@vectorize-io/hindsight-coding-agents 0.8.6 → 0.8.8

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (62) hide show
  1. package/README.md +31 -21
  2. package/dist/antigravity-hook.js +278 -190
  3. package/dist/antigravity-statusline.js +30 -24
  4. package/dist/antigravity-stop-hook.js +271 -169
  5. package/dist/claude-hook.js +278 -190
  6. package/dist/claude-sessionstart-hook.js +301 -212
  7. package/dist/claude-stop-hook.js +271 -169
  8. package/dist/cline.js +258 -214
  9. package/dist/codebuddy-hook.js +278 -190
  10. package/dist/codebuddy-sessionstart-hook.js +301 -212
  11. package/dist/codebuddy-stop-hook.js +271 -169
  12. package/dist/codex-hook.js +278 -190
  13. package/dist/codex-sessionstart-hook.js +301 -212
  14. package/dist/codex-stop-hook.js +271 -169
  15. package/dist/copilot-hook.js +278 -190
  16. package/dist/copilot-sessionstart-hook.js +301 -212
  17. package/dist/copilot-stop-hook.js +271 -169
  18. package/dist/cursor-hook.js +278 -190
  19. package/dist/cursor-sessionstart-hook.js +301 -212
  20. package/dist/cursor-stop-hook.js +271 -169
  21. package/dist/daemon-start.js +20 -16
  22. package/dist/dcode-hook.js +278 -190
  23. package/dist/dcode-sessionstart-hook.js +301 -212
  24. package/dist/dcode-stop-hook.js +271 -169
  25. package/dist/deepen.js +98 -83
  26. package/dist/devin-hook.js +278 -190
  27. package/dist/devin-sessionstart-hook.js +301 -212
  28. package/dist/devin-stop-hook.js +271 -169
  29. package/dist/droid-hook.js +278 -190
  30. package/dist/droid-sessionstart-hook.js +301 -212
  31. package/dist/droid-stop-hook.js +271 -169
  32. package/dist/dsh.js +309 -251
  33. package/dist/grok-hook.js +278 -190
  34. package/dist/grok-sessionstart-hook.js +301 -212
  35. package/dist/grok-stop-hook.js +271 -169
  36. package/dist/hindsight-seed.js +35 -26
  37. package/dist/index.js +310 -252
  38. package/dist/installer.js +172 -68
  39. package/dist/kilo.js +310 -252
  40. package/dist/kimi-hook.js +278 -190
  41. package/dist/kimi-sessionstart-hook.js +301 -212
  42. package/dist/kimi-stop-hook.js +271 -169
  43. package/dist/mcp-server.js +165 -148
  44. package/dist/opencode2.js +310 -252
  45. package/dist/pi.js +309 -251
  46. package/dist/prime-agent.js +309 -251
  47. package/dist/qwen-hook.js +278 -190
  48. package/dist/qwen-sessionstart-hook.js +301 -212
  49. package/dist/qwen-stop-hook.js +271 -169
  50. package/dist/status.js +134 -117
  51. package/dist/traecode-hook.js +278 -190
  52. package/dist/traecode-sessionstart-hook.js +301 -212
  53. package/dist/traecode-stop-hook.js +271 -169
  54. package/dist/workbuddy-hook.js +278 -190
  55. package/dist/workbuddy-sessionstart-hook.js +301 -212
  56. package/dist/workbuddy-stop-hook.js +271 -169
  57. package/dist/zcode-hook.js +278 -190
  58. package/dist/zcode-sessionstart-hook.js +301 -212
  59. package/dist/zcode-stop-hook.js +271 -169
  60. package/package.json +2 -1
  61. package/plugin.json +1 -1
  62. package/skill/SKILL.md +31 -26
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@vectorize-io/hindsight-coding-agents",
3
- "version": "0.8.6",
3
+ "version": "0.8.8",
4
4
  "repository": {
5
5
  "type": "git",
6
6
  "url": "https://github.com/vectorize-io/hindsight.git",
@@ -107,6 +107,7 @@
107
107
  "smol-toml": "^1.8.0",
108
108
  "tsup": "^8.3.0",
109
109
  "typescript": "^5.6.0",
110
+ "undici": "^6.29.1",
110
111
  "vitest": "^4.1.12",
111
112
  "zod": "^4.4.3"
112
113
  },
package/plugin.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "hindsight-coding-agents",
3
- "version": "0.8.6",
3
+ "version": "0.8.8",
4
4
  "description": "Long-term project memory for coding agents",
5
5
  "skills": "./skill",
6
6
  "hooks": "./hooks/hooks.json",
package/skill/SKILL.md CHANGED
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: hindsight-coding-agent
3
- description: How this machine's Hindsight coding-agent memory works — the plugin behind the 🧠 banner. Use when the user says "store/remember this in hindsight", asks what the memory/knowledge pages are, wants to configure per-repo memory (disable, rename banks, git depth), or something memory-related looks broken.
3
+ description: How this machine's Hindsight coding-agent memory works — the plugin behind the 🧠 banner. Use when the user says "store/remember this in hindsight", asks what the memory/pages are, wants to configure per-repo memory (disable, rename banks, git depth), or something memory-related looks broken.
4
4
  ---
5
5
 
