Merge branch 'codex/simp-ui-identity-residue' into codex/simp-hide-concrete-agent-loop

# Conflicts:
#	docs/config-catalog.md
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/event-producer-consumer.md
#	packages/core/agent-loop/tests/agent.spec.ts
#	packages/core/agent-loop/tests/contract-regressions.spec.ts

packages/compact/compact-basic/README.md

@@ -6,16 +6,15 @@ This is the implementation tier of the compaction capability — see the [interf
 
 ## What it owns
 
-The abstract contract states only WHAT compaction does; this backend owns every HOW decision:
+This backend owns the compaction policy:
 
-- **Token estimation** — `estimateContentTokens()`: chars divided by the `charsPerToken` config (default 4) with per-block structural overhead (`text`/`reasoning` = `ceil(len/charsPerToken) + 4`, `tool-call` from name + arguments, `tool-result` recursive, unknown blocks via JSON length). The pressure gate estimates the NEXT request via `estimatePressure()`: the session prefix (the `agent/session-prefix` product — composed by the loop BEFORE the pre-step seam and handed through it, so the gate counts the prefix this instance will actually send in front of the history, never a stale logged one) + the derived history + the system prompt.
-- **Retention policy** — `compactIfNeeded()` walks the surface nodes tail→head summing per-node token estimates, and retains the smallest tail-run of WHOLE units (a closed step, or a single no-step node such as a pre-step `user/message` or inter-step `steering/message`) whose total reaches `retainTokens`; everything older is compacted. Retention is **turn-agnostic** — turn boundaries play no role, so a single runaway turn that alone exceeds the window compacts its OWN early closed steps rather than being retained verbatim (the failure mode that motivated dropping turn-protection: a tool-heavy turn must stay compactable or the harness dies exactly when compaction is needed). The only structural guard is **tool-pairing balance**: the compacted region's edges are balanced cuts on the surface (no unanswered tool-call crosses either edge), so it never splits a step's `assistant/message` tool-calls from their `tool/result`s. When the only compactable content left is an un-splittable open tail step, it declines (returns `null`) and retries once an older step closes. **Single-unit overflow is out of scope, by design**: if one retained unit (a single closed step, or a large pasted `user/message`) ALONE exceeds the budget, compaction cannot help and the call may go out over-budget — bounding an individual unit's size is a separate concern. `compactRegion()` enforces tool-pairing balance strictly, throwing on a boundary that would split a step. `dsh-session` exports `isToolPairingBalanced` for the check.
-- **Dynamic convergence** — no static summary-length config pretends to bound what the model will write. If framing/estimator/system overhead leaves the compacted surface above threshold, `compactIfNeeded()` re-compacts the head checkpoint up to `compactionRetries` extra times; if it still cannot get below threshold, it throws. A summary whose estimated stored size is not smaller than the shadowed content fails closed before it mutates the surface.
-- **Summarization** — `summarize()`: a `GenerateOptions` request assembled via `BlockAssembler` with a fixed system prompt that asks for a structured checkpoint (Primary Request and Intent · Key Technical Concepts · Files and Code · Errors and Fixes · Pending Tasks · Current Work · Next Step · Critical Context), every section mandatory, exact paths/commands/identifiers preserved. The request is a direct one-shot `ctx.llm.stream()` call — NOT a loop step, so it does not run `agent/request` (that seam shapes the loop's conversation requests); the model comes from `summarizationModel` falling back to the agent's own, and per-call routing happens at `llm/stream` like any other direct call. `maxTokens` is the provider-side generation cap; only text blocks from the model's reply are kept before the checkpoint is stored (reasoning is dropped so private chain-of-thought never leaks into the durable summary, and a stray `tool-call` is dropped so the synthesized `user/message` summary cannot land an orphaned call with no matching `tool-result`). The compacted region is flattened to a plain-text transcript first: text and reasoning contribute their text, and every non-text block (tool-call, tool-result, plugin-added types) contributes a type-tagged placeholder (`[tool-call: name(args)]`, `[tool-result: …]`, …) so the summarizer is told what existed rather than silently dropping it.
