pantheon-opencode 1.5.0-beta.8 → 1.5.0

package/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.backends._legacy:_Backend"
 
 [project]
 name = "pantheon"
-version = "1.5.0-beta.8"
+version = "1.5.0"
 description = "Multi-agent orchestration framework"
 requires-python = ">=3.11"
 dependencies = []
@@ -37,10 +37,8 @@ ignore = ["E501"]
 "scripts/scrub-secrets.py" = ["N999"]
 # These modules defer optional/heavy imports until the corresponding command is used.
 "scripts/vector_memory/*.py" = ["PLC0415"]
-"tests/test_code_mode_args.py" = ["PLC0415"]
 "tests/test_code_mode_sandbox.py" = ["PLC0415", "N806"]
 "tests/test_code_mode_server.py" = ["PLC0415"]
-"tests/test_eval_store.py" = ["PLC0415", "PLR2004"]
 "tests/test_memory_mcp_server.py" = ["PLC0415", "PLR2004"]
 # Existing public APIs and test fixtures are intentionally broad/simple; refactoring
 # them would be behavior-affecting rather than a mechanical lint correction.
@@ -54,8 +52,7 @@ ignore = ["E501"]
 "scripts/vector_memory/query.py" = ["PLR0913"]
 "src/mcp/eval_store.py" = ["PLR2004"]
 "tests/test_code_mode_frontmatter.py" = ["PLR2004"]
-"tests/test_eval_judge.py" = ["PLR2004"]
-"tests/test_eval_static.py" = ["PLR2004"]
+"tests/test_eval.py" = ["PLR2004"]
 "tests/test_mcp_persistence_server.py" = ["PLR2004"]
 
 [tool.mypy]

package/scripts/doctor.mjs

@@ -23,7 +23,7 @@
 
 import { spawn as spawnAsync, spawnSync } from 'node:child_process'
 import { createHash } from 'node:crypto'
-import { existsSync, mkdirSync, readdirSync, readFileSync, statSync } from 'node:fs'
+import { existsSync, lstatSync, mkdirSync, readdirSync, readFileSync, statSync } from 'node:fs'
 import { homedir } from 'node:os'
 import { basename, dirname, join, resolve } from 'node:path'
 import { fileURLToPath } from 'node:url'
@@ -959,6 +959,35 @@ function checkVenvLayer(args) {
 // Check F.2: Code-Mode Scripts Directory
 // ---------------------------------------------------------------------------
 
+/**
+ * Return whether *dir* contains an executable code-mode target.
+ *
+ * Mirrors `_has_usable_scripts` in `scripts/code_mode_server.py`: a directory
+ * is only a valid resolver candidate when it is a real (non-symlink) directory
+ * containing a regular `.py`/`.sh` direct child. This prevents an empty project
+ * overlay from masking a lower-priority installation that actually ships
+ * scripts. Keep both implementations in sync (see tests/test_doctor_layers.mjs).
+ */
+function hasUsableScripts(dir) {
+  try {
+    if (!existsSync(dir)) return false
+    const stat = lstatSync(dir)
+    if (stat.isSymbolicLink() || !stat.isDirectory()) return false
+    return readdirSync(dir).some((name) => {
+      if (name.startsWith('.')) return false
+      const lower = name.toLowerCase()
+      if (!lower.endsWith('.py') && !lower.endsWith('.sh')) return false
+      try {
+        return statSync(join(dir, name)).isFile()
+      } catch {
+        return false
+      }
+    })
+  } catch {
+    return false
+  }
+}
+
 /**
  * Verify the code-mode scripts directory exists for the resolved runtime
  * root (project → <target>/.opencode, otherwise the global config dir).
@@ -977,7 +1006,7 @@ export function checkCodeModeDir(args) {
   // install (.opencode present) gets its runtime dir created when missing.
   // Only targets with no project layout fall back to the global config dir.
   const codeModeDir =
-    projectCandidates.find((candidate) => existsSync(candidate)) ??
+    projectCandidates.find(hasUsableScripts) ??
     (existsSync(join(target, '.opencode'))
       ? projectCandidates[0]
       : join(resolveOpenCodeConfigDir(env), '.pantheon', 'code-mode'))
@@ -1003,7 +1032,7 @@ export function resolveCodeModeDir(args) {
     join(target, '.opencode', '.pantheon', 'code-mode'),
     join(target, '.pantheon', 'code-mode'),
   ]
-  const projectDir = projectCandidates.find((candidate) => existsSync(candidate))
+  const projectDir = projectCandidates.find(hasUsableScripts)
   if (projectDir) return projectDir
   return join(resolveOpenCodeConfigDir(env), '.pantheon', 'code-mode')
 }

package/scripts/install/plugin.mjs

@@ -8,8 +8,10 @@ import { isAbsolute, join, resolve } from 'node:path'
 import { ROOT, writeIfChanged } from './shared.mjs'
 