6
6
  <!-- GENERATED from README.md (its skill:begin regions) + skill-src/preamble.md.
@@ -18,11 +18,11 @@ explains what happens automatically, which tools you have, and how to configure
18
18
  `↳ memory bank “coding-agent::<repo>”`). Worktrees share the main repo's bank.
19
19
  - **Ingestion builds itself**: on first open, the bank is seeded from recent commit messages and a
20
20
  read-only codebase survey; every session start, a background engine tops it up (new commits, new
21
- conversations) and keeps 5 knowledge pages current. There is NO ingest command to run.
21
+ conversations) and keeps 5 pages current. There is NO ingest command to run.
22
22
  - **Session synthesis**: by default, the first prompt of a session triggers one deep memory
23
- synthesis (`reflect`) injected into context. `autoInject` switches the source: `pages` (knowledge
24
- page search hits), `recall` (recalled observations), or `none` (nothing injected; the agent
25
- searches the knowledge pages first and reflects only when they are too shallow).
23
+ synthesis (`reflect`) injected into context. `autoInject` switches the source: `pages` (page
24
+ search hits), `recall` (recalled observations), or `none` (nothing injected; the agent
25
+ searches the pages first and reflects only when they are too shallow).
26
26
  - **Write-back**: the session transcript is retained into the bank automatically at session end
27
27
  (per-turn on opencode). The user never needs to "save" a conversation.
28
28
 
@@ -41,9 +41,9 @@ When the user says "store this in hindsight" / "remember this":
41
41
 
42
42
  ## Retrieving
43
43
 
44
- - `hindsight_search_knowledge_pages(query)` — FIRST STOP for project questions (components,
44
+ - `hindsight_search_pages(query)` — FIRST STOP for project questions (components,
45
45
  conventions, past decisions, initiatives). Server-side hybrid search, fast.
46
- - `hindsight_read_knowledge_page(page_id)` / `hindsight_list_knowledge_pages` — read pages fully.
46
+ - `hindsight_read_page(page_id)` / `hindsight_list_pages` — read pages fully.
47
47
  - `hindsight_reflect(query)` — deep reasoning over the whole memory for WHY questions and exact
48
48
  decided values; slower (seconds), use deliberately.
49
49
  - Credit visibly whenever memory informs an answer: start that part with
@@ -60,7 +60,7 @@ source contradicts it), FIX THE RECORD — don't just ignore it. Call
60
60
  checked (file/commit/output). Quote exact values verbatim.
61
61
 
62
62
  Newer facts supersede older ones in retrieval, so one clear correction permanently outranks the
63
- stale memory. Do this whenever you catch a wrong injected memory, a stale knowledge-page claim, or
63
+ stale memory. Do this whenever you catch a wrong injected memory, a stale page claim, or
64
64
  an outdated decision — silent disregard leaves the trap armed for the next session.
65
65
 
66
66
  ## Install / update
@@ -80,9 +80,11 @@ command again** — it re-copies the runtime in place.
80
80
 