-- **Checkpoint framing** — the raw summary is not landed directly. `compactRegion()` wraps it in a checkpoint preamble (so a resuming model reads it as a checkpoint, not a fresh user request, and builds on the captured context rather than restating it) plus `<compacted-summary>…</compacted-summary>` tags. Because region compaction can be invoked manually, a surface may hold several checkpoints, so the framing does not claim everything after it is recent or verbatim. The tags make a prior checkpoint detectable in the transcript on the next compaction cycle: the summarization prompt then instructs the model to merge it in place (preserve still-true facts, drop stale ones) rather than re-summarize it verbatim — a cheap incremental merge that needs no extra log/event machinery. The unframed summary stays on the `compact/summary` provenance event.
-- **Surface mutation** — `compactRegion()` appends the `compact/start` → `compact/summary` → `compact/end` log records and the single `user/message` replace node carrying the framed summary (see the interface README).
-- **Auto-compaction** — an `agent/pre-step` listener delegates to `compactIfNeeded()` before every step (not just a turn's first — a tool-heavy turn grows the surface mid-turn, so a runaway turn still compacts, and per-step firing is the only moment to rescue it before overflow). `agent/pre-step` is a serial (awaited, in-order) surface-mutation checkpoint that fires after `turn/start` and BEFORE the step opens (`step/start`) and its request history is derived, so compaction mutates the surface — with its log-only `compact/*` records landing cleanly outside any step — and the loop derives once from the result: no double-derive, and the listener cannot see (or need to rewrite) an already-assembled `messages` array. The listener owns no threshold logic of its own (the single token-pressure check lives in `compactIfNeeded()`); because Cordis `serial` bails early on non-void return values, the listener returns `void` and does not use the dispatcher's bail channel as a veto surface.
-- **Failure handling** — the `compact/start … compact/end` bracket is a log-recorded lock: it makes a crash mid-summarization a detectable orphan (a `compact/start` with no `compact/end`), records provenance, and prevents a concurrent compaction. Two failure paths: a **crash** (the loop dies mid-summarization) leaves a dangling `compact/start` that is inert — `compact/*` events are log-only, the surface replacement never landed, so the full history derives fine and generic turn-repair closes the turn; a **recoverable** failure (summarization throws but the loop survives) appends `compact/end` with its `error` field set, leaving the surface untouched so the call proceeds with full history. Core session repair stays compaction-agnostic by design — it never learns about `compact/*`.
+- **Estimation** — a configurable characters-per-token heuristic counts the current session prefix supplied to pre-step, derived history, and system prompt, matching the next request rather than stale logged prefix state.
+- **Retention** — compact the oldest whole surface units while preserving a recent tail and balanced tool-call/result cuts. Turn boundaries do not protect old steps inside a runaway turn. An open indivisible tail declines until it closes; a single unit larger than the budget remains out of scope.
+- **Convergence** — retry head-checkpoint compaction up to `compactionRetries`; reject a summary that does not shrink its source, and throw if retries cannot return below threshold.
+- **Summarization** — a direct `llm/stream` call uses the configured model and cap without running the loop-only `agent/request` seam. The input transcript preserves non-text blocks as tagged placeholders; only returned text enters the checkpoint, excluding reasoning and tool calls that would leak private reasoning or create an orphaned call.
+- **Framing** — the replacement user message marks established checkpoint context with `<compacted-summary>` tags. The raw summary remains on the provenance event, and later automatic cycles merge the prior checkpoint.
+- **Lifecycle** — `compactRegion()` records its start, summary, replacement, and end. The serial `agent/pre-step` listener checks pressure before every step, outside an open step, so a tool-heavy turn remains compactable and the loop derives history once after mutation.
+- **Failure handling** — an unmatched `compact/start` is an inert crash marker because no replacement landed. Recoverable failure records an error end and leaves the surface unchanged.
 
