Why: The E1 quick-fix increment landed (delegate full text, MiniMax
reasoning split, sandbox deps layer, parallel tool execution with kernel
ordering) and the proposal is the master record, so its stage table and
the index row must reflect the actual progress with links.
Evidence: Agent-Native #42/#43/#44, Backend #127, Dev task
feature/agent-e1-parallel-fixes (live verification receipts: F2 zero
think-leak, F3 sandbox IMPORTS-OK, F5 concurrent overlap; eval
toolFailures 19->11, unverifiedFacts 7->12 recorded honestly).
Impact: Documents-only progress backfill; E2-E5/S0 remain unauthorized.
Why: The user asked for a researched design covering subagent use,
tiered model routing (Claude via dmxapi for complex work, MiniMax for
the rest), a millisecond/sub-second task sandbox (record-only), and a
verdict on why the agent still feels weaker than codex/claude-code/kimi.
Why: Four research threads (external frontier survey, subagent/routing
evidence, harness-vs-model attribution, local code audit and probes)
converge on role/stage routing instead of whole-task routing, and on
three corrections to the sandbox assumptions (overlay is not a snapshot;
snapshots defer conflicts to merge time; destroy must follow sealing).
Evidence: Local measurements are SELF receipts in the Dev task card
(bwrap namespace ~7ms, overlay same, docker ~142ms; MiniMax reasoning
split; dmxapi /v1/messages cache_read; EXT-16 sandbox missing the
python-docx layer). External claims carry per-item source URLs in the
proposal's section 8.
Impact: Documents-only addition: new proposal 2026-10-10 (E1-E5/S0
increments, D/R workstreams, sandbox tiers L0-L2) plus INDEX rows for it
and the previously unlisted G1 package. No product code changes; all
implementation increments stay unauthorized until approved.
Refs: proposals/2026-10-09-agent-quality-improvement-plan.md (P4/P5,
model A/B), 2026-10-09-ext-g1-b1-b3-exec-backend.md (EXT-16),
Dev task feature/agent-exec-routing-sandbox-plan.
Why: RDM G1/G2 are blocked on four base capabilities - the member agent
cannot see published project knowledge inside a run, plugin commands are
unreachable as tools, members cannot see or open conversations in shared
projects, and the isolated exec tier needs a backend seam.
Evidence: SELF - code citations verified at Dev main (runmgr.go:726-736
owner-only Retrieve; hostcaps.go:64-66 owner-only search; server.go:438-441
owner-only listProjects; store/projects.go:124-130 owner-scoped conversation
creation); bwrap availability tested on this host (2026-10-09).
Impact: Docs only. New proposal docs/proposals/2026-10-09-ext-g1-b1-b3-exec-backend.md
registering EXT-13..EXT-16 per the compat-policy template; no code change.
Refs: RDM plan V1.1 sections 3.3/3.4/5.3; owner Q1-Q8 (Q4=option A, Q2)
Why: The 2026-10-09 diagnosis on real run transcripts identified the direct
conversation path's failure chain and a phased plan was approved with six
explicit user rulings (open up tools, kernel-transcript-authoritative context,
markdown-source deliverables with all file types retained, gate demotions,
uncapped stronger-model evals, real-model eval required for behavior changes).
The plan needs a durable main record per the long-term-direction policy, and
the 2026-09-30 preview proposal's "fs tools hidden by default" ruling is
superseded by ruling 1, which must be discoverable from the index.
Evidence: SELF - the record cites the diagnosis session, the transcript
sources (pg1 + legacy SQLite, 62 assistant turns) and the before-baseline
report location on the task card; no code or pointers changed in this repo.
Impact: New proposal 2026-10-09-agent-quality-improvement-plan.md plus one
index row. Subsequent phase tasks reference this record instead of restating
the plan.
Refs: Dev task feature/agent-quality-phase01; supersedes the fs-tool default
in 2026-09-30-file-preview-and-reserved-capabilities.md §2.3.
Why: v0.2.0 is the hard prerequisite for RDM shared work, and the release
checklist referenced a stale SurfaceVersion and tag message.