81
81
  Day to day you should not have to: once a day, a session start checks npm and re-stages a newer
82
82
  runtime in the background (`autoUpdate`, on by default — set it to `false` to pin the version you
83
- have). That is the `update` command above, which refreshes the copy every wired agent already
84
- points at and deliberately touches no host config; re-run `install` yourself after a release that
85
- adds a new hook, or to wire another agent.
83
+ have). It only replaces a runtime that `npx` installed: a copy from `npm i -g`, a project dependency
84
+ or a local checkout is left alone. Running `update` or `install` yourself is different — it re-stages
85
+ the published release over whatever is installed, a local build included. `update` refreshes the copy
86
+ every wired agent already points at and deliberately touches no host config; re-run `install`
87
+ yourself after a release that adds a new hook, or to wire another agent.
86
88
 
87
89
  ## Local daemon settings (daemon mode)
88
90
 
@@ -143,7 +145,7 @@ what reads it:
143
145
  authentication or rotating the key is picked up on the next call with nothing to restart —
144
146
  otherwise a rotation would leave a long-running agent failing every memory call until it was
145
147
  restarted. Everything else follows the table: `apiUrl`, `disabled`, bank routing, `gitIngest`, and
146
- the survey and knowledge-page settings.
148
+ the survey and page settings.
147
149
 