 /**
- * Copy a plugin's runtime payload (src/index.tsx → index.tsx, dist/*,
- * package.json and package-lock.json) from source to destination.
+ * Copy a plugin's runtime payload (the bundled dist/*, package.json and
+ * package-lock.json) from source to destination. Only the bundle is copied —
+ * the raw TSX source is never shipped to the destination, so the plugin can
+ * be modularized without the loader needing relative imports.
  * @param {string} srcDir - Source plugin directory (e.g. ROOT/src/plugins/tui)
  * @param {string} dstDir - Destination plugin directory
  * @param {object} [options]
@@ -22,16 +24,11 @@ export function copyPluginFiles(srcDir, dstDir, { dryRun = false } = {}) {
   if (!dryRun) mkdirSync(dstDir, { recursive: true })
   if (!dryRun) mkdirSync(join(dstDir, 'dist'), { recursive: true })
 
-  // Copy src/index.tsx -> index.tsx
-  const srcIdx = join(srcDir, 'src', 'index.tsx')
-  if (existsSync(srcIdx)) {
-    const idxStatus = writeIfChanged(
-      join(dstDir, 'index.tsx'),
-      readFileSync(srcIdx, 'utf8'),
-      dryRun,
-    )
-    if (idxStatus === 'created') result.created++
-    else result.skipped++
+  // Drop legacy raw copies from previous installs (root index.tsx + dist/tui.tsx).
+  // The loader consumes only the bundle, so stale raws must not linger.
+  if (!dryRun) {
+    rmSync(join(dstDir, 'index.tsx'), { force: true })
+    rmSync(join(dstDir, 'dist', 'tui.tsx'), { force: true })
   }
 
   // Copy dist/* files

package/scripts/mcp_persistence_server.py

@@ -1323,7 +1323,7 @@ def build_rehydration_blocks(checkpoint: dict) -> list[str] | None:
     """Build deterministic rehydration blocks from a checkpoint dict.
 
     Pure string templating — no LLM, no embeddings. Mirrors the
-    ``<mission_context>`` convention of delegation-compaction.ts: only a
+    ``<mission_context>`` convention of the compaction-context builder: only a
     non-done goal is re-emitted. Returns None when nothing critical remains.
     """
     if not isinstance(checkpoint, dict) or not checkpoint:

package/scripts/sync-tui.mjs

@@ -10,7 +10,7 @@
  * If the user hasn't initialized yet → do nothing (silent exit).
  */
 import { execSync } from 'node:child_process'
-import { existsSync, mkdirSync, readdirSync, readFileSync, writeFileSync } from 'node:fs'
+import { existsSync, mkdirSync, readdirSync, readFileSync, rmSync, writeFileSync } from 'node:fs'
 import { homedir } from 'node:os'
 import { join } from 'node:path'
 import { fileURLToPath, pathToFileURL } from 'node:url'
@@ -58,9 +58,9 @@ function resolveConfigDir() {
 }
 
 /**
- * Copy plugin runtime files (dist/*, package.json, package-lock.json,
- * src/index.tsx) from srcDir
- * to dstDir. Skips files that are byte-identical.
+ * Copy plugin runtime files (the bundled dist/*, package.json,
+ * package-lock.json) from srcDir to dstDir. Skips files that are byte-identical.
+ * The raw TSX source is never copied — the loader consumes only the bundle.
  * @returns {{ created: number, skipped: number }}
  */
 function copyPluginFiles(srcDir, dstDir) {
@@ -69,13 +69,10 @@ function copyPluginFiles(srcDir, dstDir) {
   mkdirSync(dstDir, { recursive: true })
   mkdirSync(join(dstDir, 'dist'), { recursive: true })
 