Evidence: SELF - scope lines are tied to merged Backend PRs (#66-#110);
Backend #110 CI success; UI composite run 1369 shows 14 files/103 tests.
Impact: Adds docs/records/2026-10-09-base-v0.2.0-release.md and points the
compat policy and the EXT-1 proposal at the actual 2.5.0-experimental line.
Tag creation and push stay with the owner (dual-key rule).
Refs: Dev feature/base-v020-release; Backend #110
Why: U0 (merged in RDM) rules that domain logic stays downstream and the base needs seven minimal generic capabilities; the formal four-element applications are the only legal path to base changes.
Evidence: All current-state citations re-verified at Dev 34a2bbe (backend fe7c245); RDM requirement source pinned at RDM main ca72cfc.
Impact: New proposal doc + one INDEX row; no code, no surface change in this PR.
Refs: RDM U0 proposal section 5 / ruling D1; extension-compat-policy; phase-plan section 3.3.
Why: The RDM plan's 2026-10-07 snapshot (downstream at zero, N1 in
flight, O1/O3/O7 blocked) was contradicted by the RDM repo's 103 merged
PRs; the planning index registered this as an open reconciliation item
and named it the preferred follow-up to the stage-record task.
Evidence: isolated clone replay at RDM 4feb2f0 (pins=v0.1.0) - make
test exit 0, -ms1 PASS (same-source gold caveat recorded), ms0
acceptance PASS=9/SKIP=0 on a disposable postgres container, five
upload probes, and entrance probes (chat 400 vs commands 200); card/
PR snapshot JSON; all receipts SELF (RDM has no CI), stored under
docs/records/2026-10-08-rdm-status-*.json. The private minutes probe
receipt stays local by decision; only hashes and metrics are recorded.
Impact: adds plan SS2.3 (row-by-row re-verdict, MS1 seven-clause audit,
six registered gaps), marks SS2 as a historical snapshot, updates the
index milestone table and closes the RDM-snapshot open item, registers
the dual-main-record ruling and the missing-CI gap.
Refs: Dev task feature/rdm-status-review; Documents index next-step
(2026-10-08).
Why: The planning index listed the stage-record reconciliation as the
preferred next task: N1 WP6b/6c transfers, the Q1 platform-task vs
squad-run boundary, I1 reserved command consumption, and the I2 card's
dangling reference all feed N2/Q3 and RDM dependency judgments.
Evidence: Dev merges #230/#231/#234/#235/#237/#240/#242 verified in
main via git log --merges on 2026-10-08; stage claims are SELF-level
card statements, explicitly not replayed; intent command.go:18-25/78-84
checked for the Cancel/Handoff ruling.
Impact: Adds a status-backfill section (SS7) to the N1/Q1/I1 plan with
per-item done/transferred/todo ownership, an I2 status note in the
stack completion plan (the sole I2 main record), and INDEX navigation
updates; registers the truncated Q2/Q3 archive lines as a new open
item.
Refs: Dev task feature/agent-stack-stage-records; planning index
"next-step" recommendation (2026-10-08).
Why: documents main gained two plans after the index snapshot, and Dev has since merged N2, N3, Q2, and Q3.
Evidence: 21 markdown proposals are present at HEAD; merge SHAs were read from Dev origin/main git log --merges.
Impact: navigation only; proposal bodies and acceptance claims are unchanged.
Refs: Documents #43#44; Dev #244#247#248#249#250#251#253
Why: the index branch was cut before N3 and Q2/Q3 plans landed on main.
Evidence: merge-tree reported no content conflicts against origin/main 16795ed598.
Impact: bring those two proposal files into the index branch without rewriting history.
Refs: documents main
Why: N1-N3/Q1/I1-I2 are closed; per the completion doc dependency
order Q2 then Q3 are next. Both need plans grounded in current code:
squad has no topology abstraction (two modes, dormant Cond
combinators, dead FactItem.Verified), RespondDecision has no actor
attribution (the mailbox acceptance attack surface), WorkflowDef
execution compresses steps into SpawnSubagent, and adapters/a2a does
not exist.
