Skip to content

feat(plans): surface lifecycle evidence summaries#1500

Merged
esengine merged 1 commit into
esengine:mainfrom
GTC2080:GTC/lifecycle-evidence-plan-views
May 22, 2026
Merged

feat(plans): surface lifecycle evidence summaries#1500
esengine merged 1 commit into
esengine:mainfrom
GTC2080:GTC/lifecycle-evidence-plan-views

Conversation

@GTC2080

@GTC2080 GTC2080 commented May 21, 2026

Copy link
Copy Markdown
Contributor

Summary

  • Surface completed-step evidence in /plans for active plans, including verification, diff, checkpoint, and manual evidence summaries.
  • Surface compact evidence summaries for archived plans so users can inspect why completed work was considered done.
  • Show a short evidence-pending line when the strict lifecycle snapshot reports mutation since the last completed step.
  • Keep this slice UI-only: no runtime constraint semantics, prompt, tool schema, or immutable prefix changes.

Test Plan

  • npm test -- tests/slash.test.ts
  • npm test -- tests/slash.test.ts tests/plan-store.test.ts tests/handle-tool-event.test.ts tests/lifecycle-e2e.test.ts tests/lifecycle.test.ts tests/tools.test.ts
  • npm run typecheck
  • npm run lint
  • npm run verify
  • Push hook also ran npm run verify successfully: build + lint + typecheck + full test suite (257 files, 3544 passed, 10 skipped).

Refs #1285

@esengine esengine merged commit 3cc7207 into esengine:main May 22, 2026
4 checks passed
esengine added a commit that referenced this pull request May 22, 2026
…se (#1565)

* chore(release): 0.49.0 — static-history TUI, queued steers, Bing default, lifecycle plans

Headline themes:
- TUI: Static-history renderer is the only path; virtual-viewport layers removed (#1529 stages 1-4)
- Chat: queued mid-turn steer handling so input mid-render doesn't drop or fight the live frame (#1501)
- Web search: default switches to Bing; dashboard engine switcher; Mojeek dropped (#1558)
- Plans: lifecycle evidence summaries surface why a plan is ready to accept (#1500)
- Desktop: native OS notifications for approvals + completion (#1519)
- i18n: CLI command output (/mcp /sessions /prune /theme) + approval-prompt labels translated (#1524, #1560)
- Security: SSRF block in web_fetch (#1544), edit-snapshot path containment (#1454), shell redirect sandbox (#1457), Task integrity guardrail (#1516)
- Tools: per-turn dispatch-rate limit (#1356); run_command discourages shell-based edits (#1514)
- Client: DeepSeek 429 → concurrency-limit hint (#1526); timeoutMs honored with AbortSignal (#1535); --no-proxy opt-out for direct route (#1507)
- Files: read/edit/restore preserves source encoding (GB18030 / UTF-8 BOM) (#1518)
- Context: pinned constraints survive folds + full tail capture (#1515, #1552)
- Refactor: lifecycle risk policy extracted into its own module (#1557)

See CHANGELOG for the full list.

* fix(context): align fold summary prefix with main agent for cache reuse

The summarizer call was sending a bespoke "You compress conversation
history" system prompt and no tools, guaranteeing a 0% cache hit
against the main agent's just-cached prefix. Reshape the request so
system + tools + head bytes mirror the live agent's last call — the
only novel bytes are the trailing summarize instruction.

Skill-pin handling now collects bodies read-only instead of stubbing
mid-head, so the cache prefix stays unbroken. The summarize
instruction names pinned skills so the model knows not to paraphrase
their bodies (which we append verbatim regardless).

Measured on a real session at 48.7K prompt tokens:
  OLD shape: 0.0% cache hit  → $0.145 per fold
  NEW shape: 99.6% cache hit → $0.015 per fold
  saving: 89.6% per fold

* tools: add fold-cache shape + live benchmarks

bench-fold-cache-shape.mjs replays real session jsonls, simulates
OLD vs NEW summary-call shapes at the fold point, and reports
byte-level shared-prefix with the main agent's preceding request.
Pure local — no API required.

bench-fold-cache-live.mjs sends one priming + two summary calls to
DeepSeek and reports prompt_cache_hit_tokens / cost for each shape.
Used to confirm the shape change actually translates to API-side
cache hits.

---------

Co-authored-by: reasonix <reasonix@deepseek.com>
@GTC2080 GTC2080 deleted the GTC/lifecycle-evidence-plan-views branch May 31, 2026 10:43
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants