@playform/hook-dsh-doc-suggester
v0.2.1 - UNPUBLISHED - plan:
SEARCH-SUGGESTER-PLUGIN
The role
This package is the doc-task companion suggester for the
DeepSeek Harness plugin family (the Classic
release).
It is a DeepSeek Harness plugin that hooks the tools/post-execute waterfall, and it acts when
a call touches a documentation task - a plan, guide, skill, plugin-doc, index, site, or
package-prose path in read, grep, glob, or an edit.
The hook then prepends ONE labeled additionalContexts note that names the doc-graph companions the
task conventionally requires: the INDEX row, the frontmatter statuses/registry/ index block, the
archive style, the cross-references, the site mirror.
This package is the third consumer of the search-suggester's pattern algebra
(SEARCH-SUGGESTER-PLUGIN.md section 8).
The surfaces
- The
tools/post-execute waterfall listener: one labeled additionalContexts note, never a
content replacement.
- No tool, no service: the note is the only surface; the learning layer records through the optional
pattern service (ctx.get("pattern"), probed per use) or a bounded in-memory fallback.
Why
The documentation tree has a graph that the model must keep coherent but usually discovers late: a
plan edit must keep the INDEX row and the frontmatter statuses/registry/index block; a skill must
keep its references and the session-orientation routing table; a content change must keep the site
mirror.
Like the edit suggester, this consumer owns the NOTIFY side of the pattern: it names the companions,
never the change.
The families
Seven, priority order: Plan, Guide, Skill, PluginDoc, Index, Site, PackageProse.
Each family is a pack row: its path rules (regexes on the doc path the call names, with weights) and
its companion set - each companion a path or glob with a prior and one reason phrase ("the index
row", "the frontmatter and style rules", "the site mirror").
A companion without a reason is not emitted.
The families are pack-driven: the built-in pack (this monorepo's default) lives in
@playform/lib-dsh-pack and it is projected here as the doc/ domain.
A repository that ships .dsh/pack.yml (or a user-layer pack at
~/.dsh/playform/workspaces/<slug>.yml) gets its OWN doc/ families; a repository without a pack
stays silent.
The gate
The gate uses the same algebra as the search and edit consumers: k = sigmoid(sum(weights) - 0.6),
the candidate scoring over the pickable heuristics (see below), and the noise control - a
cooldown, a dedupe, a per-turn cap, and the already-touched filter (doc paths touched earlier this
turn are dropped; when nothing remains, the verdict is an already-touched abstention).
Every abstention and suppression is a ledger line.
The learning layer (D8)
Every emitted note - and every gated silence worth learning from (low-confidence,
already-touched) - records a decision: the family, the companion rows with their six pickable
heuristic values (scope, graph, prior, literal, history, accept), the effective weight
table, the enabled list, and a pending outcome placeholder.
The record is logged (decided ...) and stored through the optional pattern service
(ctx.get("pattern"), probed per use, never an inject); without one it lives in a bounded in-memory
fallback (storeLimit, default 512), which is per instance and documented as such.
The note opens a follow-through window counted in judged calls (never a timer): a later call
that names one of the note's companions is an accept for that companion and its family
(accepted <Family> <path>); a window that reaches learnWindow judged calls untouched closes as a
soft reject (rejected <Family> <n> companions).
Both fill the decision record's outcome and move the learned accept rates.
The score is sum over the enabled heuristics of weight * value:
| Heuristic | Value | Default weight |
|---|
scope | 1.00 - the call matched the family's path rules | 0.35 |
graph | 0.50 - the neutral graph-distance placeholder | 0.00 |
prior | the pack's prior for the companion | 0.25 |
literal | 0.50 - the neutral literal (no generated index) | 0.25 |
history | the learned per-companion accept rate (neutral 1/3) | 0.15 |
accept | the learned per-family accept rate (neutral 1/3) | 0.00 |
The default row is exactly the PoC formula, and a missing store answers the neutral 1/3, so the
default behavior is unchanged byte-for-byte.
A user can disable any heuristic (heuristics) or re-weight any of them (weights), and the
decision record plus the decided line show the choice.
Before the score, two workspace guards run: the workspace locator
(@playform/lib-dsh-pack's Locate, whose signature comes from the resolved
pack; the built-in default is Documentation/ARCHIVE-STYLE.md) abstains foreign-workspace when
the call belongs to another repository, and the existence filter drops every companion that does not
exist under that root (abstaining no-companions when the winning family has none left).
A note therefore never names a path from this repository's graph in a workspace that does not carry
it.
The delivery
The hook delivers one note and never a content replacement: the post-execute listener runs after the
ccr and the normalize family, and it only adds additionalContexts.
The note carries the plugin's own source label ({kind: "doc-suggester", form: "notice", summary}).
The judged tool set is config (tools): the read and search calls that touch documentation plus the
edits that land on it.
The waterfall discipline
The hook always awaits next() first; a pass-through returns the downstream decision unchanged; the
whole transform is fail-open (an internal error logs a warning and the decision passes through - a
note never fails a tool call).
The ledger
The lines are prefixed hook-dsh-doc-suggester: and go to logFile:
activated (...)
suggest <family> <k> <n> companions <path>
decided <family>
accepted <family> <path>
rejected <family> <n> companions
suppressed <reason> <family>
abstained <reason> <family> <k>
abstained foreign-workspace
hook-dsh-doc-suggester: <error>; the call passes through unnoted
The configuration
See SCHEME.md for the full schema.
Every knob is volatile (hot-editable, no remount).
The learning layer adds learn, learnWindow, heuristics, weights, and storeLimit.
Ships disabled - enable by explicit ACTIVATE in the profile.
| Field | Default | Meaning |
|---|
enabled | true | the plugin ships enabled |
log | true | the ledger switch (the factory's shared cell) |
logFile | ~/.dsh/playform/hook-dsh-doc-suggester.log | the ledger |
threshold | 0.75 | the gate threshold k |
tools | ["read", "grep", "glob", "write", "edit", "raw-write"] | the judged tool set |
maxCompanions | 7 | the bound on named companions |
maxNoteChars | 1200 | the note length bound |
cooldownCalls | 6 | the cooldown between notes |
maxNotesPerTurn | 3 | the per-turn cap |
exclude | ["node_modules", "Target", ".git", "dist"] | the excluded paths |
learn | true | the decision-recording layer |
learnWindow | 3 | the follow-through window (judged calls) |
heuristics | all six | the enabled heuristics |
weights | the Defaults table above | the heuristic weights |
storeLimit | 512 | the in-memory fallback bound |
The build and the tests
The build is pnpm prepublishOnly (Source/prepublishOnly.sh): the plugin build (ESM Target/, Test
tree excluded), the Test build, the harness selfcheck, and the Test type-check.
The smoke folders: Learning-Loop, Pack-Driven, Post-Execute-And-Ring, Wiring-And-Ledger,
Workspace-Gate.
The plan
License
CC0-1.0.