-  // src/index.tsx → index.tsx
-  const srcIdx = join(srcDir, 'src', 'index.tsx')
-  if (existsSync(srcIdx)) {
-    const content = readFileSync(srcIdx, 'utf8')
-    if (writeIfChanged(join(dstDir, 'index.tsx'), content)) result.created++
-    else result.skipped++
-  }
+  // Drop legacy raw copies from previous installs (root index.tsx + dist/tui.tsx).
+  // The loader consumes only the bundle, so stale raws must not linger.
+  rmSync(join(dstDir, 'index.tsx'), { force: true })
+  rmSync(join(dstDir, 'dist', 'tui.tsx'), { force: true })
 
   // dist/*
   const distSrc = join(srcDir, 'dist')

package/src/agents/apollo.md

@@ -12,6 +12,7 @@ permission:
   glob: allow
   webfetch: allow
   edit: deny
+  hashline_edit: deny
   bash: deny
   task:
     "*": deny

package/src/agents/gaia.md

@@ -11,6 +11,7 @@ permission:
   grep: allow
   webfetch: allow
   edit: deny
+  hashline_edit: deny
   bash: deny
   task:
     "*": deny

package/src/agents/zeus.md

@@ -144,33 +144,11 @@ task_status(task_id="ses_xxx", wait=true)
   -> bloqueia ate completar: { state: "completed", task_result: "..." }
 ```
 
-### Pantheon Delegation Tools (plugin) — 3-tool API
+### DELEGATION_RULES (native task API)
 
-O plugin Pantheon adiciona 3 tools de delegacao gerenciada pelo BackgroundJobBoard:
-
-```
-pantheon_delegate({prompt, agent, description?, read_only?})
-  -> cria sessao filha, registra no board, retorna alias: [apo-1]
-pantheon_delegation_read({id: "apo-1"})
-  -> BLOQUEIA ate o job terminar, retorna o report markdown, marca reconciled
-  -> durante a espera, mostra o que o agente esta fazendo: seccao final "## Agent Activity"
-     (amostra as messages do child a cada ~2s; tool calls + args truncados / texto)
-pantheon_delegation_list()
-  -> lista jobs da sessao, com [unread] para jobs terminados nao lidos
-  -> jobs RUNNING mostram "last activity:" (ultima acao visivel do child)
-  -> fail-open: sem suporte a messages, formato atual inalterado
-```
-
-- **Read-only enforcement:** agentes read-only (apollo, gaia — `read_only_agents` no routing.yml) tem `edit`, `write`, `bash`, `task` NEGADOS dentro da sessao delegada (o guard de `tool.execute.before` THROW com mensagem acionavel). Use `read_only: true` no delegate para qualquer agente de investigacao.
-- **Depth-2 hard-enforced:** sessao read-only NAO cria subagentes (`task` bloqueado) — investigacao nunca vira arvore.
-- **Compactacao:** jobs em voo (running + unread terminal) sao injetados no contexto de compactacao via `experimental.session.compacting` — delegacao em andamento nao se perde ao compactar.
-
-### DELEGATION_RULES (plugin path)
-
-1. **NUNCA** polle `pantheon_delegation_list` para checar se um job terminou.
-2. Voce NAO recebe notificacao injetada no chat — politica do usuario: ZERO `task-notification` no transcript. Visibilidade de conclusao: marcador `[unread]` em `pantheon_delegation_list`, `pantheon_delegation_read({id})`, toasts TUI (pantheon-hooks) e carry-forward de compactacao.
-3. Use `pantheon_delegation_read({id})` APENAS para fan-in explicito / recuperacao de resultado sob demanda (bloqueia ate o fim).
-4. `pantheon_delegation_list` e para diagnostico, nao para polling.
+1. Todo dispatch usa `task(background=true, subagent_type=..., prompt=...)`.