 The protected `estimateContentTokens()` and `summarize()` methods are overridable hooks: a tokenizer-based or template-based backend can subclass `BasicCompactService` and override just those, reusing the private retention/pressure accounting and surface plumbing. `summarize()` returns the summary blocks together with the call envelope it actually used (`{ summary, model, maxTokens? }`) — the caller logs that envelope on the `compact/summary` provenance event, so an overriding backend reports its own envelope honestly.
 

packages/compact/compact-basic/src/types.ts

@@ -48,13 +48,6 @@ export type ResolvedConfig = Required<BasicCompactConfig>
 /**
  * Default `auto`/`charsPerToken` when unset and reject nonsensical numeric knobs.
  *
- * Convergence is not a static config invariant: provider generation caps can be
- * spent on hidden or surfaced reasoning tokens, and the model may emit a summary
- * of unpredictable size. The backend instead enforces convergence dynamically:
- * each committed summary must be smaller than the content it shadows, and
- * `compactIfNeeded` may re-compact up to `compactionRetries` extra times before
- * throwing if the surface still exceeds the threshold.
- *
  * @param config - the raw, unresolved backend config.
  * @returns the validated config with `auto` and `charsPerToken` defaulted.
  */

packages/compact/compact-basic/tests/compact-loop-repro.spec.ts

@@ -15,24 +15,10 @@ import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic'
 import type { SurfaceEvent } from '@deepseek-ai/dsh-session'
 
 /**
- * CBR-001 regression: a compaction checkpoint that the REAL loop lands is a
- * free surface boundary (it carries no tool-call/result pair), so it must be a
- * valid region edge on BOTH sides. A surface-anchored balance check sees that;
- * the abandoned log-position scan did not.
- *
- * The loop fires the compaction seam mid-flight, so the landed checkpoint
- * `user/message{replace}` sits at a HIGH log seq positioned beside the current
- * step even though its SURFACE position is the head. A log-position forward scan
- * from the checkpoint reaches the step's own later `assistant/message` and
- * wrongly reports the checkpoint as mid-step — refusing it as a region end. A
- * SECOND compaction that re-summarizes just that head checkpoint (region end ==
- * checkpoint) therefore throws and is swallowed, so the surface never
- * re-consolidates.
- *
- * This drives a real auto-compaction through the agent-loop and asserts the
- * landed checkpoint balances on both sides AND that re-compacting it (end ==
- * checkpoint) succeeds. RED on the log-position predicates; GREEN once alignment
- * is decided from surface tool-pairing balance.
+ * CBR-001 regression through the real loop. A replacement checkpoint has a high
+ * log seq at the surface head and carries no tool pair, so both adjacent cuts
+ * must be safe and re-compacting that checkpoint alone must succeed. This pins
+ * surface-position semantics rather than raw-log scanning.
  */
 
 const TOKENS_PER_BLOCK = 10
@@ -133,14 +119,8 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', ()
       )
       expect(checkpoints.length).toBeGreaterThan(0)
 
-      // The loop fired compaction mid-flight, so each landed checkpoint sits at a
-      // high log seq beside the step it landed in, even though its SURFACE
-      // position is the head of the range it shadowed. A checkpoint carries no
-      // tool-call/result pair (only summarized prose), so every checkpoint still
-      // on the surface must be a balanced cut on BOTH sides — the cut before it
-      // (region START) and the cut after it (region END). The abandoned
-      // log-position scan reported the END as mis-aligned because the forward log
-      // scan reached the neighbouring step's assistant/message.
+      // High log position does not make a text-only checkpoint mid-step; both
+      // its start and end cuts are balanced in surface order.
       const nodes = agent.session.surface.nodes
       for (const cp of checkpoints) {
         const index = nodes.indexOf(cp.seq)