Evidence: three-area survey with file:line citations at the pinned
baselines (agent-squad c462bc4, backend 6e02a1f); the review
equivalence baseline is quoted from backend runReview with its test
anchors; the P4 ruling is quoted verbatim from agent-harness.md.
Impact: documentation only; Q2 implementation starts after merge,
Q3 after Q2 closes.
Refs: 2026-10-02-agent-stack-completion.md Q2/Q3 sections
Why: N2 is closed; per the completion doc's dependency order N3 is
next and needs a plan grounded in current code (the crash window
between persist and intent commit is unprotected, the product
conversation path has zero durability, span names/attributes do not
follow the GenAI convention, the memory port does not exist).
Evidence: five-area survey with file:line citations at the pinned
baselines (agent-native 74aa60b, backend 7980a8a, core 0b5c774);
audit N1/N21 verified fixed, N6/N20 verified still open.
Impact: documentation only; work starts after this plan merges.
Refs: 2026-10-02-agent-stack-completion.md N3 section
Why: expose existing milestone records and distinguish source observations from combination tests.
Evidence: linked records exist at the fixed source version; proposal blobs and the observation receipt remain unchanged.
Impact: index wording and navigation only; no plan or acceptance decision changes.
Refs: docs/proposals/INDEX.md
Why: author and task-account names do not establish ownership of a plan.
Evidence: independent review found four missing owner fields in the adopted set and N2 also has none; fourteen source headers explicitly name weichen.
Impact: correct the index attribution and clarify the local N2 document adoption boundary; source proposals remain unchanged.
Refs: planning-index review P2; docs/proposals/INDEX.md
Why: make existing directions, milestones and tasks discoverable without treating document claims as acceptance.
Evidence: fixed file blobs, 55 PR API records and Git ancestry are preserved as SELF observations; document links and all 19 proposals are checked.
Impact: navigation and evidence only; original plans, approval scope and business code are unchanged.
Refs: Dev feature/planning-index; docs/proposals/INDEX.md
Why: N1/Q1/I1/I2 are closed; per the completion doc's dependency order
N2 is next and needs a plan grounded in current code (the audit's N4 is
still open; the product-side ctxasm trim is the real gap for acceptance
clause 2; MCP 2026-07-28 features are absent).
Evidence: six-area survey with file:line citations at the pinned baselines
(agent-native ead690b, backend 68addfd); audit items N2/N3/N18/N19/N22
verified fixed against current code, N4 verified still open.
Impact: documentation only; work starts after this plan merges.
Refs: 2026-10-02-agent-stack-completion.md N2 section
Why: The further-objective docs are now the system's next big-phase
target; the plan pins the two-tree-one-net product on top of the
generic platform with two hard invariants - downstream-only domain
logic and always-degradable-to-generic-agent when the plugin is off.
Evidence: docs-only change; milestone mapping verified against
further-objective 10 (W1-W16), readiness claims verified against the
pinned worktrees (EXT-1 symbols in surface.txt, v0.1.0 tags, RDM repo
seed facts as recorded in vision doc 13).
Impact: Adds one proposal; no code changes.
Refs: docs/proposals/2026-10-07-agent-stack-n1q1i1-plans.md
Why: The completion proposal defines the N1/Q1/I1 phases but not their
work packages; D1 has landed, so the three phases are now unblocked and
need file-level plans grounded in the current pins.
Evidence: docs-only change; file:line claims verified against the pinned
worktrees (native 3a110a7, squad 5a57636, intent 65aaebc, backend
e7fb276).
Impact: Adds one proposal and one link line; no code changes.
Refs: docs/proposals/2026-10-02-agent-stack-completion.md
Why: downstream parsers are unreachable through the Host handle and the base lacks xlsx/pptx parsers; MS1 needs both. The snapshot also missed interface methods, so adding one was undetectable.