+2. Recolha com `task_status(task_id=..., wait=true)` — bloqueia ate o fim, sem polling.
+3. Use `task_status(wait=true)` apenas para fan-in explicito / recuperacao sob demanda.
 
 ### Background (sempre usar)
 - **Apollo, Hermes, Aphrodite, Demeter, Hephaestus, Prometheus**
@@ -301,32 +279,11 @@ vão a idle com todos incompletos. Guards (todos no `src/pantheon/todo-enforcer.
 
 ## Wave 4 (PR #46): Empty-Result Retry + /cost + Themis Tier
 
-### Empty-Result Retry (dispatch-guard — MANUAL orchestration)
-OpenCode 1.18.x NAO permite interceptar a conclusao de `task()` via hooks,
-entao o `src/pantheon/dispatch-guard.ts` e uma lib pura usada POR VOCE na
-orquestracao (NAO esta wired no plugin):
-
-```
-import { createDispatchGuard } from '.../src/pantheon/dispatch-guard.ts'  # via code-mode ou subagente
-
-guard = createDispatchGuard({ retryOnEmpty: true, logger: { warn: console.warn } })
-
-# classificar resultado de task_status/wait:
-#   'content'      → tem texto, pronto
-#   'empty-mode1'  → SEM texto E SEM tokens (nada voltou)      → RETRY 1x
-#   'empty-mode2'  → SEM texto, MAS tokens (raciocinou, perdeu a parte de texto;
-#                    assinatura da falha themis Wave-2)         → RETRY 1x
-
-out = await guard.maybeRetry(result, async () => { ...task() de novo... })
-# out.retried=true se redisparou; CAP DURO de 1 retry — nunca 2x.
-# Se o retry voltar vazio, `out.retried=false` — NAO tente de novo: escale.
-```
-Regra: retry 1x APENAS em `empty-mode1`/`empty-mode2`. Resultado com conteudo
-nunca redispara. Apos 1 retry vazio → escalate (mesma regra do TODO Enforcer).
-
-> **Waves DEVEM usar `zeusDelegateWithRetry`** (`src/pantheon/zeus-delegate-with-retry.ts`) — encapsula `delegate → waitForTerminal → classify → retry 1x → escalate` com cap duro 1; se ainda vazio throw `ZeusEscalationError` (escale: tente outro agente, simplifique, manual).
-> Uso alto-nível: `import { zeusDelegateWithRetry } from './pantheon/zeus-delegate-with-retry.ts'` → `await zeusDelegateWithRetry({ board, client, sessionID, agent, prompt })`.
-> Uso baixo-nível: `createZeusRetryHelper().executeWithRetry(first, () => secondRead())` — classifica empty e decide retry/escalate (mesmo cap 1).
+### Empty-Result Retry (runtime — automatic)
+Empty-response detection for native `task()` subagent calls is wired at runtime
+in `task-result-guard.ts` (plugin `tool.execute.after` chain): an
+empty/whitespace-only result is converted into an explicit error so a silent
+child failure is never mistaken for success. No manual retry helper is required.
 
 ### /cost — pantheon_cost tool (WIRED no plugin)
 `pantheon_cost({ days?: number })` le o `opencode.db` READ-ONLY usando o backend

package/src/instructions/memory-protocol.instructions.md

@@ -84,7 +84,9 @@ memory_store({
     agreements: ["point1", "point2"],
     divergences: [{"issue": "...", "resolution": "..."}],
     response_rate: "X of Y",
-    themis_audit: "approved|issues"
+    themis_audit: "approved|issues",
+    precedent_used: false,
+    timestamp: "<ISO-8601>"
   },
   metadata: {
     type: "council_decision",
@@ -93,6 +95,7 @@ memory_store({
   }
 })
 ```
+`value` is JSON-serialized before storing (the MCP `memory_store.value` argument is a string).
 
