docs(report): add project-context deep-dive verdict and roadmap#156
Merged
Conversation
Verdict on .codearbiter context handling vs four external memory/context archetypes (claims verified against source + Anthropic docs). Sound design; one real gap (drift/staleness). Prioritized: drift layer, scout provenance index, file-scoped JIT injection. Explicit do-not list (vectors/daemons/ transcript-parsing/MITM proxy). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017ELqqfPQUTXWJEDSwQDFe6
…rompts Harden the project-context deep-dive report into a self-contained handoff: codeArbiter internals map (creation/storage/consumption/maintenance/pruning, hook surface, injection mechanics + #16538 caveat) so a fresh session needs no re-discovery. Add two parallel /ca:brainstorming kickoff prompts: drift+provenance (the flaw-fix) and file-scoped JIT injection (enhancement). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017ELqqfPQUTXWJEDSwQDFe6
All three prioritized recommendations in this 2026-06-26 deep dive shipped in v2.6.0 — drift/staleness + scout provenance via #145, file-scoped JIT injection via #146 — so the report's to-do framing was stale. - Rename README.md -> verdict-and-roadmap.md: the dated folder already names the topic, so "README" carried no information about what the file is. - Add a status banner pointing at the shipping PRs (#145/#146), including that #146 resolved the plugin-hook additionalContext risk the report flagged. - Drop the two now-consumed brainstorming kickoff prompts; they seeded those PRs and only referenced each other and the report. Retained as the durable decision record: the "do not add vectors/daemons/ transcript-mining" verdict and the Anthropic-docs constraint table. Ref: #145, #146 Claude-Session: https://claude.ai/code/session_01LuWyr8xxjBcJ43GTSK7XGB
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What this lands
One documentation file:
docs/reports/deepdive-2026-06-26-project-context/verdict-and-roadmap.md. It is the verdict from a 2026-06-26 deep dive asking whether codeArbiter's single-project context handling (.codearbiter/*.md) is sound, benchmarked against external memory/context tools, with every external claim checked against source code and every Claude Code mechanism checked against Anthropic docs.Why keep it
The report's three prioritized recommendations already shipped in v2.6.0, so its value is now the record, not the to-do list:
feat/context-drift-provenance).feat/file-scoped-context-injection), which also settled the plugin-hookadditionalContextrisk the report flagged (claude-code #16538).What stays useful: the "do not add vectors, daemons, or transcript parsing" verdict, and a table of which Claude Code hooks can inject context. Both save re-litigating the same questions on the next context-handling proposal.
What changed on the branch
The branch first carried this report as
README.mdalongside two/ca:brainstormingkickoff prompts. The final commit:README.mdtoverdict-and-roadmap.md(the dated folder already names the topic, soREADMEdescribed nothing).Test plan
check-plugin-refs.pyPASS at commit time.coverage-auditordispatched: no source in the diff, no coverage obligation.README.mdpath or the deleted kickoff files anywhere in the repo.Tradeoff
Conflict-hierarchy level 3 (maintainability and reviewability): the report is kept as a committed decision record rather than discarded once the work shipped, so the rationale against vector and daemon approaches stays auditable for future proposals.
Ref: #145, #146
https://claude.ai/code/session_01LuWyr8xxjBcJ43GTSK7XGB