148
150
  `hindsight_diagnose` reports both sides of that gap — what the file says now, and what the running
149
151
  client is actually using.
@@ -211,20 +213,20 @@ hook by Codex...), so one shared config serves several agents side by side:
211
213
  | `defaultBankConfig` | — | bank-config fields of your own for the banks the plugin shapes, e.g. `{"enable_observations": false, "enable_auto_consolidation": false, "mental_model_min_refresh_interval_seconds": 21600}`. Keys are the bank-config API's own field names. Written under the same additive rule as the rest: only where the bank does not define the field, so a bank the plugin creates is born with these instead of the server's defaults and a value you set in the control plane is never overwritten. Wins over the template on a key both name (`enable_observations`); `retain_strategies`, `entity_labels` and `retain_extraction_mode` are refused, since the plugin governs them itself. Ignored with `manageBankConfig: false` — see **A bank you shape yourself** below. File-only, like `recallOptions`; in a `banks.<id>` section it replaces the global map rather than merging into it |
212
214
  | `observationScopes` | `"shared"` | how consolidation groups observations: `"shared"` (default) = ONE global scope per bank, so every agent on a repo builds one set of beliefs; also `"combined"` (the server default), `"per_tag"`, `"all_combinations"`, `[["t"]]`; `"per_source"` adds a scope per `source:` kind alongside the global one, so commit knowledge and conversation knowledge consolidate apart |
213
215
  | `disabled` | `false` | hard off-switch (inert plugin/hook — a no-memory baseline) |
214
- | `reflectTimeoutMs` | `20000` | **automatic** session-reflect timeout; on hook harnesses the installer registers a 30s prompt-hook timeout, so going above ~20s also means raising that hook's `timeout` in the host's config, or the host kills the hook mid-reflect; on timeout or a 5xx the hook falls back to knowledge-page search, then to a raw recall of observations (recorded) |
216
+ | `reflectTimeoutMs` | `20000` | **automatic** session-reflect timeout; on hook harnesses the installer registers a 30s prompt-hook timeout, so going above ~20s also means raising that hook's `timeout` in the host's config, or the host kills the hook mid-reflect; on timeout or a 5xx the hook falls back to page search, then to a raw recall of observations (recorded) |
215
217
  | `reflectToolTimeoutMs` | `330000` | timeout for the agent-invoked `hindsight_reflect` tool — a call the agent waits on, whose high-budget synthesis on a populated bank runs for minutes. Defaults above the server's own reflect wall timeout (`HINDSIGHT_API_REFLECT_WALL_TIMEOUT`, 300s) so the server decides when to give up. Unset, it inherits an explicitly raised `reflectTimeoutMs`, but a short one never lowers it |
216
218
  | `injectTimeoutMs` | `7000` | retrieval timeout in milliseconds for `autoInject: "pages"` and `autoInject: "recall"`; also the **shared** budget for page search then recall after a reflect timeout/5xx (recall gets only the time left after page search). Set e.g. `2000` to limit turn latency or `15000` for a slower self-hosted bank. Environment fallback: `HINDSIGHT_INJECT_TIMEOUT_MS`. On hook harnesses, injection must fit the host's prompt-hook timeout (30s by default); for reflect with fallback, allow for **`reflectTimeoutMs` + `injectTimeoutMs`**, and raise the host hook's `timeout` when needed |
217
219
  | `reflectBudget` | `"high"` | reflect budget for the `hindsight_reflect` tool: `"low"`, `"mid"` or `"high"`. Drop it on a large bank where high-budget synthesis exceeds the server's wall timeout. The automatic session-start reflect always uses `"low"` to fit its hook window and is unaffected |
218
- | `autoInject` | `"reflect"` | what to inject once, on the session's **first prompt**: `"reflect"` = a low-budget reflect synthesis (on timeout/5xx it falls back to page search, then recall); `"pages"` = the knowledge pages matching the prompt by search; `"recall"` = the bank's memories recalled for the prompt (what it asks for is `recallOptions`, observations by default); `"none"` = nothing — the agent searches knowledge pages first and reflects only when they are too shallow. `"pages"` and `"recall"` are retrieval only (no LLM), their time budget is `injectTimeoutMs`, and when one finds nothing for the prompt it tries again on the next one, up to 5 prompts |
220
+ | `autoInject` | `"reflect"` | what to inject once, on the session's **first prompt**: `"reflect"` = a low-budget reflect synthesis (on timeout/5xx it falls back to page search, then recall); `"pages"` = the pages matching the prompt by search; `"recall"` = the bank's memories recalled for the prompt (what it asks for is `recallOptions`, observations by default); `"none"` = nothing — the agent searches pages first and reflects only when they are too shallow. `"pages"` and `"recall"` are retrieval only (no LLM), their time budget is `injectTimeoutMs`, and when one finds nothing for the prompt it tries again on the next one, up to 5 prompts |
219
221
  | `autoReflect` | `true` | **deprecated** — use `autoInject`. Still honoured (`false` = `autoInject: "none"`), ignored when `autoInject` is set, and logs a deprecation warning |
220
- | `pageSearchLimit` | `3` | knowledge pages ONE search returns. Applies to every search of the bank — the `autoInject: "pages"` injection, the reflect fallback, and the agent's own `hindsight_search_knowledge_pages` tool — because the limit lives on the client they all share |
222
+ | `pageSearchLimit` | `3` | pages ONE search returns. Applies to every search of the bank — the `autoInject: "pages"` injection, the reflect fallback, and the agent's own `hindsight_search_pages` tool — because the limit lives on the client they all share |
221
223
  | `recallOptions` | see description | overrides merged key-by-key into the body of every recall — the `autoInject: "recall"` source and the reflect fallback. Keys are the API's own recall parameters, passed straight through, so anything recall accepts is settable without a new option here; `query` is the one field it cannot replace. The default body is `{"types": ["observation"], "budget": "low", "max_tokens": 2000, "include": {"entities": null}}`, and what you set is merged over it one key at a time — `{"max_tokens": 4000}` changes the budget and leaves the rest alone. Observations are the consolidated layer, so they answer best per token, but a bank with **consolidation disabled never grows any** and the default recall comes back empty on it: set `{"types": ["world", "experience"]}` there, or `{"types": null}` for every type. File-only, like `retainMetadata` — an object does not flatten into an env var |