 ### Read Path (Precedent Fast-Path)
 Before dispatching a new council, Zeus runs:
@@ -103,8 +106,8 @@ memory_search(question, top_k=2, namespace="council_decisions")
 Result interpretation:
 | Score | Age | Action |
 |-------|-----|--------|
-| > 0.85 | < 30 days | Return precedent as fast-path answer. Skip council dispatch entirely. |
-| > 0.85 | >= 30 days | Return with warning "Reavaliar se contexto mudou" + proceed with council |
+| > 0.85 | < 30 days | Return precedent verbatim (note "⚠️ Decisão de [data] — reavaliar se contexto mudou") as fast-path answer. Skip council dispatch entirely. |
+| > 0.85 | >= 30 days | Return with warning "Reavaliar se contexto mudou — decisão tem mais de 30 dias" + proceed with council |
 | 0.5 - 0.85 | Any | Include as context for specialists but still dispatch council |
 | < 0.5 | Any | Ignore, proceed with fresh council |
 

package/src/instructions/zeus-anti-stall.instructions.md

@@ -15,7 +15,7 @@ You MUST self-monitor for these stall conditions:
 | Symptom | Detection Rule | Recovery Action |
 |---------|---------------|-----------------|
 | Silent loop | 3+ consecutive turns with no tool call AND no visible progress | Output `[STALL_DETECTED]` and re-read your task definition. If still stuck, escalate to user with: "I appear to be stuck on [task]. Options: (1) retry with different approach, (2) delegate to specialist, (3) simplify scope." |
-| Delegation black hole | Agent dispatched but no response after 2x the timeout from routing.yml | Log the hang, cancel via `cancel_task`, dispatch to fallback agent, report to user |
+| Delegation black hole | Agent dispatched but no response after 2x the timeout from routing.yml | Log the hang, cancel via `cancel_task`, then follow the fallback chain in `## ⏱️ Timeout & Retry Enforcement` |
 | Circular delegation | Same specialist re-dispatched for same task 2+ times without progress | Break cycle: dispatch to different specialist OR escalate to user |
 | Idle after completion | All background tasks completed but no synthesis/next step for 2+ turns | Force synthesis: summarize all completed results and propose next action |
 | Context thrash | Re-reading same files repeatedly without new action | Stop re-reading. State: "Already have context on [file]. Proceeding with [action]." |
@@ -41,9 +41,7 @@ When a delegation fails (timeout, empty response, error):
 
 2. **Retry ONCE** with rephrased prompt — add: "Previous attempt failed with: [error]. Adjusted approach: [what changed]."
 
-3. **If retry also fails** → DO NOT retry a third time blindly. Instead:
-   - Dispatch to fallback agent (from routing.yml)
-   - If no fallback, escalate to user with: "Task [X] failed after retry. Options: (a) simplify, (b) different agent, (c) manual intervention."
+3. **If retry also fails** → do NOT retry blindly; follow the fallback chain and escalation protocol in `## ⏱️ Timeout & Retry Enforcement`.
 
 ## Progress Checkpoint
 

package/src/instructions/zeus-council-synthesis.instructions.md

@@ -85,10 +85,7 @@ sequenceDiagram
 ## Dispatch Sequence (9-Step Protocol)
 
 ### Step 0 — Precedent Fast-Path (Fase 1)
-Before any dispatch: `memory_search(query, top_k=2, namespace="council_decisions")`
-- Score > 0.85 AND age < 30 days → return precedent verbatim with note "⚠️ Decisão de [data] — reavaliar se contexto mudou". SKIP entire dispatch.
-- Score > 0.85 AND age > 30 days → return precedent with ⚠️ "Reavaliar se contexto mudou — decisão tem mais de 30 dias"
-- Else → proceed to Step 0b
+Run the precedent read path defined in `## Memory Protocol > Council Decisions Namespace` (`memory_search(query, top_k=2, namespace="council_decisions")`). If no precedent applies, proceed to Step 0b.
 
 ### Step 0b — Apollo Pre-Scan (Fase 2, --research flag)
 If `/pantheon --research <question>`: dispatch @apollo with 30s timeout. Inject findings as `shared_context` into ALL specialist prompts. Skip if flag absent.
@@ -190,33 +187,11 @@ task(subagent_type: "themis", prompt: "Audit this council synthesis for fidelity
 - If issues → fix each issue before delivering to user
 
 ### Step 9 — Persist & Reconcile (Fase 1)
-```
-memory_store({
-  namespace: "council_decisions",
-  key: "council:<yyyy-mm-dd>:<slug>",
-  value: JSON.stringify({
-    question, specialists, recommendation, confidence,
-    agreements, divergences, precedent_used, timestamp
-  }),
-  metadata: {type: "council_decision", specialist_count: N}
-})
-board.markReconciled("<task-id>")
-```
+Persist the decision using the write path in `## Memory Protocol > Council Decisions Namespace`, then `board.markReconciled("<task-id>")`.
 
 ## Specialist Output Format (Fase 1 — machine-parseable structured fields)
 
-Specialists MUST return these structured fields in their response:
-
-```
-## specialist_response
-**position:** <clear one-sentence position>
-**reasoning:** <2-4 sentences>
-**trade_offs:** <what's gained vs lost>
-**risks:** <what could go wrong>
-**confidence:** High | Medium | Low
-**agreement_signals:** agree: @agent1, @agent2 on [issue] | disagree: @agent3 on [issue]
-**specific_claims:** <count of specific factual claims in response>
-```
+Specialists MUST return the structured `## specialist_response` format (position, reasoning, trade_offs, risks, confidence, agreement_signals, specific_claims) defined in `## Agent Return Format > Council Specialist Response Format`.
 
