** items 1–2 landed; item 3 is an accepted-or-rejected upstream design
+doc, not an open question; item 4 has a standing ledger section.
+
+## 6. Explicitly out of scope
+
+Recorded so a later audit does not re-litigate:
+
+- `builder/` (1,699 + 666 + 96 + 55) — 21-domain host wiring, and it builds a
+  *different object* than the crate's `AgentHarness` (§3.5.1). **Permanent
+  host**, minus the dispatcher-selection carve-out in S6.1.
+- `turn/core.rs`, `turn/tools.rs`, `turn/context.rs`, `turn/session_io.rs`,
+  `turn/mod.rs`, `turn/graph.rs` — product turn preparation; the engine already
+  left in WP-3 (§3.5.2). **Permanent host**, minus the ~150 LOC of message-list
+  helpers in S6.2 and whatever S6.3's preparation seam later absorbs.
+- `runtime.rs`, `types.rs` — `AgentSession` is a bag of host handles. **Permanent host.**
+- `tool_progress.rs` (256) — already the C4 Step-5 deletion target; belongs to
+  the progress-tracing workstream (parent spec DS-5), not here.
+- `ChatMessage` itself — WP-1 settled this: it is the versioned on-disk record,
+  and replacing it with crate `Message` changes existing users' data. Under
+  Option A it does not move. Only Option B reopens it.
+
+---
+
+## 7. Risks
+
+- **Silent model-context corruption is the top risk.** If `messages()` is wired
+  to the display read path (or to a naive line replay), every compacted thread
+  feeds the model duplicated pre-compaction history. It will not throw; it will
+  degrade answers and inflate token cost. S3's compaction test is the gate.
+- **`replace()`'s trait default is dangerous here.** The crate's default clears
+  then re-appends, which the crate's own docs flag as non-atomic. Against an
+  append-only durable log it is worse than non-atomic — it is destructive.
+  Override it; never inherit it.
+- **On-disk compatibility.** Existing installs have live `session_raw` files,
+  including legacy `DDMMYYYY/` dirs. Resume must keep working across the change;
+  the `read_transcript_legacy_md` path and the flat/dated fallback both need
+  coverage in the soak.
+- **Blast radius beyond `agent/`.** 24 files across `threads`, `session_import`,
+  `learning`, `migrations`. The `threads/turn_state` derived-view contract is
+  the fragile one.
+- **≥ 80% diff-coverage merge gate.** S2/S4 touch many call sites; check
+  `diff-cover` locally before pushing rather than discovering it in CI.
+- **Two Cargo worlds** — any vendored bump (only under Option B) regenerates
+  root **and** `app/src-tauri` lockfiles.
+- **`GGML_NATIVE=OFF`** for local root-crate `cargo` runs on Apple Silicon.
+- **GPL/crates.io boundary** — under Option B, the `session_raw` format becomes
+  public API of a redistributed crate. Nothing product-specific (agent ids,
+  OpenHuman path conventions, `.md` rendering) may cross.
+
+---
+
+## 8. Summary
+
+| | |
+| --- | --- |
+| Proposed | move `harness/session/` → `tinyagents::sessions` |
+| Verdict | **rejected as a unit** — ~8,600 of 11,073 prod LOC is host wiring; `builder/factory.rs` alone imports 21 OpenHuman domains |
+| In scope | `transcript.rs` (1,997), `turn_checkpoint.rs` (105), `migration.rs` (373) — ≤ 2 host imports each |
+| Key finding | the crate already ships `harness::memory::ChatHistory` + `harness::store` stream API; OpenHuman has a **second implementation**, not a missing home |
+| Key constraint | crate `ChatHistory` cannot express compaction records, interrupted partials, or dual read paths — a naive impl corrupts model context |
+| Recommendation | **Option A** — host backend behind the crate trait; ~400 LOC, zero on-disk change, reversible |
+| Escalation | **Option B** (upstream `JsonlChatHistory`, ~2,100 LOC) only as a deliberate crate-roadmap decision |
+| `builder/factory.rs` re-check (§3.5.1) | stays — builds `Agent` (40+ fields of product session state), not `AgentHarness` (6 fields of execution config); one real carve-out: dispatcher selection duplicates crate `with_native_tool_calling` |
+| `turn/core.rs` re-check (§3.5.2) | stays — the engine left in WP-3; residue is product enrichment. ~150 LOC of message-list helpers are upstreamable |
+| The generalizable ask | the missing artifact is a crate **turn-preparation seam** (S6.3), not a relocated file — move the shape down, keep the wiring up |
+
diff --git a/docs/tinyagents-drift-ledger.md b/docs/tinyagents-drift-ledger.md
index 4c8023689f..4902acafd0 100644
--- a/docs/tinyagents-drift-ledger.md
+++ b/docs/tinyagents-drift-ledger.md
@@ -261,6 +261,23 @@ error emitted before the cap.
 | Phase 5 - workflow/team generic slices | Validation/scheduling slice evaluation | **NOT STARTED** |
 | Phase 6 - cleanup and docs | Transitional shim deletion and architecture docs | **NOT STARTED** |
 
+## Agent-Relocation Reopen Rows (2026-07-28)
+
+Opened by the maintainer decision of 2026-07-28 to move `src/openhuman/agent/`
+into `vendor/tinyagents` as a generic agent runtime, with OpenHuman coupling
+expressed as trait injection. Governing plan:
+[`specs/2026-07-28-agent-runtime-into-tinyagents-design.md`](specs/2026-07-28-agent-runtime-into-tinyagents-design.md)
+(formerly filed as `plan-agents.md`; renamed to the directory convention so both
+it and the transcript spec cross-link cleanly). These rows reopen dispositions
+that earlier documents had closed as permanently host-owned.