222
- | `toolGuideExtra` | — | your own guidance on how the agent should treat memory, added **after** the built-in tool guide (at session start and on every refresh) and after the crediting note returned with `hindsight_search_knowledge_pages` results. It adds to the built-in text, never replaces it. Set it per harness or per bank like any other key, e.g. `"Memory is a past record, not current state: verify any claim against the code before acting on it."` |
223
- | `pageRefreshEveryTurns` | `1` | refetch the knowledge pages and re-inject the page roster + tool guide every N user turns (`0` also means 1) |
224
- | `pageTriggerType` | `"cron"` | when NEW knowledge pages refresh, i.e. what keeping them current costs — `"cron"` (default) on `pageTriggerCron` only and only when actually stale, `"auto-refresh"` after every consolidation that produced new material, `"manual"` never on their own. Auto-refresh is the most current and by far the most expensive: one synthesis per page per consolidation. Maps to the page's `trigger.refresh_cron`, or `trigger.refresh_after_consolidation` in the Hindsight API (`true` for auto-refresh, `false` for manual) |
224
+ | `toolGuideExtra` | — | your own guidance on how the agent should treat memory, added **after** the built-in tool guide (at session start and on every refresh) and after the crediting note returned with `hindsight_search_pages` results. It adds to the built-in text, never replaces it. Set it per harness or per bank like any other key, e.g. `"Memory is a past record, not current state: verify any claim against the code before acting on it."` |
225
+ | `pageRefreshEveryTurns` | `1` | refetch the pages and re-inject the page roster + tool guide every N user turns (`0` also means 1) |
226
+ | `pageTriggerType` | `"cron"` | when NEW pages refresh, i.e. what keeping them current costs — `"cron"` (default) on `pageTriggerCron` only and only when actually stale, `"auto-refresh"` after every consolidation that produced new material, `"manual"` never on their own. Auto-refresh is the most current and by far the most expensive: one synthesis per page per consolidation. Maps to the page's `trigger.refresh_cron`, or `trigger.refresh_after_consolidation` in the Hindsight API (`true` for auto-refresh, `false` for manual) |
225
227
  | `pageTriggerCron` | `"H * * * *"` | schedule for `pageTriggerType: "cron"` — UTC, standard 5-field cron, e.g. `"0 3 * * *"`. The default is hourly, each page on its own hashed minute. Sets the page's `trigger.refresh_cron`, which the API treats as mutually exclusive with `refresh_after_consolidation`; a scheduled refresh is skipped when nothing changed. Write a field as `H` to give each page its own value there — see **Spreading refreshes with `H`** below |
226
- | `pages` | every page | per-page configuration for the seeded knowledge pages, keyed by page name (case-insensitive): `false` skips a page entirely, `{"source_query": "..."}` seeds it with your question instead of the built-in one. Omitted, all five pages are seeded with their built-in queries. This is the supported way to own a page's wording — the plugin re-syncs a page whose live query differs from the one it is configured to have, so a query edited through the API or the control plane is replaced on the next session. A skipped page is **not deleted**: one already seeded keeps its content and stops being re-synced. The scoping clause is appended to your query too, so a reworded page cannot start reporting a dependency's decisions as this project's. File-only, like `recallOptions`; in a `banks.<id>` section it replaces the global map rather than merging into it |
227
- | `customPages` | — | knowledge pages of your own, seeded alongside the five above and keyed by the name they get: `{"Security posture": {"source_query": "...", "tags": ["knowledge:decision"]}}`. `source_query` is required; `tags` picks which facts feed the page and is optional — omitted, the page draws on everything the bank holds. A separate setting from `pages` on purpose, so that an unknown name there stays a typo warning rather than quietly creating a page. File-only, and replaced (not merged) by a `banks.<id>` section |
228
+ | `pages` | every page | per-page configuration for the seeded pages, keyed by page name (case-insensitive): `false` skips a page entirely, `{"source_query": "..."}` seeds it with your question instead of the built-in one. Omitted, all five pages are seeded with their built-in queries. This is the supported way to own a page's wording — the plugin re-syncs a page whose live query differs from the one it is configured to have, so a query edited through the API or the control plane is replaced on the next session. A skipped page is **not deleted**: one already seeded keeps its content and stops being re-synced. The scoping clause is appended to your query too, so a reworded page cannot start reporting a dependency's decisions as this project's. File-only, like `recallOptions`; in a `banks.<id>` section it replaces the global map rather than merging into it |
229
+ | `customPages` | — | pages of your own, seeded alongside the five above and keyed by the name they get: `{"Security posture": {"source_query": "...", "tags": ["knowledge:decision"]}}`. `source_query` is required; `tags` picks which facts feed the page and is optional — omitted, the page draws on everything the bank holds. A separate setting from `pages` on purpose, so that an unknown name there stays a typo warning rather than quietly creating a page. File-only, and replaced (not merged) by a `banks.<id>` section |
228
230
  | `autoSeed` | `true` | SessionStart: auto-seed a cold repo's bank from git history |
229
231
  | `seedLimit` | `300` | git-log document size: a full write keeps the newest commits, between half of this and this many (the window moves in steps of half), and logs how many older ones it drops |
230
232
  | `codebaseSurvey` | `true` | SessionStart: headless survey of a cold repo's structure, run only under the current harness's own CLI (Claude Code, Codex, Antigravity, opencode v1); other agents get no survey |
@@ -246,7 +248,7 @@ LLM synthesis per page per consolidation, on a repo that consolidates all day. S
246
248
  `pageTriggerType: "auto-refresh"` to go back to refreshing on every consolidation.
247
249
 