 ## Domain-to-Specialist Mapping
 

package/src/instructions/zeus-timeout-retry.instructions.md

@@ -126,39 +126,14 @@ ANY NO  → full task (IMPL artifact + Themis review mandatory)
 3. **No Themis dependency** — output doesn't feed into a phase that requires review
 
 ## Subtask Return Format
-Expect a `subtask_summary` response with:
-```
-## subtask_summary
-**files_changed:** [paths]
-**summary:** What was done
-**tests:** ✅ or N/A
-**status:** complete | partial | escalated
-```
+Return the standard `## subtask_summary` defined in `## Agent Return Format` (files_changed, summary, tests, coverage, tokens, status, blockers).
 
 ## Timeout Parcial (Partial Results)
 
-Timeout parcial is ONLY for read-only, independent agents:
-- ✅ @apollo — can return partial file list ("found 7 of 12 files before timeout")
-- ✅ @gaia — can return partial literature findings
-
-- ✅ @talos — can confirm progress if hotfix times out
-- ❌ Never for implementers or reviewers — must complete or fail
-
-When dispatching with partial-OK, set expectation:
-```
-@apollo Search for auth files. Timeout parcial OK — return whatever you have.
-```
+Only agents marked ✅ in the Timeout Behavior table above may return partial results: @apollo (partial file list, e.g. "found 7 of 12 files before timeout"), @gaia (partial literature findings) and @talos (confirm progress if a hotfix times out). Never for implementers or reviewers — they must complete or fail. When dispatching with partial-OK, set the expectation: `@apollo Search for auth files. Timeout parcial OK — return whatever you have.`
 
 ---
 
 # 📊 TIMEOUT TRACKING
 
-Maintain awareness of in-flight delegations:
-
-| Agent | Timeout | Status | Partial OK? |
-|-------|---------|--------|-------------|
-| @apollo | 60s | ✅ complete | ✅ |
-| @hermes | 180s | ⏳ in progress | ❌ |
-| @themis | 120s | ⏳ in progress | ❌ |
-
-Log timeouts to `/memories/session/timeout-log.md` for later analysis.
+Track in-flight delegations against the Timeout Behavior table above. Log timeouts to `/memories/session/timeout-log.md` for later analysis.

package/src/mcp/mcp_persistence_server.py

@@ -1323,7 +1323,7 @@ def build_rehydration_blocks(checkpoint: dict) -> list[str] | None:
     """Build deterministic rehydration blocks from a checkpoint dict.
 
     Pure string templating — no LLM, no embeddings. Mirrors the
-    ``<mission_context>`` convention of delegation-compaction.ts: only a
+    ``<mission_context>`` convention of the compaction-context builder: only a
     non-done goal is re-emitted. Returns None when nothing critical remains.
     """
     if not isinstance(checkpoint, dict) or not checkpoint:

package/src/mcp/toon_codec.py

@@ -9,7 +9,7 @@ absent/fails.
 Only the standard library (``json`` + ``re``) — prohibited: external
 gateway, generative embedding.
 
-Encoding rules (mirrored byte-for-byte by ``src/pantheon/toon-codec.ts``):
+Encoding rules:
 
 - Scalars: ``None``/``True``/``False`` → ``null``/``true``/``false``;
   numbers → shortest form; strings bare when unambiguous, else
@@ -20,8 +20,7 @@ Encoding rules (mirrored byte-for-byte by ``src/pantheon/toon-codec.ts``):
 - Lists of scalars: ``- item`` lines; empty list → ``[]``.
 - Lists of dicts with uniform keys: ``@table k1|k2`` header + ``v1|v2``
   rows (savings are per payload class — ~11% on content-dominated board
-  records up to ~47% on large tabular checkpoints — see
-  ``docs/ws3-token-opt-measurements.md`` for the reproducible table).
+  records up to ~47% on large tabular checkpoints).
 - Dict values never need quoting for ``:`` (split is on the FIRST colon);
   list items / top-level scalars that look like ``key: ...`` are quoted.
 """
@@ -471,7 +470,6 @@ def toon_size_report(value: Any) -> dict[str, Any]:
     Reports BOTH chars and tokens: token ratios on tiny payloads suffer
     ceiling bias (``ceil`` rounds 161→41 vs 143→36), so the char columns are
     the honest basis and the token columns show what metering will debit.
-    Per-class numbers: see ``docs/ws3-token-opt-measurements.md``.
     """
     compact_json = json.dumps(value, ensure_ascii=False, separators=(",", ":"))
     toon = toon_encode(value)

