@zhixuan92/multi-model-agent 4.7.19 → 4.8.0

package/dist/skills/mma-research/SKILL.md

@@ -2,7 +2,7 @@
 name: mma-research
 description: >-
   Use when you need external multi-source research with citations — arxiv,
-  semantic_scholar, github_search, rss, brave-with-site:-filters — for a focused
+  semantic_scholar, github_search, brave-with-site:-filters — for a focused
   question. Worker is bibliographic, not opinionated. Pair with mma-investigate
   (internal) under mma-explore for divergent landscape scans.
 when_to_use: >-
@@ -10,7 +10,7 @@ when_to_use: >-
   others do, what published methods exist) AND mmagent is running. Delegate the
   multi-source web/adapter research to a worker so the main context stays on
   judgment. NOT for codebase questions — those are mma-investigate.
-version: 4.7.19
+version: 4.8.0
 ---
 
 # mma-research
@@ -18,8 +18,8 @@ version: 4.7.19
 ## Overview
 
 Run external multi-source research via a single mmagent worker. The worker
-consults configured adapters (arxiv, semantic_scholar, github_search, rss) and
-— when Brave keys are configured — escalates to `web_search` with `site:`
+consults configured adapters (arxiv, semantic_scholar, github_search) and
+— when Brave keys are configured — escalates to Brave web search with `site:`
 filters. The worker is bibliographic: it returns a numbered narrative with a
 `## Sources used` table. It does not opinion or rank.
 
@@ -62,7 +62,7 @@ Obtain a free API key from [Semantic Scholar API](https://www.semanticscholar.or
 **Degraded behavior:**
 
 If the Semantic Scholar API key is not configured:
-- The worker continues with available adapters (arxiv, github_search, rss, brave-search)
+- The worker continues with available adapters (arxiv, github_search, brave-search)
 - Semantic Scholar queries are skipped without errors
 - Research completes successfully but may lack academic-paper coverage
 - No failure occurs; graceful fallback is automatic
@@ -157,6 +157,7 @@ Each `results[N]` is the v5 `ComposePayload`:
 | `findings` | The deliverable. `source: 'implementer'`. Empty `findings` on a research route means "no signal found" — still a valid completion. |
 | `workerSelfAssessment` | `'done'` or `'failed'` — never `done_with_concerns`. |
 | `blockId` | Always `null` — research is a task route, not register-context-block. |
+| `contextBlockId` | The terminal context block id for this read-route task (its report as a reusable block). Pass it into a later call's `contextBlockIds` for delta follow-ups. |
 
 Legacy aliases (still emitted for back-compat):
 