Evidence: request follows compat-policy sect.6 four elements; behavior contract and limits in the proposal body (documents has no CI; verified via git diff --check recorded on the Dev task card).
Impact: docs only; compat-policy sect.3 gains one sentence, usage.md format list gains xlsx/pptx.
Refs: docs/proposals/2026-10-06-ext-5-host-parse-document.md
Why: The comparison has to say what was borrowed, what was refused, and which product behaviors changed, without copying upstream text.
Evidence: The record lists the verified security gaps and the features implemented in this task. Proposal section 2.5 links to it.
Impact: Deferred and rejected items stay deferred and rejected. Adopted context and secret behavior is no longer described as a later batch.
Refs: feature/sillytavern-review
Why: The October 3 durable note described Pico5 before packages 1-23 existed, and the stack proposal had no place for the v1.0.1 and ZCode v3.14.3 findings.
Evidence: The new record, the correction at the top of the durable note, and proposal section 2.4 link to each other. No code changes.
Impact: Documents only. Later batches can cite the adopt, hold, and reject rows.
Refs: Dev feature/pi-zcode-second-pass
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The review record still said the proposal was unmerged, but Documents PR #34 is on main and this branch is cut from that commit.
Evidence: origin/main is 76044b5, the merge of feature/agent-stack-blueprint.
Impact: One sentence in the review record. The proposal text is unchanged.
Refs: Dev feature/pi-durable-borrow
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Pico5's package is a contract sketch, but its commit and recovery rules match four verified gaps in how runs survive a hard kill.
Evidence: Reviewed earendil-works/pi @ c7cdb460a, packages/durable and docs/pico-v5.md, against the skeleton section 4.2 and the current backend store, run manager, and SSE handler.
Impact: Documents only. The record rejects taking the package as a dependency and lists what the matching backend task changes.
Refs: Dev feature/pi-durable-borrow
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The three libraries cannot be reused or recovered independently, and the tested dependency combination is not the one the product builds.
Evidence: Read-only audit at native c6d867c, squad 590fd86, intent 1dbbe81, recorded with file references in docs/records/2026-10-02-agent-stack-audit.md.
Impact: Documents only. No library code or gitlinks change in this commit. Later stages stay separate tasks.
Refs: Dev feature/agent-stack-blueprint
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The harness proposal still said the script decision was deferred, after the implementation chose both declarative workflows and two dynamic forms.
Evidence: The P4 section now states routing order, copy-on-start, step and retry caps, and the script switch.
Impact: Documentation only.
Refs: feature/agent-harness-p4
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Tool-call history is flattened into assistant text, so the model imitates calls and invents artifact ids. The fix belongs to a shared harness, not another prompt tweak.
Evidence: Proposal 2026-10-01-agent-harness.md records the 2026-10-01 session evidence, the ZCode and Claude Code patterns, and the P0-P4 acceptance.
Impact: Documents only. P0 code lands in the backend on the same branch name. P1-P4 are not implemented here.
Refs: feature/agent-harness-p0
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The base must stay unmodified by downstream products, so the roadmap, compatibility window, and plugin contract need a written proposal before further forks.
Evidence: Three proposals under docs/proposals and a short pointer in the plugin development guide.
Impact: Downstream work follows extension-point requests and a published base version. Tag commands in the compat proposal are not executed.
Refs: .task/feature-base-extension-roadmap.md
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: user approved the proposal 2026-09-30 and directed implementation.
Evidence: approval recorded in status line and D49 note.
Impact: docs-only; unlocks CF-S task start.
Why: D1-D5 were settled by the user (deps in, full-fidelity pptx, OG
card plus optional embed, dual placement); the proposal status must
reflect that before implementation starts.
Evidence: decision section rewritten with the settled choices and the
accepted trade-off on D2 (fall back to outline level with evidence only
if no Vite-compatible renderer builds).
Impact: documentation only.
Refs: task feature/file-preview-caps.
Why: the user asked for a reviewable plan covering (a) previews for
office/image/markdown/code files and web links, docked in the right rail
or the system overlay, (b) keeping artifact deletion as a capability with
no UI entry, and (c) implementing fs tools without enabling them.