package/src/pantheon/background-job-board.ts

@@ -2,7 +2,7 @@
  * Background Job Board — state machine for tracking background agent jobs.
  *
  * Tracks jobs through a state machine (running → completed/error/cancelled → reconciled),
- * supports alias generation per session, persistence via adapter, auto-wake signal files,
+ * supports alias generation per session, persistence via adapter, wake signal files,
  * and terminal state listeners (persist-before-notify write-ahead-log pattern).
  *
  * Pure TypeScript — zero external dependencies beyond Node.js builtins (fs/path).
@@ -123,7 +123,7 @@ export interface BoardOptions {
   /** Maximum completed jobs kept per agent for reuse (default: 3). */
   maxReusablePerAgent?: number
   /**
-   * Directory for auto-wake signal files.
+   * Directory for wake signal files.
    * When set, a `.signal.json` file is atomically written on every terminal transition.
    * When null or undefined, no signal files are written.
    */
@@ -175,7 +175,7 @@ function getAgentPrefix(agent: string): string {
  * - Strict state machine with validated transitions
  * - Per-session, per-agent alias generation (apo-1, her-2, …)
  * - Optional persistence via injected PersistenceAdapter
- * - Optional auto-wake signal files on terminal transitions
+ * - Optional wake signal files on terminal transitions
  * - Terminal state listeners with persist-before-notify guarantee
  * - expire/prune helpers for session lifecycle management
  */
@@ -652,7 +652,7 @@ export class BackgroundJobBoard {
   }
 
   /**
-   * Delete the auto-wake signal file for an alias (`<alias>.signal.json`).
+   * Delete the wake signal file for an alias (`<alias>.signal.json`).
    * No-op (false) when no signalDir is configured or the file is absent.
    * The delegate manager calls this on the spot right after auto-reconcile.
    */

package/src/pantheon/{delegation-compaction.ts → compaction-context.ts}

@@ -1,8 +1,8 @@
 /**
- * Compaction Context (Phase 4 + release-134 Phase 2) — build the context
- * blocks injected by the `experimental.session.compacting` hook so a
- * compacted session does not lose its working state: in-flight background
- * delegations, active goals and pending todos.
+ * Compaction Context (Phase 4 + release-134 Phase 2, slimmed in Fase 2 of the
+ * delegate removal) — build the context blocks injected by the
+ * `experimental.session.compacting` hook so a compacted session does not lose
+ * its working state: active goals and pending todos.
  *
  * Returns a Promise<string[]> (empty when there is nothing to preserve).
  * Section order is stable:
@@ -17,23 +17,10 @@
  *     `opts.todos`: "  [id] description — status". Omitted when the todo
  *     source is absent, disabled, unscoped (no sessionID), fails, or has
  *     no pending todos.
- *   - "Background Delegations (running):" — every running job launched by
- *     the session (active work is never capped): alias, agent, started ISO,
- *     truncated prompt.
- *   - "Background Delegations (finished, unread):" — terminal-unreconciled
- *     jobs, newest first, capped at `maxItems` (default 10, matching
- *     routing.yml background_delegation.max_compaction_items).
  *
- * Reconciled jobs are excluded — they have been read already.
- *
- * The block style mirrors board.formatForPrompt ("  [alias] description —
- * STATUS") so compaction context reads consistently with the system prompt,
- * but with the extra id/agent/started detail the compaction hook needs.
- *
- * @module delegation-compaction
+ * @module compaction-context
  */
 
-import type { BackgroundJobBoard, BackgroundJobRecord } from './background-job-board.ts'
 import type { Goal } from './goal-store.ts'
 import { createPantheonLogger } from './logger.ts'
 import type { TodoLike } from './todo-enforcer.ts'
@@ -72,56 +59,14 @@ export interface CompactionTodoSource {
 }
 
 export interface CompactionContextOptions {
-  /** Scope to jobs launched by this session; omit for all jobs. */
+  /** Scope to this session; omit to skip the per-session sections. */
   sessionID?: string
-  /** Cap on unread terminal jobs kept (default 10). */
-  maxItems?: number
   /** Goal source for <mission_context> (optional — omitted when absent). */
   goals?: CompactionGoalSource
   /** Todo source for <todo_context> (optional — omitted when absent). */
   todos?: CompactionTodoSource
 }
 