@@ -166,6 +167,14 @@ results[0].structuredReport.sourcesUsed[] // table of sources tried
 results[0].output                          // raw narrative report
 ```
 
+## Terminal context block
+
+Every completed **read-route** task (audit / review / debug / investigate / research) auto-registers a reusable terminal context block containing its report (headline + findings). The block id is returned on each per-task result as **`contextBlockId`**. Write routes (delegate / execute-plan / retry) return `contextBlockId: null` — their record is the commit, not a block. This block is immutable, lives for the session duration, and counts against the project's `maxEntries` quota (default 500).
+
+Use it for delta follow-ups — feed prior results' block ids into a later call's `contextBlockIds`, filtering out nulls:
+
+    contextBlockIds: priorResults.map(r => r.contextBlockId).filter((id) => id !== null)
+
 ## Best practices
 
 - Keep `researchQuestion` topical (keywords, not full sentences).

package/dist/skills/mma-retry/SKILL.md

@@ -10,7 +10,7 @@ when_to_use: >-
   re-try the failed indices only. Prefer this over re-dispatching the whole
   batch or inline-retrying — it's idempotent and preserves the original batch's
   diagnostics.
-version: 4.7.19
+version: 4.8.0
 ---
 
 # mma-retry
@@ -167,7 +167,7 @@ Each task result is the per-task wire object (`ComposePayload`):
 | `findings` | Issues surfaced by the worker or reviewer. `severity` = `critical` \| `high` \| `medium` \| `low`. `source` = `implementer` \| `reviewer`. |
 | `filesChanged` | File paths modified (empty for read-only routes). |
 | `commitSha` | Git SHA of the committed diff; `null` for read-only routes or when commit was skipped. |
-| `blockId` | `terminalBlockId` — pass to `contextBlockIds` in a follow-up task to chain results without re-inlining. |
+| `blockId` | Always `null` (retry replays write tasks; `contextBlockId` is `null` too — no terminal block). |
 
 **The stages array** (always 9 rows) is the canonical telemetry log. `outcome` is one of:
 - `advance` — stage ran and produced its payload
@@ -214,8 +214,8 @@ Retry preserves the ORIGINAL config (prompt, agentType, filePaths, reviewPolicy)
 
 ## Terminal context block
 
-Every completed task automatically registers a terminal markdown context block containing the full task report. The `blockId` is returned in each task result as `terminalBlockId`. This block is immutable, lives for the session duration, and counts against the project's `maxEntries` quota (default 500).
+Write-route tasks (delegate / execute-plan / retry) do NOT register a terminal context block — their durable record is the commit (`commitSha` + changed files). The per-task result's `contextBlockId` is always `null` for these routes. Read routes (audit / review / debug / investigate / research) return a non-null `contextBlockId`; see those skills for the delta-follow-up recipe.
 
-Note: the retry batch produces its own terminal context blocks for each re-run task. The original batch's terminal context blocks remain intact and are not overwritten.
+Note: a re-run **read-route** task registers its own terminal context block (`contextBlockId`); re-run write tasks register none. Original-batch blocks remain intact and are not overwritten.
 
 @include _shared/error-handling.md

package/dist/skills/mma-review/SKILL.md

@@ -10,7 +10,7 @@ when_to_use: >-
   AND mmagent is running. Delegate so each file reviews on its own worker; the
   main agent only decides what to merge. Review on SOURCE CODE — use mma-audit
   for prose specs / configs.
-version: 4.7.19
+version: 4.8.0
 ---
 
 # mma-review
@@ -163,7 +163,11 @@ Self-review and cross-model review are not the same thing. The whole reason to d
 
 ## Terminal context block
 
-Every completed task automatically registers a terminal markdown context block containing the full task report (headline, annotated findings, and per-file review notes). The `blockId` is returned in each task result as `terminalBlockId`. This block is immutable, lives for the session duration, and counts against the project's `maxEntries` quota (default 500).
+Every completed **read-route** task (audit / review / debug / investigate / research) auto-registers a reusable terminal context block containing its report (headline + findings). The block id is returned on each per-task result as **`contextBlockId`**. Write routes (delegate / execute-plan / retry) return `contextBlockId: null` — their record is the commit, not a block. This block is immutable, lives for the session duration, and counts against the project's `maxEntries` quota (default 500).
+
+Use it for delta follow-ups — feed prior results' block ids into a later call's `contextBlockIds`, filtering out nulls:
+
+    contextBlockIds: priorResults.map(r => r.contextBlockId).filter((id) => id !== null)
 
 **Use cases:**
 - Pass round-N review findings to round N+1 via `contextBlockIds`

package/dist/skills/multi-model-agent/SKILL.md

@@ -11,7 +11,7 @@ when_to_use: >-
   tasks — AND mmagent is running. Read this once, pick the matching mma-* skill,
   and delegate there. Applies equally whether the user invoked a superpowers
   methodology skill or asked directly.
-version: 4.7.19
+version: 4.8.0
 ---
 
 # multi-model-agent (router)
@@ -63,7 +63,7 @@ digraph picker {
 | `mma-review` | Review code for quality, security, performance, correctness. Pass acceptance checklists in the brief if you need verification-style checks. |
 | `mma-debug` | Debug a failure with a structured hypothesis |
 | `mma-investigate` | Codebase Q&A — structured answer with `file:line` citations + confidence |
-| `mma-explore` | Divergent ideation from codebase + web research — use before `superpowers:brainstorming` |
+| `mma-explore` | Divergent ideation from codebase + web research + prior-learnings recall — use before `superpowers:brainstorming` |
 | `mma-delegate` | Ad-hoc implementation / research with no plan file |
 | `mma-retry` | Re-run specific failed/incomplete tasks from a previous batch by index |
 | `mma-context-blocks` | Register a reused doc once; reference by ID across N tasks |
@@ -181,7 +181,11 @@ Context blocks are immutable after creation. To update content, register a new b
 
 ## Terminal context block
 
-Every completed task across all routes automatically registers a terminal markdown context block with the full task report. The `blockId` is in each task result as `terminalBlockId`. This block is immutable, lives for the session duration (or idle-evicts after 24 h), and counts against the `maxEntries` quota. Use `terminalBlockId` values in downstream `contextBlockIds` to chain findings across workflow steps without re-inlining report content. No caller action needed — blocks are registered server-side at task completion.
+Every completed **read-route** task (audit / review / debug / investigate / research) auto-registers a reusable terminal context block containing its report (headline + findings). The block id is returned on each per-task result as **`contextBlockId`**. Write routes (delegate / execute-plan / retry) return `contextBlockId: null` — their record is the commit, not a block. This block is immutable, lives for the session duration, and counts against the project's `maxEntries` quota (default 500).
+
+Use it for delta follow-ups — feed prior results' block ids into a later call's `contextBlockIds`, filtering out nulls:
+
+    contextBlockIds: priorResults.map(r => r.contextBlockId).filter((id) => id !== null)
 
 ## General flow
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@zhixuan92/multi-model-agent",
-  "version": "4.7.19",
+  "version": "4.8.0",
   "type": "module",
   "license": "MIT",
   "description": "Standalone HTTP server for multi-model-agent. Routes tool-invocation work to Claude, Codex, or OpenAI-compatible sub-agents with async-polling REST dispatch and installable skills for Claude Code, Gemini CLI, Codex CLI, and Cursor.",
@@ -53,7 +53,7 @@
   },
   "dependencies": {
     "@asteasolutions/zod-to-openapi": "^8.5.0",
-    "@zhixuan92/multi-model-agent-core": "^4.7.19",
+    "@zhixuan92/multi-model-agent-core": "^4.8.0",
     "gray-matter": "^4.0.3",
     "minimist": "^1.2.8",
     "proper-lockfile": "^4.1.2",