Evidence: the proposal assesses each idea against current architecture,
defines the FilePreview capability component with a format matrix and
lazy-loaded office parsers, the SSRF-guarded url-preview endpoint, the
gated sandboxed fs tool family, four delivery phases with acceptance
criteria, and decision points D1-D5 for the user.
Impact: documentation only; implementation follows in a separate task
after D1-D5 are settled.
Refs: task feature/file-preview-proposal; extends 2026-09-30
ui-redesign-and-auth.md section 9.
Why: the delivery log for the 2026-09-30 afternoon fixes (part-order
fidelity, download channel, artifact file management, settings cascade)
belongs with the redesign proposal it extends, including the two durable
conventions it produced.
Evidence: adds section 9 with root causes, the render-order-equals-
storage-order rule, the compound-selector lesson for @ui shells on host
generic classes, and the full verification record (vitest/go suites plus
the 12/12 headless run).
Impact: future UI work inherits both conventions without rediscovering
the failure modes.
Refs: task feature/chat-order-artifact-files.
Why: parallel conversations in one project cannot see each other's
transcripts, which already caused duplicate delivery of the same
requirement (records/2026-09-30-lesson-parallel-session-duplication.md);
artifacts/knowledge are already project-shared, so transcripts are the
only missing channel.
Evidence: permission formula and gate matrix designed fail-closed
(project switch default off; per-conversation outbound/inbound flags
default open/shared); tool design lands the "conversation history
search" builtin planned in skeleton design 4.8.
Impact: documents only; implementation follows in core/backend/frontend
under Dev task feature/cross-session-reading.
Refs: proposals/2026-09-29-system-skeleton-design-and-plan.md 4.8/4.9;
records/2026-09-30-lesson-parallel-session-duplication.md.
Why: proposal must record the 2026-09-30 decision (avatars, cards,
settings as base capabilities plugins reuse) and where it landed.
Evidence: feature/ui-capability-platform across core (avatar
vocabulary), ui (shared components + full vocabulary renderers),
frontend (consumption); 35+ tests and headless walk green.
Impact: status line only.
Why: the user replaced the stage-2 email self-registration sketch with
admin-issued accounts (2026-09-30): no self registration, admin sets
initial passwords, first login after creation or reset forces a change.
Evidence: R2 landed on feature/auth-admin-accounts (migration v10,
auth/session APIs, CLI user subcommands, login page + forced change
gate + admin user management); store/e2e tests and a full headless
journey on the real binary are green (see that task's PR).
Impact: proposal status line only; section 5.1 sketch superseded.
Why: the backend now registers tavily_search/web_search via
Agent-Native's TavilyProvider, so the guide's not-ported reason no
longer holds.
Evidence: backend PR records the registration and runtime checks.
Impact: table row updated, library count 44 -> 46.
Refs: feature/tavily-search-tool task card.
Why: the user picked option A (task-centric) after reviewing the demos;
the proposal status must reflect the decision and where R1 landed.
Evidence: R1 delivered on feature/task-sidebar-r1 across core/backend/
frontend (contract flags, migration v8, task list APIs, TaskSidebar);
headless walk and test suites green there.
Impact: status line only; no design content change.
Why: deciding what enters the library from an external prompt catalog
needs a stated rule (carrier mechanism or future slot) and an auditable
per-item disposition, otherwise coverage drifts by reviewer taste.
Evidence: table maps every Claude Code catalog entry to a library module
or an explicit not-ported reason.
Impact: guide gains section 9; no code change.
Refs: feature/prompt-catalog-coverage task card.
Why: the prompt system's design rationale (layering, the eight module
patterns, trigger semantics, override chain) needs to live with the
docs so future prompt work follows it instead of re-deriving it.
Evidence: guide content distilled from the implemented library and the
Claude prompt catalog analysis recorded in the task card.
Impact: new docs/guides/prompt-library-design.md; no code change.
Refs: feature/prompt-library task card.
weichen
weichen