Coding Agents Don’t Need Longer History — They Need Intent Continuity | Towards Data Science

text

Retrieval asks:"What historical information might be relevant?"Verification asks:"Is that information still valid?"Intent continuity asks:"What historical intent should influence this task, right now?"

This diagram maps how an AI coding agent recovers and verifies project requirements from earlier conversations instead of relying on a longer context window or plain vector search. Interaction history moves left to right through rule-based intent extraction, then drops down and continues right to left through candidate retrieval and verification, where superseded or out-of-scope decisions get dropped before anything reaches the agent. The pipeline ends with a deterministic agent and a requirement checker, so every recovered requirement is graded the same way it was verified. The whole system runs in pure Python, with no embedding model or vector database anywhere in the chain.

python

# extractor.py (abridged)TRIGGER_PHRASES = ["must", "never", "required", "require", "prefer", "should","always", "migrating", "let's use", "default", "for now",]def _looks_like_requirement(text: str) -> bool:lower = text.lower()return any(phrase in lower for phrase in TRIGGER_PHRASES)

python

# domain_schema.pyCOMPONENT_RELATIONSHIPS = {"auth": ["security", "api"],"api": ["security", "testing"],"security": ["auth", "api"],"database": ["deployment"],"deployment": ["database"],"testing": ["api"],"ui": [],"performance": [],}

python

# compiler.py — resolution rule, applied identically for every conditiondef compile_context(context_records):provenance = {}for record in sorted(context_records, key=lambda r: r.index):provenance[record.effect_key] = record  # later overwrites earlierfields = {key: r.effect_value for key, r in provenance.items()}token_estimate = sum(len(r.text.split()) for r in context_records)return fields, provenance, token_estimate

This diagram walks through a real supersession case from the intent-continuity experiment: an early decision to use JWT-based authentication, later replaced by a decision to migrate to OAuth2. Naive lexical retrieval, the kind of behavior you’d get from plain keyword or vector similarity search, finds both records and lets the newer one win purely because it was mentioned more recently, a coincidence of ordering rather than an actual validity check. Intent-aware retrieval finds the same two records but runs an explicit verification step that determines the older record is superseded before either one reaches the coding agent. Both approaches land on the correct auth method in this particular case, which is exactly the point: one got there by luck, and the other by design, and that difference is invisible until you test a case where the ordering doesn’t happen to save you.

This bar chart shows the final task-completion results from the intent-continuity experiment across the same 8 coding tasks. A coding agent with no access to history passed 0 of 8 tasks, breaking a requirement it was never told still applied. Naive lexical retrieval, the kind of result you’d expect from basic keyword or vector-similarity search with no validity checking, passed 4 of 8. Intent-aware retrieval, which adds an explicit verification step to drop superseded or out-of-scope requirements before they reach the agent, passed all 8. The gap between naive retrieval and intent-aware retrieval is the actual finding of this experiment: retrieving related history isn’t the same as retrieving requirements the agent can currently trust.

Source: towardsdatascience.com