248
250
  `pageTriggerType`/`pageTriggerCron` decide only **when** a page refreshes. **How** it refreshes
249
- belongs to the server: Hindsight creates a knowledge page with a delta refresh (each pass edits the
251
+ belongs to the server: Hindsight creates a page with a delta refresh (each pass edits the
250
252
  page instead of rebuilding it) that doesn't reflect over sibling pages, and these settings merge
251
253
  over those defaults rather than replacing them.
252
254
 
@@ -284,7 +286,7 @@ file is the source of truth for these pages: to give one a different schedule, c
284
286
  page. Only the fields this plugin states are touched — a page's `mode`, its excluded siblings and
285
287
  its minimum refresh interval are left exactly as they are.
286
288
 
287
- ### Customize Knowledge Pages — `pages`
289
+ ### Customize Pages — `pages`
288
290
 
289
291
  Every repo gets the same five pages. They are a **taxonomy**, not a summary of your source: each one
290
292
  is synthesized from what the bank ingested — commit history and past conversations — and each is
@@ -405,7 +407,7 @@ it: the seed pass only visits the pages it is configured to own.
405
407
 
406
408
  Pointed at a bank, this plugin gives it the shape its ingestion needs: retain strategies for the
407
409
  kinds of document it writes (`git`, `gitlog`, `conversation`, `document`, `survey`), a `knowledge`
408
- entity-label group that routes facts to the knowledge pages, and — on a bank that has no missions of
410
+ entity-label group that routes facts to the pages, and — on a bank that has no missions of
409
411
  its own — the coding missions.
410
412
 
411
413
  **It only ever adds what is missing.** A strategy you defined, an edit you made to one of the
@@ -454,7 +456,7 @@ you configure yourself. That bank should then define the five strategies above i
454
456
  miss is **silent**: the server does not reject a retain naming a strategy the bank lacks, it logs a
455
457
  warning and extracts with the bank's own configuration — so a commit diff, a session transcript and
456
458
  a survey marker would all get the same generic treatment instead of the extraction each needs.
457
- Knowledge pages are seeded either way; `pageTriggerType` governs what they cost.
459
+ Pages are seeded either way; `pageTriggerType` governs what they cost.
458
460
 
459
461
  Like every field here it can be set per bank, which is usually where it belongs:
460
462
 
@@ -645,7 +647,7 @@ scope fills with beliefs built from chat transcripts. Only a per-document decisi
645
647
 
646
648
  It costs one extra consolidation pass per document, and it reads only `source:`, so a volatile
647
649
  provenance tag never becomes a scope. The global scope is still written first and unchanged, so the
648
- untagged observations knowledge pages read are unaffected.
650
+ untagged observations pages read are unaffected.
649
651
 
650
652
  `"per_tag"` and `"all_combinations"` split further still, and an explicit `[["project:demo"], …]`
651
653
  declares the scopes literally. `HINDSIGHT_OBSERVATION_SCOPES` sets the scalar modes; a scope list is
@@ -680,7 +682,7 @@ as a JSON line to `~/.hindsight/coding-agents-logs/diag.jsonl` (override with
680
682
 
681
683
  `reflect_failed` / `pages_failed` record the error; if you're comparing memory-on vs memory-off,
682
684
  check this file — a run whose reflects failed is a no-memory run. When the failure was a timeout or
683
- a 5xx, the hook falls back to knowledge-page search and, if no page matches, to a raw recall of the
685
+ a 5xx, the hook falls back to page search and, if no page matches, to a raw recall of the
684
686
  bank's memories: `reflect_fallback_pages` / `reflect_fallback_observations` record what each
685
687
  step returned (`*_failed` when it errored). Seed starts are logged as
686
688
  `seed_started`.
@@ -717,6 +719,9 @@ Delete its bank on the server. The bank is the **only** state this integration k
717
719
  session in that repo is a true first open — seed and survey run again from scratch. There are no
718
720
  client-side files to clean up.
719
721
 
722
+ Deleting a bank cannot be undone, so an agent never does it on its own: it names the repo and what
723
+ would be lost, and the owner deletes the bank themselves from the control plane.
724
+
720
725
  ### Marker documents you may notice
721
726
 
722
727
  Two document ids exist for the machinery's own bookkeeping. Both are safe to ignore and safe to