+
+| # | Area | Status | Evidence / action |
+| --- | --- | --- | --- |
+| AR-1 | `agent/harness/session/{builder/, turn/, runtime.rs, types.rs}` — recorded as **Permanent host** in `specs/2026-07-28-agent-session-transcript-to-tinyagents-design.md` §6 | **REOPENED — DRIFT -> tinyagents PR** | The 2026-07-28 relocation decision puts session lifecycle/assembly (~3,700 LOC) and the turn orchestration shell (~4,476 LOC) in scope as `harness::session` / `harness::session::turn` generic over host capability traits. §6 of the transcript spec keeps its analysis but no longer holds its verdict for these four areas. Blocked behind Phase 3 (config mapping) and Phase 4 (trait injection in place); relocation itself is Phase 5. |
+| AR-2 | `agent/` remainder — recorded as **STAYS (product/host)** in `tinyagents-migration-plan-2026-07-22.md` §7 | **REOPENED — narrowed, not reversed** | `agent/` is 152 files / 70,530 LOC (measured 2026-07-28). The runtime half moves; a measured **22,121 LOC** stays as the host adapter layer (`ChatMessage`, `message_convert`, `AgentProgress`, `turn_origin`, `prompts/`, `triage/`, `bus.rs`, `host_runtime.rs`, `agent/tools/`, `archivist/`, plus every impl of the ~10 new capability traits). The §7 row is annotated in place. |
+| AR-3 | Transcript format ownership — the transcript spec §4 recommended **Option A** (host-owned format) | **REOPENED — Option B selected** | Moving the session runtime down forces the `session_raw` JSONL format to become crate-owned public API (`harness::memory::JsonlChatHistory`). Recorded in the transcript spec's own header and in the plan §4.2. The §3.1 gap table (compaction-replacement records, skippable interrupted partials, dual/display-order read path, cumulative `_meta`) is a binding acceptance constraint on that implementation — it is plan Phase 2, the program's only on-disk/user-visible data risk, and is **not started**. |
+| AR-4 | Phase 0 + Phase 1 of the relocation plan | **CLOSED (2026-07-28)** | Phase 0: host-capability trait catalogue documented upstream as `vendor/tinyagents/docs/modules/harness/host.md` (the plan's original "RFC in `docs/`" wording was corrected — the crate's `AGENTS.md` / `docs/spec/README.md` forbid standalone spec files there); plan counts re-derived from the tree and corrected in the plan header. Phase 1: the ten seams + inert default impls committed in `vendor/tinyagents` on branch `agent-to-tinyagents` (`e3f06d7`). **Phases 2–7 deliberately not executed**; the submodule gitlink bump is a separate later step. |
+
 ## Closing Procedure
 
 1. For a **DRIFT -> tinyagents PR** row, branch inside `vendor/tinyagents`, port
diff --git a/docs/tinyagents-migration-plan-2026-07-22.md b/docs/tinyagents-migration-plan-2026-07-22.md
index c98b2b6763..e4d3d2362c 100644
--- a/docs/tinyagents-migration-plan-2026-07-22.md
+++ b/docs/tinyagents-migration-plan-2026-07-22.md
@@ -483,7 +483,7 @@ changes remain gated on explicit approval of that proposal.
 | `tinyagents/middleware.rs` generic middlewares | UPSTREAM case-by-case (WP-5) |
 | `tinyagents/` remainder (seam) | STAYS, shrinks |
 | `agent/` legacy `run_turn_engine` + escape hatches | ALREADY DELETED; WP-3 corrected the stale audit and runner documentation |
-| `agent/` remainder, `agent_registry/`, `agent_experience/`, `agent_memory/`, `agent_tool_policy/`, `agentbox/`, `orchestration/`, `tool_registry/` | STAYS (product/host) |
+| `agent/` remainder, `agent_registry/`, `agent_experience/`, `agent_memory/`, `agent_tool_policy/`, `agentbox/`, `orchestration/`, `tool_registry/` | **REOPENED 2026-07-28** (was: STAYS (product/host)). The maintainer decided on 2026-07-28 to relocate `src/openhuman/agent/` into `vendor/tinyagents` as a generic runtime with OpenHuman coupling expressed as trait injection — see [`specs/2026-07-28-agent-runtime-into-tinyagents-design.md`](specs/2026-07-28-agent-runtime-into-tinyagents-design.md). ~22.1k LOC still stays host-side as the adapter layer, so this row is narrowed rather than reversed; the runtime half is now in scope. Tracked as rows AR-1..AR-3 in [`tinyagents-drift-ledger.md`](tinyagents-drift-ledger.md). |
 | `routing/` | DELETED; #4783 crate router already owned the only live path (WP-2) |
 | `tool_timeout/` | HOST-OWNED: config/env state + hard-deadline enforcement; crate timeout is metadata only (WP-2 closed) |
 | `tool_status/` classification | HOST-OWNED: OpenHuman UI/security/recovery taxonomy (WP-2 closed) |
diff --git a/vendor/tinyagents b/vendor/tinyagents
index 37815400eb..f210efae74 160000
--- a/vendor/tinyagents
+++ b/vendor/tinyagents
@@ -1 +1 @@
-Subproject commit 37815400eb035f74e20b8a1e4da3c8b2a0b49a1e
+Subproject commit f210efae74784c918af4d79b76d4af2b529350bc