-/** Prompt truncation length for a context line. */
-const PROMPT_MAX_LEN = 100
-
-// ─── Formatting ────────────────────────────────────────────────────────
-
-/** Collapse whitespace and truncate a prompt to PROMPT_MAX_LEN chars. */
-function truncatePrompt(text: string): string {
-  const flat = text.trim().replace(/\s+/g, ' ')
-  if (flat.length <= PROMPT_MAX_LEN) return flat
-  return `${flat.slice(0, PROMPT_MAX_LEN)}…`
-}
-
-/** One-line terminal status label, mirroring formatForPrompt. */
-function terminalLabel(state: BackgroundJobRecord['state']): string {
-  switch (state) {
-    case 'completed':
-      return 'OK'
-    case 'error':
-      return 'ERR'
-    case 'cancelled':
-      return 'CAN'
-    default:
-      return state.toUpperCase()
-  }
-}
-
-function runningLine(job: BackgroundJobRecord): string {
-  return (
-    `  [${job.alias}] ${job.agent} — ${truncatePrompt(job.description)} — ` +
-    `RUNNING since ${new Date(job.launchedAt).toISOString()}`
-  )
-}
-
-function unreadTerminalLine(job: BackgroundJobRecord): string {
-  return (
-    `  [${job.alias}] ${job.agent} — ${truncatePrompt(job.description)} — ` +
-    `${terminalLabel(job.state)} ${new Date(job.updatedAt).toISOString()} [unread]`
-  )
-}
-
 // ─── Sections ──────────────────────────────────────────────────────────
 
 /**
@@ -180,58 +125,23 @@ async function todoContextBlock(opts: CompactionContextOptions): Promise<string
   return `<todo_context>\n${lines.join('\n')}`
 }
 
-/**
- * `<delegation_context>` — the existing delegation blocks, byte-for-byte
- * unchanged from Phase 4 (running, then unread terminal ≤ maxItems).
- */
-function delegationBlocks(board: BackgroundJobBoard, opts: CompactionContextOptions): string[] {
-  const maxItems = opts.maxItems ?? 10
-  const jobs = opts.sessionID !== undefined ? board.list(opts.sessionID) : board.list()
-
-  const running = jobs
-    .filter((j) => j.state === 'running')
-    .sort((a, b) => a.launchedAt - b.launchedAt)
-  const unreadTerminal = jobs
-    .filter((j) => j.terminalUnreconciled)
-    .sort((a, b) => b.updatedAt - a.updatedAt)
-    .slice(0, maxItems)
-
-  const blocks: string[] = []
-  if (running.length > 0) {
-    blocks.push(`Background Delegations (running):\n${running.map(runningLine).join('\n')}`)
-  }
-  if (unreadTerminal.length > 0) {
-    blocks.push(
-      `Background Delegations (finished, unread):\n${unreadTerminal
-        .map(unreadTerminalLine)
-        .join('\n')}`,
-    )
-  }
-  return blocks
-}
-
 // ─── Build ─────────────────────────────────────────────────────────────
 
 /**
  * Build the compaction context blocks for a session: preservation
- * directive, active goals, pending todos, and in-flight background
- * delegations. Returns an empty array when there is nothing to preserve
- * (caller skips the hook injection entirely).
+ * directive, active goals, and pending todos. Returns an empty array when
+ * there is nothing to preserve (caller skips the hook injection entirely).
  */
 export async function buildCompactionContext(
-  board: BackgroundJobBoard,
   opts: CompactionContextOptions = {},
 ): Promise<string[]> {
   const [mission, todo] = await Promise.all([missionContextBlock(opts), todoContextBlock(opts)])
-  const delegation = delegationBlocks(board, opts)
 
   // Totally-empty state → nothing to preserve; a lone directive is noise.
-  if (mission === undefined && todo === undefined && delegation.length === 0) return []
+  if (mission === undefined && todo === undefined) return []
 
-  const blocks: string[] = []
-  blocks.push(`<pantheon-context directive>\n${PANTHEON_COMPACTION_DIRECTIVE}`)
+  const blocks: string[] = [`<pantheon-context directive>\n${PANTHEON_COMPACTION_DIRECTIVE}`]
   if (mission !== undefined) blocks.push(mission)
   if (todo !== undefined) blocks.push(todo)
-  blocks.push(...delegation)
   return blocks
 }